6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 1/38

Help

Contents

1. Core System1.1. Overview

1.1.1. What's new in version 21?1.1.2. What's new in version 20?1.1.3. What's new in version 19?1.1.4. What's new in version 18?1.1.5. What's new in version 17.0?1.1.6. What's new in version 16.0?1.1.7. What's new in version 15.0?1.1.8. What's new in version 14.0.11.1.9. What's new in version 14.0?

1.1.9.1. Version 14.0 compatibility with previous releases1.1.10. What's new in version 11.5?1.1.11. What's new in version 11.01.1.12. What's new in version 10.0.51.1.13. What's new in version 10.01.1.14. What's new in version 9.01.1.15. What's new in version 8.01.1.16. What's new in version 7.51.1.17. What's new in version 7.01.1.18. Windows

1.1.18.1. Designated window versus active window1.1.18.1.1. Changing the designated window

1.1.19. Status Bar1.1.20. Dialog boxes1.1.21. Variable names and variable labels in dialog box lists1.1.22. Resizing dialog boxes1.1.23. Dialog box controls1.1.24. Selecting variables1.1.25. Data type, measurement level, and variable list icons1.1.26. Getting information about variables in dialog boxes1.1.27. Command line options1.1.28. Basic steps in data analysis1.1.29. Statistics Coach

1.2. Getting Help1.2.1. Getting Help on Output Terms

1.3. Data files1.3.1. Opening data files

1.3.1.1. To open data files1.3.1.2. Data file types1.3.1.3. Opening file options1.3.1.4. Reading Excel Files1.3.1.5. Reading Excel 95 or Later Files

1.3.1.5.1. How to Read Excel 95 or Later Files1.3.1.6. Reading older Excel files and other spreadsheets1.3.1.7. Reading dBASE files1.3.1.8. Reading Stata files1.3.1.9. Reading Database Files

1.3.1.9.1. To Read Database Files1.3.1.9.2. Selecting a Data Source1.3.1.9.3. Selecting Data Fields1.3.1.9.4. Creating a Relationship between Tables

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 2/38

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.1. What's new in version 21?

Simulation. Predictive models, such as linear regression, require a set of known inputs to predictan outcome or target value. In many real world applications, however, values of inputs areuncertain. Simulation allows you to account for uncertainty in the inputs to predictive models andevaluate the likelihood of various outcomes in the presence of that uncertainty. See the topicSimulation for more information.

One-click descriptive statistics. Select variables in the Data Editor and get summary descriptivestatistics (for example, mean, median, frequency counts). Appropriate statistics are automaticallydetermined based on measurement level. See the topic Obtaining Descriptive Statistics for SelectedVariables for more information.

Read Cognos Business Intelligence data. If you have access to an IBM® Cognos® BusinessIntelligence server, you can read data packages and list reports into IBM® SPSS® Statistics. Seethe topic Reading Cognos data for more information.

Merge data files without pre-sorting. Merge data files by values of key variables without pre-sorting the files based on key values. You can also merge data files based on string keys ofdifferent defined lengths in each file and merge a case data file with multiple table-lookup files withdifferent keys in each table-lookup file. See the topic STAR JOIN for more information.

Compare datasets. Compare the data values and metadata attributes (dictionary information) oftwo datasets. See the topic Comparing datasets for more information.

Password protect and encrypt data and output files. See the topic Encrypting data files andoutput documents for more information.

Pivot table editing enhancements. After creating pivot tables, you can now:

• Toggle the display of names, values, and labels. See the topic Controlling display of variable andvalue labels for more information.

• Sort table rows. See the topic Sorting rows for more information.

• Insert rows and columns. See the topic Inserting rows and columns for more information.

• Change the output language. See the topic Changing the output language for more information.

Export output in Excel 2007 and higher format. See the topic Export output for moreinformation.

Preserve table styles when exporting output to HTML. All pivot table style information (forexample, font styles, background colors) and column widths can now be preserved. See the topicHTML options for more information.

Unicode default. SPSS Statistics now runs in Unicode mode by default instead of code page mode.See the topic Unicode mode for more information.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.2. What's new in version 20?

Maps. The Graphboard Template Chooser now includes templates for creating different types ofmap visualizations, such as choropleth maps (color maps), maps with mini-charts, and overlaymaps. IBM® SPSS® Statistics ships with several map files, but you can use the Map Conversion

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 3/38

Utility to covert your existing map shapefiles for use with the Graphboard Template Chooser. Seethe topic Using the Map Conversion Utility for more information.

Faster rendering of pivot tables. Pivot tables now render much faster than in previous versions,while retaining full support for pivoting and editing. If you used fast rendering of lightweight tablesin version 19, you will find comparable results for pivot tables in version 20 and higher, without thelimitations of lightweight tables. Users who require compatibility with versions prior to 20 canchoose to generate legacy tables (referred to as full-featured tables in version 19). See the topicPivot table options for more information.

Background, disconnected execution for production jobs. Production jobs can be run in aseparate background session on a remote server. You can submit the jobs from your localcomputer, disconnect from the remote server, reconnect later and retrieve your results. You don'tneed to keep SPSS Statistics running on your local computer. You don't even need to keep yourlocal computer turned on. Progress of remote jobs can be monitored and results retrieved from thenew Background Job Status tab of the production facility dialog.See the topic Production jobs formore information.

Ordinal Targets for Generalized linear mixed models. The Generalized linear mixed modelsprocedure now uses the information in the ordering of categories of targets with the ordinalmeasurement level. Ordinal targets are modeled with an ordinal multinomial distribution, and thetarget is linearly related to the factors and covariates via one of a number of cumulative linkfunctions. This feature is available in the Advanced Statistics add-on option.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.3. What's new in version 19?

Linear models. Linear models predict a continuous target based on linear relationships betweenthe target and one or more predictors. Linear models are relatively simple and give an easilyinterpreted mathematical formula for scoring. The properties of these models are well understoodand can typically be built very quickly compared to other model types (such as neural networks ordecision trees) on the same dataset. This feature is available in the Statistics Base add-on module.See the topic Linear models for more information.

Generalized linear mixed models. Generalized linear mixed models extend the linear model sothat: the target is linearly related to the factors and covariates via a specified link function; thetarget can have a non-normal distribution; and the observations can be correlated. Generalizedlinear mixed models cover a wide variety of models, from simple linear regression to complexmultilevel models for non-normal longitudinal data. This feature is available in the AdvancedStatistics add-on module. See the topic Generalized linear mixed models for more information.

Lightweight tables. Lightweight tables can be rendered much faster than full-featured pivottables. Although they lack the editing features of pivot tables, they can easily be converted topivot tables with all editing features enabled. See the topic Pivot table options for moreinformation.

Scoring wizard. The new scoring wizard makes it easy to apply predictive models to score yourdata, and scoring no longer requires IBM® SPSS® Statistics Server. See the topic Scoring datawith predictive models for more information.

Improved default measurement level. For data read from external sources and new variablescreated in a session, the method for determining default measurement level has been improved toevaluate more conditions than just the number of unique values. Since measurement level affectsthe results of many procedures, correct measurement level assignment is often important. See thetopic Data Options for more information.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 4/38

"Smart" output. The procedures in the Direct Marketing add-on module now provide "smart"output: simple, non-technical explanations that help you evaluate your results.

Syntax editor enhancements. You can now split the editor pane into two panes arranged withone above the other. You can indent or outdent blocks of syntax or automatically indent selectionswith a format similar to pasted syntax. A new toolbar button allows you to uncomment text thatwas previously commented out, and a new option setting allows you to paste syntax at the positionof the cursor. You can now also navigate to the next or previous syntactical error (such as anunmatched quote), making it easier to locate these errors before running the syntax. See the topicUsing the Syntax Editor for more information.

Database drivers for salesforce.com. Database drivers for salesforce.com allow an analyst toaccess data in salesforce.com just like you access data in a SQL database. Analysts can nowconnect to salesforce.com, extract data that is relevant and perform analysis.

Compiled transformations. When you use compiled transformations, transformation commands(such as COMPUTE and RECODE) are compiled to machine code at run time to improve the

performance of these transformations for datasets with a large number of cases. This featurerequires SPSS Statistics Server.

Statistics portal. Statistics portal is a Web-based interface for IBM® SPSS® Collaboration andDeployment Services users that allows them to analyze their data with the power of the SPSSStatistics engine. They run analyses from custom user interfaces authored in SPSS Statistics (withthe Custom Dialog Builder) and stored in their IBM SPSS Collaboration and Deployment ServicesRepository. Enhancements relevant to authors of custom user interfaces for Statistics portalinclude: honoring a filter, specified for the active dataset, between successive analyses; hidingsmall counts in tables generated by CROSSTABS, OLAP CUBES, and CTABLES; and displaying a set of

row and column dimensions as table layers in the CROSSTABS crosstabulation table.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.4. What's new in version 18?

Automated data preparation. Automated Data Preparation (ADP) handles the task of preparingdata for analysis, analyzing your data and identifying fixes, screening out fields (variables) that areproblematic or not likely to be useful, deriving new attributes when appropriate, and improvingperformance through intelligent screening techniques. You can use the algorithm in fully automaticfashion, allowing it to choose and apply fixes, or you can use it in interactive fashion, previewingthe changes before they are made and accept or reject them as desired. Automated DataPreparation is available in the Data Preparation add-on option. See the topic Automated DataPreparation for more information.

Bootstrapping. Bootstrapping is a robust method for determining the properties of populationestimators (like the mean, median, percentiles, and correlation and regression coefficients) whenparametric assumptions do not hold, or when inferences based on parametric assumptions aredifficult to compute. Bootstrapping is available in the new Bootstrapping add-on option. See thetopic Introduction to Bootstrapping for more information.

New nonparametric tests. Nonparametric tests make minimal assumptions about the underlyingdistribution of the data. The new nonparametric tests provide a new user interface and ModelViewer output, and include all of the tests available in the legacy nonparametric tests, including:one-sample Wilcoxon signed-rank test, one-sample confidence intervals for the binomial distribution,the related-samples marginal homogeneity test, and the Hodges-Lehman confidence interval for themedian of the difference in paired-samples and the difference in medians of two independentsamples. Pairwise and stepwise step-down multiple comparisons are also available for all kindependent samples and k related samples tests. The Jonckheere-Terpstra test is available without

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 5/38

requiring the Exact Tests add-on option. The new nonparametric tests are available in the

Statistics Base add-on option. See the topic Nonparametric Tests for more information.

Programmability enhancements. The R Integration Plug-in now supports R debugging features.Additionally, you can create pivot tables from R with multiple row and column dimensions and youcan nest multiple pivot tables under a common outline heading. R extension commands can beimplemented directly from R source code files, bypassing the need to distribute them as R packages.Also, you can bundle together all components of a custom R or Python procedure, allowing endusers to easily install the procedure without manually copying files. Complete documentation for thePython and R Integration Plug-ins is now integrated with the Help system.

Direct marketing tools. The new Direct Marketing add-on option provides a set of tools designedto improve the results of direct marketing campaigns by identifying demographic, purchasing, andother characteristics that define various groups of consumers and targeting specific groups tomaximize positive response rates. See the topic Direct Marketing for more information.

Custom Tables enhancements. The Custom Tables add-on option now offers computedcategories and significance results integrated into the same table as the values being tested. Formore information on computed categories, see Computed Categories. For more information onsignificance tests in custom tables, see Custom Tables: Test Statistics Tab.

Improved SAS data file support. You can now write data files in SAS 9 format. See the topicSaving data: Data file types for more information.

Improved Custom Dialog Builder. The Custom Dialog Builder now has a list box control thatsupports single or multiple selection. Also, list items for combo box and list box controls can now bedynamically populated with values associated with the variables in a specified target list. Inaddition, radio buttons can now contain a set of nested controls. See the topic Creating andManaging Custom Dialogs for more information.

Improved display of large pivot tables. New display options are now available that make it easierto view and navigate large pivot tables (tables with hundreds or thousands of rows). See the topicSet rows to display for more information.

Improved Twostep Cluster output. The Twostep Cluster procedure now provides interactivemodel viewer output. Twostep Cluster is available in the Statitics Base option. See the topic TheCluster Viewer for more information.

Additional rule-checking on quality control charts. Rule-checking is now performed on severaladditional control charts. When rule-checking is requested for an X-bar chart, it will also beperformed on the accompanying R (range) or s (standard deviation) chart. Similarly, when rule-checking is requested for an Individuals (Runs) chart, it will also be performed on the accompanyingMoving Range chart. Quality control charts are available in the Statistics Base option.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.5. What's new in version 17.0?

New syntax editor. The syntax editor has been completely redesigned with features such as auto-completion, color coding, bookmarks, and breakpoints. Auto-completion provides you with a list ofvalid command names, subcommands, and keywords; so you’ll spend less time referring to syntaxcharts. Color coding allows you to quickly spot unrecognized terms as well as some commonsyntactical errors. Bookmarks allow you to quickly navigate large command syntax files. Breakpointsallow you to stop execution at specified points so you can inspect data or output beforeproceeding. See the topic Using the Syntax Editor for more information.

Custom Dialog Builder. The Custom Dialog Builder allows you to create and manage custom

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 6/38

dialogs for generating command syntax. You can create custom dialogs to generate syntax frommultiple commands, including custom extension commands implemented in Python or R. See thetopic Creating and Managing Custom Dialogs for more information.

Multiple language support. In addition to the ability to change the output language available inprevious releases, you can now change the user interface language. See the topic General optionsfor more information.

Codebook. The Codebook procedure reports the dictionary information -- such as variable names,variable labels, value labels, missing values -- and summary statistics for all or specified variablesand multiple response sets in the active dataset. For nominal and ordinal variables and multipleresponse sets, summary statistics include counts and percents. For scale variables, summarystatistics include mean, standard deviation, and quartiles. See the topic Codebook for moreinformation.

Nearest Neighbor analysis. Nearest Neighbor analysis is a method for classifying cases based ontheir similarity to other cases. In machine learning, it was developed as a way to recognize patternsof data without requiring an exact match to any stored patterns, or cases. Similar cases are neareach other and dissimilar cases are distant from each other. Thus, the distance between two casesis a measure of their dissimilarity. See the topic Nearest Neighbor Analysis for more information.

Multiple Imputation. The Multiple Imputation procedure performs multiple imputation of missingdata values. Given a dataset containing missing values, it outputs one or more datasets in whichmissing values are replaced with plausible estimates. You can then obtain pooled results whenrunning other procedures. The procedure also summarizes missing values in the working dataset.This feature is available in the Missing Values add-on option. See the topic Impute Missing DataValues (Multiple Imputation) for more information.

RFM analysis. RFM (recency, frequency, monetary) analysis is a technique used to identify existingcustomers who are most likely to respond to a new offer. This technique is commonly used in directmarketing. This feature is available in the EZ RFM add-on option. See the topic RFM Analysis formore information.

Categorical Regression enhancements. Categorical Regression has been enhanced to includeregularization and resampling methods to assess and improve prediction accuracy. Together, thesenew methods make it possible to create state-of-the-art models, even for high-volume data (wherethere are more variables than observations, such as in genomics). This feature is available in theCategories add-on option. See the topic Categorical Regression (CATREG) for more information.

Graphboard. Graphboard visualizations are graphs, charts, and plots created from a visualizationtemplate. IBM® SPSS® Statistics ships with built-in visualization templates. You can also use aseparate product, IBM® SPSS® Visualization Designer, to create your own visualization templates.The new visualization templates are effectively custom visualization types. See the topic Creatingand Editing Graphboard Visualizations for more information.

Exporting output. More output export format options and more control over exported content,including:

• Wrap or shrink wide table in Word documents. See the topic Word/RTF options for moreinformation.

• Create new worksheets or append data to existing worksheets in an Excel workbook. See thetopic Excel options for more information.

• Save output export specifications in the form of command syntax with the OUTPUT EXPORT

command. All the features for exporting output in the Export Output dialog are now also availablein command syntax; so you can save and re-run your export specifications and include them inautomated production jobs. See the topic OUTPUT EXPORT for more information.

• The Output Management System (OMS) now supports these additional output formats: Word,Excel, and PDF. See the topic Output Management System for more information.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 7/38

Shift Values. Shift Values creates new variables that contain the values of existing variables frompreceding (lag) or subsequent (lead) cases. See the topic Shift Values for more information.

Aggregate enhancements. You can now use the features of the Aggregate procedure withoutspecifying a break variable. See the topic Aggregate Data for more information.

Median function. A median function is now available for computing the median value acrossselected variables for each case. See the topic Statistical functions for more information.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.6. What's new in version 16.0?

User interface enhancements. Enhancements to the point-and-click interface include:

• All dialog boxes are now resizable. The ability to make a dialog box wider makes variable listswider so that you can see more of the variable names and/or descriptive labels. The ability tomake a dialog box longer makes variable lists longer so that you can see more variables withoutscrolling.

• Drag-and-drop variable selection is now supported in all dialog boxes.

• Variable list display order and display characteristics can be changed on the fly in all dialogboxes. Change the sort order (alphabetic, file order, measurement level) and/or switch betweendisplay of variable names or variable labels whenever you want. See the topic Variable namesand variable labels in dialog box lists for more information.

Data and output management. Data and output management enhancements include:

• Read and write Excel 2007 files.

• Choose between working with multiple datasets or one dataset at a time. See the topic Generaloptions for more information.

• Search and replace information in Viewer documents, including hidden items and layers inmultidimensional pivot tables. See the topic Finding and replacing information in the Viewer formore information.

• Assign missing values and value labels to any string variable, regardless of the defined stringwidth (previously limited to strings with a defined width of 8 or less bytes).

• New character-based string functions. See the topic String functions for more information.

• Output Management System (OMS) support for Viewer file format (.spv) and VML-format chartsand image maps with pop-up chart information for HTML documents. See the topic OutputManagement System for more information.

• Customize Variable View in the Data Editor. Change the display order of the attribute columns,and control which attribute columns are displayed. See the topic Customizing Variable View formore information.

• Sort variables in the active dataset alphabetically or by attribute (dictionary) values. See thetopic Sort variables for more information.

• Spell check variable labels and value labels in Variable View. See the topic Spell checking formore information.

• Change basic variable type (string, numeric), change the defined width of string variables, andautomatically set the width of string variables to the longest observed value for each variable.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 8/38

See the topic ALTER TYPE for more information.

• Read and write Unicode data and syntax files. See the topic General options for more information.

• Control the default directory location to look for and save files. See the topic File locationsoptions for more information.

Performance. For computers with multiple processors or processors with multiple cores,multithreading for faster performance is now available for some procedures. See the topic THREADSSubcommand (SET command) for more information.

Statistical enhancements. Statistical enhancements include:

• Partial Least Squares (PLS). A predictive technique that is an alternative to ordinary leastsquares (OLS) regression, canonical correlation, or structural equation modeling, and it isparticularly useful when predictor variables are highly correlated or when the number ofpredictors exceeds the number of cases. See the topic Partial Least Squares Regression for moreinformation.

• Multilayer perceptron (MLP). The MLP procedure fits a particular kind of neural network called amultilayer perceptron. The multilayer perceptron uses a feed-forward architecture and can havemultiple hidden layers. The multilayer perceptron is very flexible in the types of models it can fit.It is one of the most commonly used neural network architectures. This procedure is available inthe new Neural Networks option. See the topic Multilayer Perceptron for more information.

• Radial basis function (RBF). A Radial basis function (RBF) network is a feed-forward, supervisedlearning network with only one hidden layer, called the radial basis function layer. Like themultilayer perceptron (MLP) network, the RBF network can do both prediction and classification.It can be much faster than MLP, however it is not as flexible in the types of models it can fit.This procedure is available in the new Neural Networks option. See the topic Radial BasisFunction for more information.

• Generalized Linear Models supports numerous new features, including ordinal multinomial andTweedie distributions, maximum likelihood estimation of the negative binomial ancillary parameter,and likelihood-ratio statistics. This procedure is available in the Advanced Statistics option. Seethe topic Generalized Linear Models Response for more information.

• Cox Regression now provides the ability to export model information to an XML (PMML) file. Thisprocedure is available in the Advanced Statistics option. See the topic Cox Regression Save NewVariables for more information.

• Complex Samples Cox Regression. Apply Cox proportional hazards regression to analysis ofsurvival times—that is, the length of time before the occurrence of an event for samples drawnby complex sampling methods. This procedure supports continuous and categorical predictors,which can be time-dependent. This procedure provides an easy way of considering differences insubgroups as well as analyzing effects of a set of predictors. The procedure estimates variancesby taking into account the sample design used to select the sample, including equal probabilityand probability proportional to size (PPS) methods and with replacement (WR) and withoutreplacement (WOR) sampling procedures. This procedure is available in the Complex Samplesoption.

Programmability extension. Programmability extension enhancements include:

• R-Plugin. Combine the power of IBM® SPSS® Statistics with the ability to write your ownstatistical routines with R. This plug-in is available only as a download fromhttp://www.ibm.com/developerworks/spssdevcentral.

• Nested Begin Program-End Program command structures. See the topic BEGIN PROGRAM-END

PROGRAM for more information.

• Ability to create and manage multiple datasets.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 9/38

Command syntax. For a complete list of command syntax additions and changes, see ReleaseHistory.

Features no longer supported

• There is no longer a separate chart editor for "interactive" charts. Charts created from thelegacy "interactive" chart dialog boxes and from IGRAPH command syntax are created in the

same format as all other charts and edited in the same chart editor.

• Some features provided in the legacy "interactive" chart dialog boxes and IGRAPH command

syntax are no longer available. See the "Release History" section of IGRAPH for details.

• The Draft Viewer is no longer available.

• You cannot open Viewer files created in previous versions of SPSS Statistics (.spo files) in SPSSStatistics 16.0. For Windows operating systems, the installation CD includes a Legacy Viewerthat you can install to view and edit Viewer files created in previous releases.

• The Maps option is no longer available.

• Dialog box interfaces for the legacy procedures in the Trends and Tables options are no longeravailable. For Trends, this includes the following commands: AREG, ARIMA, and EXSMOOTH. For

Tables, this includes the TABLES command. If you have a license for either of these options that

includes the legacy procedures, command syntax for these commands is still supported.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.7. What's new in version 15.0?

Data management

Custom variable attributes. In addition to the standard variable attributes (for example, valuelabels, missing values, measurement level), you can create your own custom variable attributes.You can display and edit these attributes directly in Variable View of the Data Editor. Like standardvariable attributes, these custom attributes are saved with IBM® SPSS® Statistics data files. Seethe topic Custom Variable Attributes for more information. (A syntax-only implementation of customvariable attributes was introduced in version 14 with the VARIABLE ATTRIBUTE command.)

Variable sets. You can now use variable sets to control which variables are displayed in the DataEditor as well as in dialog box variable lists. (In previous releases, variable sets affected only dialogbox variable lists.) Variable sets make it easier to work with data files that contain a large numberof variables. See the topic Defining variable sets for more information.

Export to Database wizard. Create new database tables, replace values for selected fields, andadd new fields to an existing table, all without having to write a single line of SQL code yourself.See the topic Exporting to a Database for more information.

Export to Data Collection. Export to IBM® SPSS® Data Collection creates a data file in SPSSStatistics format and a Data Collection metadata file that you can use to read the data into DataCollection applications. See the topic Exporting to IBM SPSS Data Collection for more information.(Note: This is only available on Microsoft Windows operating systems.)

Save data in CSV format. Save data in CSV (comma-separated values) format. CSV is a commondata format recognized by many applications. See the topic Saving data files in external formats formore information. For information on command syntax for saving data in CSV format, see SAVETRANSLATE.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 10/38

Reporting

Export results in PDF format. Export output in PDF format, including Viewer outline headings asbookmarks in the PDF file. See the topic Export output for more information.

Control chart enhancements. You can now define rules for control charts to help you quicklyidentify points that are out of control.

More chart types in Chart Builder. The Chart Builder has been expanded to include histograms,boxplots, scatterplot matrices, overlay scatterplots, population pyramids, error bar charts, high-low-close charts, difference area charts, range bar charts, dot plots, charts of separate variables,and paneled charts. You can also create charts that were not previously available, such as chartswith dual, independent y axes.

Chart Editor enhancements. The Chart Editor now offers more control over your charts. Majorfeatures include an updated Variables tab for changing chart types easily, automatic control ofwhite space, additional distribution curves for histograms, a tool for quickly rescaling axes, and theability to use custom equations to create reference lines. See the topic What's New and Differentfor more information.

Programmatic control of output documents. You can now create, open, activate, save, andclose Viewer and documents with command syntax using OUTPUT NEW, OUTPUT NAME, OUTPUTACTIVATE, OUTPUT OPEN, OUTPUT SAVE, and OUTPUT CLOSE.

Statistical Enhancements

Ordinal Regression. This procedure, previously available as part of the Advanced Statistics add-on option, is now available in the Core system. See the topic Ordinal Regression for moreinformation.

PMML model files with transformations. You can now include transformations in PMML model filesand merge information from model files using the TMS BEGIN-TMS END and TMS MERGE commands.

Generalized Linear Models. The Generalized Linear Models procedure expands the general linearmodel so that the dependent variable is linearly related to the factors and covariates via a specifiedlink function. Moreover, the model allows for the dependent variable to have a non-normaldistribution. This procedure is available in the Advanced Statistics option. See the topic GeneralizedLinear Models Response for more information.

Generalized Estimating Equations. The Generalized Estimating Equations procedure extends thegeneralized linear model to allow for analysis of repeated measurements. This procedure is availablein the Advanced Statistics option. See the topic Generalized Estimating Equations for moreinformation.

Complex Samples Ordinal Regression. The Complex Samples Ordinal Regression procedureperforms regression analysis on a binary or ordinal dependent variable for samples drawn by complexsampling methods. Optionally, you can request analyses for a subpopulation. This procedure isavailable in the Complex Samples option. See the topic Complex Samples Ordinal Regression for moreinformation.

Optimal Binning. The Optimal Binning procedure discretizes one or more scale variables bydistributing the values of each variable into bins. Bin formation is optimal with respect to acategorical guide variable that "supervises" the binning process. Bins can then be used instead ofthe original data values for further analysis. This procedure is available in the Data Preparationoption. See the topic Optimal Binning for more information.

Programmability Extension

The Programmability Extension now allows you to write to the active dataset and create custompivot tables and custom procedures. For more information go to

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 11/38

http://www.ibm.com/developerworks/spssdevcentral

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.8. What's new in version 14.0.1

• Dialog box interface for new PREFSCAL procedure, introduced in version 14.0. This procedure is

available in the Categories option.See the topic Multidimensional Unfolding (PREFSCAL) for moreinformation.

• New add-on option: Adaptor for Predictive Enterprise Services enables you to publish and shareobjects through a central repository. Objects can be shared among users, shared with otherapplications, and tracked using versioning, thus eliminating the need for ad-hoc file systems tomanage enterprise-wide assets.

• Access to data for external programming languages. The Programmability Extension has beenenhanced to provide the ability to send data to an external programming language.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.9. What's new in version 14.0?

Data management

• Have multiple data sources open at the same time, making it easier to compare data files, copydata and attributes from one file to another file, and merge multiple data sources without savingeach data source as a sorted data file first. For more information, see Basic Handling of MultipleData Sources and DATASET NAME.

• Read and write Stata-format data files. You can read Stata version 4–8 data files and writeStata version 5–8 data files. For more information, see Reading Stata files, Saving data files inStata format, GET STATA, SAVE TRANSLATE.

• Read data from IBM® SPSS® Data Collection data sources. See the topic Reading IBM SPSSData Collection Data for more information. (Note: This is available only on Microsoft Windowsoperating systems.)

• Read data from OLE DB data sources. See the topic Selecting a Data Source for moreinformation. (Note: This is available only on Microsoft Windows operating systems.)

• Define descriptive value labels up to 120 bytes (previous limit was 60 bytes).

• Create data values from value labels or use them in transformation logic with the VALUELABEL

function. See the topic VALUELABEL function for more information.

• Find and replace string values with the REPLACE function. See the topic String functions for more

information.

• Define custom variable attributes and data file attributes with the VARIABLE ATTRIBUTE andDATAFILE ATTRIBUTE commands.

• Write data to database tables and other formats by using field/column names that are notconstrained by IBM® SPSS® Statistics variable-naming rules. SAVE TRANSLATE has been

enhanced to allow you to use quoted values for field/column names that contain spaces,

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 12/38

commas, or other characters that are not allowed in ˜variable names. See the topic RENAMESubcommand (SAVE TRANSLATE command) for more information.

• Use the new SQL subcommand of the SAVE TRANSLATE command to append new columns to

database tables, modify database table column attributes, join tables, and perform other actionsthat are permitted with valid SQL statements. See the topic SQL Subcommand (SAVETRANSLATE command) for more information.

Charts

• Use the new Chart Builder interface (Graphs menu) to build charts from predefined gallery chartsor from the individual parts (for example, coordinate systems and bars) that make up a chart.See the topic Building Charts for more information.

• Create custom chart types by using powerful GGRAPH and GPL command syntax. See the topic

GGRAPH for more information.

Statistical enhancements

• New Expert Modeler in the Forecasting option automatically identifies and estimates the best-fitting model for one or more time series, thus eliminating the need to identify an appropriatemodel through trial and error. For more information, see Time Series Modeler and TSMODEL.

• New Data Validation option provides a quick visual snapshot of your data and provides the abilityto apply validation rules that identify invalid data values. You can create rules that flag out-of-range values, missing values, or blank values. You can also save variables that record individualrule violations and the total number of rule violations per case. A limited set of predefined rules isprovided that you can copy or modify. For more information, see Introduction to Data Preparationand VALIDATEDATA.

New Anomaly Detection procedure in the Data Validation option finds unusual observations thatcould adversely affect predictive models. Some of these outlying observations represent trulyunique cases and are thus unsuitable for prediction, while other observations are caused bydata-entry errors in which the values are technically “correct” and thus cannot be caught by theValidate Data procedure. For more information, see Identify Unusual Cases and DETECTANOMALY.

• New Multidimensional Unfolding procedure (PREFSCAL) in the Categories option attempts to find

the structure in a set of proximity measures between row and column objects. This process isaccomplished by assigning observations to specific locations in a conceptual low-dimensionalspace such that the distances between points in the space match the given (dis)similarities asclosely as possible. The result is a least-squares representation of the objects in that low-dimensional space, which, in many cases, helps you further understand your data. This procedureis currently available with PREFSCAL command syntax. See the topic PREFSCAL for more

information.

• New Predictor Selection procedure (SELECTPRED) in SPSS Statistics Server sifts through a very

large number of categorical and continuous predictor variables. The procedure selects a smallersubset for use in predictive modeling procedures that cannot accept so many predictors. Thisprocedure is currently available with SELECTPRED command syntax. See the topic SELECTPRED

for more information.

• New Naïve Bayes procedure (NAIVEBAYES) in SPSS Statistics Server produces a simple and stable

model for predictor selection and classification. This procedure is currently available withNAIVEBAYES command syntax. See the topic NAIVEBAYES for more information.

• Improved significance testing capabilities in the Custom Tables option allows you to now performsignificance tests on subtotals and multiple response sets. See the topic Custom Tables: TestStatistics Tab for more information.

• More flexibility is available in defining multiple response sets for multiple dichotomies. See the

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 13/38

topic Defining Multiple Response Sets for more information.

Output

• Pivot table output is now provided for Rank Cases (RANK), Replace Missing Values (RMV), and

Create Time Series (CREATE) in the Core system; all procedures in the Conjoint option; Model

Selection Loglinear Analysis (HILOGLINEAR) in the Advanced Statistics option; and Probit Analysis

(PROBIT), Weight Estimation (WLS), and 2-Stage Least Squares (2SLS) in the Regression option.

Performance enhancements

• Table structures that previously took a long time to create or that might run out of memory withthe Custom Tables option (CTABLES) can now be created quickly and efficiently.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.9.1. Version 14.0 compatibility with previous releases

Logistic Regression

In previous versions, the order of recoded string values was dependent on the order of values inthe data file. For example, when recoding the dependent variable, the first string value encounteredwas recoded to 0, and the second string value encountered was recoded to 1. The procedure nowrecodes string variables so that the order of recoded values is the alphanumeric order of the stringvalues. Thus, the procedure may recode string variables differently than in previous versions.Logistic Regression is available in the Regression option.

Macro facility

Improvements to the macro facility may cause errors in jobs that previously ran without errors.Specifically, for syntax that is processed with interactive rules, if a macro call occurs at the end ofa command, and there is no command terminator (either a period or a blank line), the next commandafter the macro expansion will be interpreted as a continuation line instead of a new command, asin:

DEFINE !macro1()var1 var2 var3!ENDDEFINE.FREQUENCIES VARIABLES = !macro1DESCRIPTIVES VARIABLES = !macro1.

In interactive mode, the DESCRIPTIVES command will be interpreted as a continuation of the

FREQUENCIES command, and neither command will run.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.10. What's new in version 11.5?

New data definition tools. Two new features make defining data faster and easier:

• The Copy Data Properties wizard provides the ability to use an external data file as a templatefor defining file and variable properties in the active dataset. You can also use variables in theactive dataset as templates for other variables in the active dataset. Copy Data Properties is

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 14/38

available on the Data menu in the Data Editor window. See the topic Copying Data Properties for

more information.

• Define Variable Properties (also available on the Data menu in the Data Editor window) scansyour data and lists all unique data values for any selected variables, identifies unlabeled values,and provides an auto-label feature. This is particularly useful for categorical variables that usenumeric codes to represent categories--for example, 0 = Male, 1 = Female. See the topicDefining Variable Properties for more information.

Expanded support for SAS format data files. You can now save data files in SAS version 6, SASversion 7, and SAS Transport file format. See the topic Saving data: Data file types for moreinformation.

Expanded output export capabilities. You can now export entire Viewer documents or selectedoutput objects in Word/RTF format and Excel format (charts are not included in Excel format). Seethe topic Export output for more information.

Multiple output languages. You can now produce pivot table output in different languages andswitch languages during the same session. See the topic General options for more information.

TwoStep Cluster Analysis. This new clustering procedure offers the following features notavailable in the other IBM® SPSS® Statistics clustering procedures:

• Automatic selection of the best number of clusters, in addition to measures for choosingbetween cluster models.

• Ability to create cluster models simultaneously based on categorical and continuous variables.

• Ability to save the cluster model to an external XML file, then read that file and update thecluster model using newer data.

• Ability to analyze large data files with a single clustering procedure.

See the topic TwoStep Cluster Analysis for more information.

New Custom Tables option. If you have used the Tables option in the past, you will discover thatalmost everything is new in this release, including:

• A simple, drag-and-drop table builder interface that allows you to preview your table as youselect variables and options.

• A single, unified table builder interface instead of multiple menu choices and dialog boxes fordifferent types of tables.

• Subtotals for subsets of categories of a categorical variable.

• Custom control over category display order and ability to selectively show or hide categories.

Note: Custom Tables is not included in the Core system. It is only available if you have purchasedthe Custom Tables add-on option.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.11. What's new in version 11.0

Ratio Statistics. A new procedure provides a comprehensive list of summary statistics fordescribing the ratio between two scale variables, including coefficient of dispersion, coefficient ofvariation, price-related differential, and average absolute deviation.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 15/38

Linear Mixed Models. A new procedure enables you to construct predictive models when you havea nested data structure. You can formulate a wide variety of models, including Fixed Effects ANOVAModel, Randomized Complete Blocks Design, Split-Plot Design, Purely Random Effects Model, RandomCoefficient Model, Multilevel Analysis, Unconditional Linear Growth Model, Linear Growth Model witha person-level covariate, Repeated Measures Analysis, and Repeated Measures Analysis with time-dependent covariate. In addition, you can work with repeated measure designs, such as incompleterepeated measurements in which the number of observations varies across subjects. Available inthe Advanced Statistics option.

Performance enhancements. General Linear Models, Proximities, Hierarchical Cluster Analysis(Core system), and Multinomial Logistic Regression (Regression) now run much faster than inprevious releases.

Data management. Restructure data to create a single case (record) from multiple cases orcreate multiple cases from a single case.

Database Wizard. Now allows you to automatically recode categorical string values to numericvariables (using the original values as value labels), auto-join tables using primary/foreign keyrelationships, and obtain random samples from large data sources.

Text Wizard. Now allows you to read CSV-format text data that contains text qualifiers (such as,"1,000", "2,000", ...).

OLAP Cubes. Now allows you to calculate arithmetic and percentage differences betweencategories of a grouping variable or between separate variables.

One-Way ANOVA. Now includes the Brown-Forsythe and Welch tests.

Scientific notation for small numbers. You can choose not to see it in your output (from the Editmenu, choose Options, and then click the General tab).

Aggregate. Median has been added to the list of available Aggregate functions.

Arithmetic functions. Available functions in arithmetic expressions are expanded to include densityfunctions for continuous and discrete distributions.

Multinomial Logistic Regression. New functionality added to this procedure allows you to saveestimated response probabilities, predicted response categories, probability of predicted responsecategories, and probability of actual response categories. Available in the Regression option.

Categorical Regression. This procedure has been redesigned to make it more powerful and easierto use. Available in the Categories option.

Categorical Principal Components Analysis. Improvements in this procedure now make resultseasier to understand. Available in the Categories option.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.12. What's new in version 10.0.5

Read native SAS files with GET SAS. The GET SAS command has been enhanced to read native

SAS data files in addition to SAS transport files.

Cache data automatically. The Cache facility now automatically creates a data cache after acertain number of changes to the active data file. By default, the number of changes is 20. You canchange the number with the SET command, CACHE subcommand.

See the Command Syntax Reference for more information on SET and GET SAS.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 16/38

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.13. What's new in version 10.0

Improved data access. Analyze large data files without requiring large amounts of temporary diskstorage space. File size limitations are virtually eliminated because duplicate copies of the data file(automatically created and stored in temporary disk space in previous releases) are no longerrequired.

Distributed analysis. Dramatically improve the speed of your analysis by using a remote servercomputer to do perform data- and compute-intensive work for you. Using distributed analysis modewith the server version, you can perform complex analyses on large data files without tying up yourdesktop computer.

Multiple sessions. You can now run multiple sessions simultaneously on the same desktopcomputer, making it possible to analyze more than one data file at the same time.

Direct Excel access. Read Excel 5 or later files directly into IBM® SPSS® Statistics simply byselecting the Excel file in the Open File dialog box. You no longer need to use special Excel ODBCdrivers to read Excel files. And now you can read columns that contain mixed data types withoutany loss of data. Columns with mixed data types are automatically read as string variables and allvalues are read as valid string values.

New Data Editor. The Data Editor has been redesigned with a new Variables tab that makes itmuch easier to view and define variable attributes such as data types and descriptive variable andvalue labels.

Multiple test variables with ROC curves. The ROC Curve procedure has been enhanced tocompare multiple test variables.

Improved quality for interactive graphics used in other applications and improved printingperformance. Interactive graphs can now be copied as Windows metafiles, which are better suitedto resizing and printing in other applications without jagged lines and edges. Interactive graphs canbe printed as metafiles for faster results at the same high quality.

Polytomous Logit Universal Models (PLUM). Enables you to apply regression techniques toordinal outcomes (such as low, medium and high). Available in the Advanced Statistics option.

Thematic mapping. Enables you to graphically summarize data by geographic regions, using bar,pie, range of value, graduated symbol, and dot density charts displayed on high-quality maps.Available in the new Map option.

New optimal scaling procedure. A new nonlinear principal components analysis procedure(CATPCA) is available in the Categories option.

Improved output for Logistic Regression and Cox Regression. Logistic Regression (Regressionoption) and Cox Regression (Advanced Statistics option) now produce high-quality, flexible, pivottable output.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.14. What's new in version 9.0

A (slightly) new look. The Analyze menu replaces the Statistics menu, and:

• Procedures formerly available on the Summarize submenu have been reorganized into two new

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 17/38

submenus: Reports and Descriptive Statistics.

• Layered Reports is now OLAP Cubes.

• GLM-General Factorial is now GLM Univariate.

Interactive graphics. More charts and more features, including:

• More chart types, including area charts, stacked bar charts, and charts of multiple variables.

• More chart features, including reference lines, secondary axes, spikes in scatterplots, control ofcategory order and display of categories with missing data, more flexibility in key display, andmore control over panel display.

• Charts from pivot tables. Just select the part of the table you want to display as a chart, right-click anywhere in the selected area, and select Create Graph.

Draft Viewer. Better-looking output in the Draft Viewer with:

• Improved table borders using box characters that produce clean, solid lines for row, column, andcell borders.

• Better page breaks for multipage tables and more control over how multipage tables aredisplayed.

Statistical enhancements. Statistical enhancements include:

• Reliability analysis, multidimensional scaling (ALSCAL), and the Matrix language are now availablein the Core system.

• New ROC Curve procedure for evaluating the performance of classification schemes where thereis one variable with two categories by which subjects are classified.

• Crosstabs procedure enhanced to include Cochran-Mantel-Haenszel statistic.

• New Nominal Regression procedure for analyzing the relationship between categorical variableswith two or more categories and multiple independent variables (available in the Regressionoption).

File management. The new Text Wizard makes it easier than ever to read text data files in avariety of formats.

Titles. Support for syntax commands TITLE and SUBTITLE.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.15. What's new in version 8.0

Dynamic, interactive charts and graphs. New graphing features make it easier to explore yourdata visually.

• Drag and drop new variables, and update charts on the fly.

• Split a single chart into multiple panels for side-by-side comparisons.

• Paste "live" charts into applications that support ActiveX objects.

Statistical enhancements. Perform more in-depth analysis with additional statistics, including:

• New ANOVA procedure with custom models and post-hoc tests.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 18/38

• Robust Levene test to compare variance between groups in the Explore procedure.

• Harmonic and geometric means in the Means procedure.

• Interclass correlation in the Reliability procedure (Professional Statistics option).

• One-minus-survival functions in Survival procedures (Advanced Statistics option).

• Improved correspondence analysis and multiple regression for categorical data (Categoriesoption).

Data management. Work faster and easier with data management improvements, including:

• Display descriptive variable labels instead of variable names in dialog boxes. Variable labels canbe up to 256 characters long.

• Create and execute database queries faster. Save queries created by the Database Wizard andcreate prompted queries that allow you to use the same query to retrieve different subsets ofdata (such as sales data for different quarters).

• Include a date and time stamp in journal files for archiving.

Output enhancements. Create more pivot tables and have more control over output, including:

• See the bottom line faster with the new Layered Reports procedure that provides summaryreports with each subgroup in a separate layer. Drill down to custom views of your results andreveal key information.

• Pick the output format you want: interactive pivot tables or simple text output. (For text output,choose Options from the Edit menu, click the General tab, and click Draft for output type.)

• Control default column width in pivot tables and save column width settings in the Data Editor.

• Use bookmarks to save different views of pivot tables.

• Display correlation coefficients and significance levels next to each other in the BivariateCorrelations procedure.

• Organize results by variable or by table type in the Frequencies procedure.

Online Help. Online Help has been expanded to include more just-in-time training features,including:

• Easily understand your results with the Results Coach. Annotated sample output that helps youunderstand how to interpret your results is available for all pivot tables in the Core system.

• Get the information you need faster and easier with "Ask Me" help -- a natural language interfacethat helps you find the answers you need without needing to know any complicated jargon.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.16. What's new in version 7.5

Scripting and automation. With new scripting features and OLE automation, you can automatemany tasks, including customizing pivot table output. You can use the sample scripts, customizethem to meet your needs, or create your own scripts.

• Use Options on the Edit menu and select the Scripts tab on the Options dialog box to selectautoscripts (scripts that run automatically each time you create a specified table type) and

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 19/38

select specific autoscript functions.

• Use Create/Modify Autoscripts on the Utilities menu to create new autoscript functions for thecurrently selected output object type in the Viewer.

• Use Run Scripts on the Edit menu to run a personal script on the currently selected outputobject in the Viewer (a variety of sample personal scripts are supplied with IBM® SPSS®Statistics).

• Use Open or New on the File menu to modify any personal script or create a new personal script.

HTML and ASCII format for exporting output. You can export output in HTML (HTML 3.0) andASCII text format. For HTML format, pivot tables can be exported as HTML tables, and charts canbe exported in JPEG format and automatically embedded by reference in your HTML document. UseExport on the File menu of the Viewer to export output.

Expanded features for reading databases. The new Database Wizard enables you to specifymultiple joins, including both inner and outer joins. Use Database Capture on the File menu to readdatabases into SPSS Statistics.

Customizable toolbars. You can modify toolbars and create your own toolbars to include thefeatures you use often, including personal scripts and any items available on the menus. UseToolbars on the View menu to customize toolbars.

Statistics Coach. For users who are not familiar with SPSS Statistics or with the availablestatistical procedures, the Statistics Coach can help you get started with many of the basicstatistical techniques in the Core system.

More statistical procedures in the Core system. Factor analysis, discriminant analysis, clusteranalysis, and proximity and distance measures are now included in the Core system (Analyze menu)and feature new, flexible, pivot table output.

Variance Components Analysis. A new procedure in the Advanced Statistics option, VarianceComponents Analysis extends the analytic capabilities of the General Linear Model procedures.

Statistical enhancements. Many statistical procedures now have additional features:

• Crosstabs. McNemar test and clustered bar charts.

• Frequencies. Pie charts.

• Factor Analysis. Promax rotation method.

• Discriminant Analysis. Leave-one-out classification (similar to jackknifing).

• Logistic Regression (Professional Statistics). Pseudo R Squared measures and Hosmer-Lemeshow goodness-of-fit statistics.

• General Linear Model (Advanced Statistics). Expanded set of analysis options and techniques.

New tables features. With the Custom Tables option, you can save multiple response setinformation, and pivoting features have been enhanced to provide greater flexibility for pivotingtables.

More printing control. Printing features have been expanded to include alignment control ofindividual output items, user-specified page and column breaks in large tables, and widow andorphan control for tables that break across pages.

• Use Align Left, Center, or Align Right on the Format menu in the Viewer to change the alignmentfor the selected output item.

• Use Break on the Format menu in an activated pivot table to specify a page or column break at

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 20/38

the selected row or column. Use Keep Together to prevent page or column breaks between rowsor columns you want to remain together.

• Use Table Properties on the Format menu in an activated pivot table to change widow/orphansettings.

More pivot table control. Features for modifying pivot tables have been expanded to include theability to: reorder categories by dragging and dropping selected rows or columns, rotate row andcolumn labels, and create groups of related rows and columns with group labels.

• Use Rotate on the Format menu in an activated pivot table to rotate inner column or outer rowlabels.

• Use Group on the Edit menu in an activated pivot table to create groups of related rows orcolumns with group labels.

Other new features. Other new features include:

• Variable labels up to 256 characters.

• Ability to read SYSTAT 6.0 for Windows files directly.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.17. What's new in version 7.0

Version 7.0 takes full advantage of the improved features of Windows 95 to bring you:

New output display. Most of the statistical procedures in the Core system have been improved toprovide presentation-quality results.

Pivot tables. Pivot table output allows you to view your results in many different ways. You canswitch row and column variables, selectively show and hide categories, and manipulatemultidimensional tables.

Easy access context menus. A simple right-mouse button click anywhere in a pivot table opens acontext menu that provides access to common editing tasks right at your fingertips.

Improved online Help. Right-mouse button context menus also provide access to online Help onindividual controls on dialog boxes and selected items in output results.

Unconstrained multiple document interface.IBM® SPSS® Statistics windows are no longerconstrained to fit inside an overall application window with a single menu bar and toolbar. Eachwindow has its own menus and toolbars and can be placed anywhere on the screen.

New Summarize procedure. Create presentation-quality listings of the cases in your data file,combined with summary statistics for subgroups of cases defined by one or more grouping variables.You can also suppress display of cases to obtain totals and subtotals for all combinations of theselected grouping variables.

New GLM procedure. The general linear model (GLM) is a flexible statistical model incorporatinganalyses involving normally distributed dependent variables and combinations of categorical andcontinuous predictor variables.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 21/38

1.1.18. Windows

There are a number of different types of windows in IBM® SPSS® Statistics:

Data Editor. The Data Editor displays the contents of the data file. You can create new data filesor modify existing data files with the Data Editor. If you have more than one data file open, there isa separate Data Editor window for each data file.

Viewer. All statistical results, tables, and charts are displayed in the Viewer. You can edit theoutput and save it for later use. A Viewer window opens automatically the first time you run aprocedure that generates output.

Pivot Table Editor. Output that is displayed in pivot tables can be modified in many ways with thePivot Table Editor. You can edit text, swap data in rows and columns, add color, createmultidimensional tables, and selectively hide and show results.

Chart Editor. You can modify high-resolution charts and plots in chart windows. You can changethe colors, select different type fonts or sizes, switch the horizontal and vertical axes, rotate 3-Dscatterplots, and even change the chart type.

Text Output Editor. Text output that is not displayed in pivot tables can be modified with the TextOutput Editor. You can edit the output and change font characteristics (type, style, color, size).

Syntax Editor. You can paste your dialog box choices into a syntax window, where your selectionsappear in the form of command syntax. You can then edit the command syntax to use specialfeatures that are not available through dialog boxes. You can save these commands in a file for usein subsequent sessions.

Data Editor and Viewer

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 22/38

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.18.1. Designated window versus active window

If you have more than one open Viewer window, output is routed to the designated Viewerwindow. If you have more than one open Syntax Editor window, command syntax is pasted into thedesignated Syntax Editor window. The designated windows are indicated by a plus sign in the iconin the title bar. You can change the designated windows at any time.

The designated window should not be confused with the active window, which is the currentlyselected window. If you have overlapping windows, the active window appears in the foreground. Ifyou open a window, that window automatically becomes the active window and the designatedwindow.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.18.1.1. Changing the designated window

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 23/38

Make the window that you want to designate the active window (click anywhere in the window).

Click the Designate Window button on the toolbar (the plus sign icon).

or

From the menus choose:

Utilities > Designate Window

Note: For Data Editor windows, the active Data Editor window determines the dataset that is usedin subsequent calculations or analyses. There is no "designated" Data Editor window. See the topicBasic Handling of Multiple Data Sources for more information.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.19. Status Bar

The status bar at the bottom of each IBM® SPSS® Statistics window provides the followinginformation:

Command status. For each procedure or command that you run, a case counter indicates thenumber of cases processed so far. For statistical procedures that require iterative processing, thenumber of iterations is displayed.

Filter status. If you have selected a random sample or a subset of cases for analysis, the messageFilter on indicates that some type of case filtering is currently in effect and not all cases in the datafile are included in the analysis.

Weight status. The message Weight on indicates that a weight variable is being used to weightcases for analysis.

Split File status. The message Split File on indicates that the data file has been split into separategroups for analysis, based on the values of one or more grouping variables.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.20. Dialog boxes

Most menu selections open dialog boxes. You use dialog boxes to select variables and options foranalysis.

Dialog boxes for statistical procedures and charts typically have two basic components:

Source variable list. A list of variables in the active dataset. Only variable types that are allowedby the selected procedure are displayed in the source list. Use of short string and long stringvariables is restricted in many procedures.

Target variable list(s). One or more lists indicating the variables that you have chosen for theanalysis, such as dependent and independent variable lists.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 24/38

1.1.21. Variable names and variable labels in dialog box lists

You can display either variable names or variable labels in dialog box lists, and you can control thesort order of variables in source variable lists. To control the default display attributes of variablesin source lists, choose Options on the Edit menu. See the topic General options for moreinformation.

You can also change the variable list display attributes within dialogs. The method for changing thedisplay attributes depends on the dialog:

• If the dialog provides sorting and display controls above the source variable list, use thosecontrols to change the display attributes.

• If the dialog does not contain sorting controls above the source variable list, right-click on anyvariable in the source list and select the display attributes from the context menu.

You can display either variable names or variable labels (names are displayed for any variableswithout defined labels), and you can sort the source list by file order, alphabetical order, ormeasurement level. (In dialogs with sorting controls above the source variable list, the defaultselection of None sorts the list in file order.)

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.22. Resizing dialog boxes

You can resize dialog boxes just like windows, by clicking and dragging the outside borders orcorners. For example, if you make the dialog box wider, the variable lists will also be wider.

Resized dialog box

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.23. Dialog box controls

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 25/38

There are five standard controls in most dialog boxes:

OK or Run. Runs the procedure. After you select your variables and choose any additionalspecifications, click OK to run the procedure and close the dialog box. Some dialogs have a Runbutton instead of the OK button.

Paste. Generates command syntax from the dialog box selections and pastes the syntax into asyntax window. You can then customize the commands with additional features that are notavailable from dialog boxes.

Reset. Deselects any variables in the selected variable list(s) and resets all specifications in thedialog box and any subdialog boxes to the default state.

Cancel. Cancels any changes that were made in the dialog box settings since the last time it wasopened and closes the dialog box. Within a session, dialog box settings are persistent. A dialog boxretains your last set of specifications until you override them.

Help. Provides context-sensitive Help. This control takes you to a Help window that containsinformation about the current dialog box.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.24. Selecting variables

To select a single variable, simply select it in the source variable list and drag and drop it into thetarget variable list. You can also use arrow button to move variables from the source list to thetarget lists. If there is only one target variable list, you can double-click individual variables to movethem from the source list to the target list.

You can also select multiple variables:

• To select multiple variables that are grouped together in the variable list, click the first variableand then Shift-click the last variable in the group.

• To select multiple variables that are not grouped together in the variable list, click the firstvariable, then Ctrl-click the next variable, and so on (Macintosh: Command-click).

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.25. Data type, measurement level, and variable list icons

The icons that are displayed next to variables in dialog box lists provide information about thevariable type and measurement level.

Numeric String Date Time

Scale (Continuous) n/a

Ordinal

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 26/38

Nominal

• For more information on measurement level, see Variable measurement level.

• For more information on numeric, string, date, and time data types, see Variable type.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.26. Getting information about variables in dialog boxes

Many dialogs provide the ability to find out more about the variables displayed in the variable lists.

Right-click a variable in the source or target variable list.

Choose Variable Information.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.27. Command line options

You can start IBM® SPSS® Statistics from the command line and include various switches to log onto an analytic server or to start production mode, among other options. The command is namedstats and can be run from one of the following locations.

Platform Executable Location

Windows <installation directory>

Mac <installation directory>/<version>.app/Contents/MacOS

Linux <installation directory>/bin

Available Switches and Options

stats [-server <inet:hostname:port>] [-user <name>] [-password <password>] [-switchserver] [-singleseat] [-nologo] [-production [silent|prompt] [-background]] [-symbol <values>] [<filename>] ... [-help|-h]

-server <inet:hostname:port> or -server <ssl:hostname:port>. The name or IP address andport number of the server. Windows only.

-user <name>. A valid user name. If a domain name is required, precede the user name with thedomain name and a backslash (\). Windows only.

-password <password>. The user's password.

-switchserver. Display the "Server Login" dialog box. This switch has precedence over the previous

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 27/38

-server, -user, and -password switches. Windows only.

-singleseat. Start application in a single seat mode.

-nologo. Start the application without displaying the splash screen.

-production [prompt|silent]. Start the application in production mode. The prompt and silent

keywords specify whether to display the dialog box that prompts for runtime values if they arespecified in the job. The prompt keyword is the default and shows the dialog box. The silentkeyword suppresses the dialog box. If you use the silent keyword, you can define the runtime

symbols with the -symbol switch. Otherwise, the default value is used. The -switchserver and -

singleseat switches are ignored when using the -production switch.

-symbol <values>. List of symbol-value pairs used in the production job. Each symbol name startswith @. Values that contain spaces should be enclosed in quotes. Rules for including quotes orapostrophes in string literals may vary across operating systems, but enclosing a string thatincludes single quotes or apostrophes in double quotes usually works (for example, “'a quoted

value'”). The symbols must be defined in the production job using the Runtime Values tab. See the

topic Runtime values for more information.

-background. Run the production job in the background on a remote server. Your local computerdoes not have to remain on and does not have to remain connected to the remote server. You candisconnect and retrieve the results later. You must also include the -production switch and

specify the server using the -server switch.

<filename> .... List of filenames, which can include all application supported file types. Enclose afile name with double quotes if it contains spaces.

-help|-h. Display the command help.

If the -server, -user, -password, -switchserver, and -singleseat switches are omitted, SPSS

Statistics runs in the default mode.

Examples

Note: The following examples assume that you changed directories to the executable location. Thedetails may vary by operating system and may require path specifications.

Starting in distributed mode using a specific server:

stats -server mystatssvr:3016 -user myuser -password mypassword

Starting in distributed mode using a specific server and a domain name:

stats -server mystatssvr:3016 -user "mydomain\myuser" -password mypassword

Starting in single seat mode:

stats -singleseat

Starting in production mode, letting SPSS Statistics prompt for runtime values:

stats C:\job1.spj -production

Starting in production mode with defined symbol-value pairs:

stats C:\job1.spj -production silent -macro @sex male @state "North Dakota"

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 28/38

Starting in default mode while opening a data file and a syntax file:

stats C:\cars.sav C:\analysis.sps

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.1.28. Basic steps in data analysis

Analyzing data with IBM® SPSS® Statistics is easy. All you have to do is:

Get your data into SPSS Statistics. You can open a previously saved SPSS Statistics data file,you can read a spreadsheet, database, or text data file, or you can enter your data directly in theData Editor.

Select a procedure. Select a procedure from the menus to calculate statistics or to create achart.

Select the variables for the analysis. The variables in the data file are displayed in a dialog boxfor the procedure.

Run the procedure and look at the results. Results are displayed in the Viewer.

© Copyright IBM Corporation 1989, 2012.

\n\ Next\n\ \n\ \n\ "); }

1.1.29. Statistics Coach

If you are unfamiliar with IBM® SPSS® Statistics or with the available statistical procedures, theStatistics Coach can help you get started by prompting you with simple questions, nontechnicallanguage, and visual examples that help you select the basic statistical and charting features thatare best suited for your data.

To use the Statistics Coach, from the menus in any SPSS Statistics window choose:

Help > Statistics Coach

The Statistics Coach covers only a selected subset of procedures. It is designed to provide generalassistance for many of the basic, commonly used statistical techniques.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.2. Getting Help

Help is provided in many different forms:

Help menu. The Help menu in most windows provides access to the main Help system, plustutorials and technical reference material.

• Topics. Provides access to the Contents, Index, and Search tabs, which you can use to findspecific Help topics.

• Tutorial. Illustrated, step-by-step instructions on how to use many of the basic features. You

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 29/38

don't have to view the whole tutorial from start to finish. You can choose the topics you want toview, skip around and view topics in any order, and use the index or table of contents to findspecific topics. You can also click here to start the tutorial.

• Case Studies. Hands-on examples of how to create various types of statistical analyses andhow to interpret the results. The sample data files used in the examples are also provided so thatyou can work through the examples to see exactly how the results were produced. You canchoose the specific procedure(s) that you want to learn about from the table of contents orsearch for relevant topics in the index. You can also click here to open the Case Studies.

• Statistics Coach. A wizard-like approach to guide you through the process of finding theprocedure that you want to use. After you make a series of selections, the Statistics Coachopens the dialog box for the statistical, reporting, or charting procedure that meets yourselected criteria. You can also click here to open the Statistics Coach.

• Command Syntax Reference. Detailed command syntax reference information is available intwo forms: integrated into the overall Help system and as a separate document in PDF form inthe Command Syntax Reference, available from the Help menu.

• Statistical Algorithms. The algorithms used for most statistical procedures are available in twoforms: integrated into the overall Help system and as a separate document in PDF form availableon the manuals CD. For links to specific algorithms in the Help system, choose Algorithms fromthe Help menu.

Context-sensitive Help. In many places in the user interface, you can get context-sensitive Help.

• Dialog box Help buttons. Most dialog boxes have a Help button that takes you directly to aHelp topic for that dialog box. The Help topic provides general information and links to relatedtopics.

• Pivot table context menu Help. Right-click on terms in an activated pivot table in the Viewerand choose What's This? from the context menu to display definitions of the terms.

• Command syntax. In a command syntax window, position the cursor anywhere within a syntaxblock for a command and press F1 on the keyboard. A complete command syntax chart for thatcommand will be displayed. Complete command syntax documentation is available from the linksin the list of related topics and from the Help Contents tab.

Other Resources

Technical Support Web site. Answers to many common problems can be found athttp://www.ibm.com/support. (The Technical Support Web site requires a login ID and password.Information on how to obtain an ID and password is provided at the URL listed above.)

If you're a student using a student, academic or grad pack version of any IBM SPSS softwareproduct, please see our special online Solutions for Education pages for students. If you're astudent using a university-supplied copy of the IBM SPSS software, please contact the IBM SPSSproduct coordinator at your university.

SPSS Community. The SPSS community has resources for all levels of users and applicationdevelopers. Download utilities, graphics examples, new statistical modules, and articles. Visit theSPSS community at http://www.ibm.com/developerworks/spssdevcentral.

© Copyright IBM Corporation 1989, 2012.

\n\ Next\n\ \n\ \n\ "); }

1.2.1. Getting Help on Output Terms

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 30/38

To see a definition for a term in pivot table output in the Viewer:

Double-click the pivot table to activate it.

Right-click on the term that you want explained.

Choose What's This? from the context menu.

A definition of the term is displayed in a pop-up window.

Show me

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3. Data files

Data files come in a wide variety of formats, and this software is designed to handle many of them,including:

• Spreadsheets created with Excel and Lotus

• Database tables from many database sources, including Oracle, SQLServer, Access, dBASE, andothers

• Tab-delimited and other types of simple text files

• Data files in IBM® SPSS® Statistics format created on other operating systems

• SYSTAT data files

• SAS data files

• Stata data files

• IBM® Cognos® Business Intelligence data packages and list reports

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1. Opening data files

In addition to files saved in IBM® SPSS® Statistics format, you can open Excel, SAS, Stata, tab-delimited, and other files without converting the files to an intermediate format or entering datadefinition information.

• Opening a data file makes it the active dataset. If you already have one or more open data files,they remain open and available for subsequent use in the session. Clicking anywhere in the DataEditor window for an open data file will make it the active dataset. See the topic Working withMultiple Data Sources for more information.

• In distributed analysis mode using a remote server to process commands and run procedures, theavailable data files, folders, and drives are dependent on what is available on or from the remoteserver. The current server name is indicated at the top of the dialog box. You will not haveaccess to data files on your local computer unless you specify the drive as a shared device andthe folders containing your data files as shared folders. See the topic Distributed Analysis Modefor more information.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 31/38

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.1. To open data files

From the menus choose:

File > Open > Data...

In the Open Data dialog box, select the file that you want to open.

Click Open.

Optionally, you can:

• Automatically set the width of each string variable to the longest observed value for thatvariable using Minimize string widths based on observed values. This is particularly useful whenreading code page data files in Unicode mode. See the topic General options for moreinformation.

• Read variable names from the first row of spreadsheet files.

• Specify a range of cells to read from spreadsheet files.

• Specify a worksheet within an Excel file to read (Excel 95 or later).

For information on reading data from databases, see Reading Database Files. For information onreading data from text data files, see Text Wizard. For information on reading IBM® Cognos® data,see Reading Cognos data.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.2. Data file types

SPSS Statistics. Opens data files saved in IBM® SPSS® Statistics format and also the DOSproduct SPSS/PC+.

SPSS Statistics Compressed. Opens data files saved in SPSS Statistics compressed format.

SPSS/PC+. Opens SPSS/PC+ data files. This is available only on Windows operating systems.

SYSTAT. Opens SYSTAT data files.

SPSS Statistics Portable. Opens data files saved in portable format. Saving a file in portableformat takes considerably longer than saving the file in SPSS Statistics format.

Excel. Opens Excel files.

Lotus 1-2-3. Opens data files saved in 1-2-3 format for release 3.0, 2.0, or 1A of Lotus.

SYLK. Opens data files saved in SYLK (symbolic link) format, a format used by some spreadsheetapplications.

dBASE. Opens dBASE-format files for either dBASE IV, dBASE III or III PLUS, or dBASE II. Eachcase is a record. Variable and value labels and missing-value specifications are lost when you savea file in this format.

SAS. SAS versions 6–9 and SAS transport files. Using command syntax, you can also read value

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 32/38

labels from a SAS format catalog file. See the topic GET SAS for more information.

Stata. Stata versions 4–8.

For information on reading data from databases, see Reading Database Files. For information onreading data from text data files, see Text Wizard. For information on reading IBM® Cognos® data,see Reading Cognos data.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.3. Opening file options

Read variable names. For spreadsheets, you can read variable names from the first row of the fileor the first row of the defined range. The values are converted as necessary to create validvariable names, including converting spaces to underscores. For information on variable namingrules, see Variable Names.

Worksheet. Excel 95 or later files can contain multiple worksheets. By default, the Data Editorreads the first worksheet. To read a different worksheet, select the worksheet from the drop-downlist.

Range. For spreadsheet data files, you can also read a range of cells. Use the same method forspecifying cell ranges as you would with the spreadsheet application.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.4. Reading Excel Files

Read variable names. You can read variable names from the first row of the file or the first row ofthe defined range. Values that don't conform to variable naming rules are converted to validvariable names, and the original names are used as variable labels. For information on variablenaming rules, see Variable Names.

Worksheet. Excel files can contain multiple worksheets. By default, the Data Editor reads the firstworksheet. To read a different worksheet, select the worksheet from the drop-down list.

Range. You can also read a range of cells. Use the same method for specifying cell ranges as youwould in Excel.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.5. Reading Excel 95 or Later Files

The following rules apply to reading Excel 95 or later files:

Data type and width. Each column is a variable. The data type and width for each variable aredetermined by the data type and width in the Excel file. If the column contains more than one datatype (for example, date and numeric), the data type is set to string, and all values are read as validstring values.

Blank cells. For numeric variables, blank cells are converted to the system-missing value, indicated

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 33/38

by a period. For string variables, a blank is a valid string value, and blank cells are treated as validstring values.

Variable names. If you read the first row of the Excel file (or the first row of the specified range)as variable names, values that don't conform to variable naming rules are converted to validvariable names, and the original names are used as variable labels. For information on variablenaming rules, see Variable Names. If you do not read variable names from the Excel file, defaultvariable names are assigned.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.5.1. How to Read Excel 95 or Later Files

From the menus choose:

File > Open > Data…

In the Open File dialog box, select the type of file and the file you want to open.

Click Open.

If the first row of the spreadsheet contains column headings or labels, click Read variable names inthe Opening File Options dialog box.

If the data you want to read do not start in the first row of the spreadsheet, enter the cell range inthe Opening File Options dialog box.

If the data you want to read are not on the first sheet of the file, select the sheet you want toread.

If all of your data are read as string data, you probably tried to read the first row as data when itreally contains headings.

Show me

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.6. Reading older Excel files and other spreadsheets

The following rules apply to reading Excel files prior to Excel 95 and other spreadsheet data:

Data type and width. The data type and width for each variable are determined by the columnwidth and data type of the first data cell in the column. Values of other types are converted to thesystem-missing value. If the first data cell in the column is blank, the global default data type forthe spreadsheet (usually numeric) is used.

Blank cells. For numeric variables, blank cells are converted to the system-missing value, indicatedby a period. For string variables, a blank is a valid string value, and blank cells are treated as validstring values.

Variable names. If you do not read variable names from the spreadsheet, the column letters (A, B,C, ...) are used for variable names for Excel and Lotus files. For SYLK files and Excel files saved inR1C1 display format, the software uses the column number preceded by the letter C for variablenames (C1, C2, C3, ...).

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 34/38

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.7. Reading dBASE files

Database files are logically very similar to IBM® SPSS® Statistics data files. The following generalrules apply to dBASE files:

• Field names are converted to valid variable names. For information on variable naming rules, seeVariable Names.

• Colons used in dBASE field names are translated to underscores.

• Records marked for deletion but not actually purged are included. The software creates a newstring variable, D_R, which contains an asterisk for cases marked for deletion.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.8. Reading Stata files

The following general rules apply to Stata data files:

• Variable names. Stata variable names are converted to IBM® SPSS® Statistics variable namesin case-sensitive form. Stata variable names that are identical except for case are converted tovalid variable names by appending an underscore and a sequential letter (_A, _B, _C, ..., _Z,_AA, _AB, ..., and so forth).

• Variable labels. Stata variable labels are converted to SPSS Statistics variable labels.

• Value labels. Stata value labels are converted to SPSS Statistics value labels, except for Statavalue labels assigned to "extended" missing values.

• Missing values. Stata "extended" missing values are converted to system-missing values.

• Date conversion. Stata date format values are converted to SPSS Statistics DATE format (d-m-

y) values. Stata "time-series" date format values (weeks, months, quarters, and so on) areconverted to simple numeric (F) format, preserving the original, internal integer value, which isthe number of weeks, months, quarters, and so on, since the start of 1960.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.9. Reading Database Files

You can read data from any database format for which you have a database driver. In local analysismode, the necessary drivers must be installed on your local computer. In distributed analysis mode(available with IBM® SPSS® Statistics Server), the drivers must be installed on the remoteserver.See the topic Distributed Analysis Mode for more information.

Note: If you are running the Windows 64-bit version of SPSS Statistics, you cannot read Excel,Access, or dBASE database sources, even though they may appear on the list of available databasesources. The 32-bit ODBC drivers for these products are not compatible.

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 35/38

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.9.1. To Read Database Files

From the menus choose:

File > Open Database > New Query...

(Or choose Edit Query to work on a saved query)

Select the data source.

If necessary (depending on the data source), select the database file and/or enter a login name,password, and other information.

Select the table(s) and fields. For OLE DB data sources (available only on Windows operatingsystems), you can only select one table.

Specify any relationships between your tables.

Optionally:

• Specify any selection criteria for your data.

• Add a prompt for user input to create a parameter query.

• Save your constructed query before running it.

You can read data from any database format for which you have a database driver. In local analysismode, the necessary drivers must be installed on your local computer. In distributed analysis mode(available with the server version), the drivers must be installed on the remote server.

To add data sources in distributed analysis mode, see your system administrator.

Show me

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.9.2. Selecting a Data Source

Use the first screen of the Database Wizard to select the type of data source to read.

ODBC Data Sources

If you do not have any ODBC data sources configured, or if you want to add a new data source,click Add ODBC Data Source.

• On Linux operating systems, this button is not available. ODBC data sources are specified inodbc.ini, and the ODBCINI environment variables must be set to the location of that file. Formore information, see the documentation for your database drivers.

• In distributed analysis mode (available with IBM® SPSS® Statistics Server), this button is notavailable. To add data sources in distributed analysis mode, see your system administrator.

An ODBC data source consists of two essential pieces of information: the driver that will be usedto access the data and the location of the database you want to access. To specify data

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 36/38

sources, you must have the appropriate drivers installed. Drivers for a variety of database formatsare included with the installation media.

OLE DB Data Sources

To access OLE DB data sources (available only on Microsoft Windows operating systems), youmust have the following items installed:

• .NET framework. To obtain the most recent version of the .NET framework, go tohttp://www.microsoft.com/net.

• IBM® SPSS® Data Collection Survey Reporter Developer Kit. For information on obtaining acompatible version of Survey Reporter Developer Kit, go to www.ibm.com/support.

The following limitations apply to OLE DB data sources:

• Table joins are not available for OLE DB data sources. You can read only one table at a time.

• You can add OLE DB data sources only in local analysis mode. To add OLE DB data sources indistributed analysis mode on a Windows server, consult your system administrator.

• In distributed analysis mode (available with SPSS Statistics Server), OLE DB data sources areavailable only on Windows servers, and both .NET and Survey Reporter Developer Kit must beinstalled on the server.

To add an OLE DB data source:

Click Add OLE DB Data Source.

In Data Link Properties, click the Provider tab and select the OLE DB provider.

Click Next or click the Connection tab.

Select the database by entering the directory location and database name or by clicking the buttonto browse to a database. (A user name and password may also be required.)

Click OK after entering all necessary information. (You can make sure the specified database isavailable by clicking the Test Connection button.)

Enter a name for the database connection information. (This name will be displayed in the list ofavailable OLE DB data sources.)

Click OK.

This takes you back to the first screen of the Database Wizard, where you can select the savedname from the list of OLE DB data sources and continue to the next step of the wizard.

Deleting OLE DB Data Sources

To delete data source names from the list of OLE DB data sources, delete the UDL file with thename of the data source in:

[drive]:\Documents and Settings\[user login]\Local Settings\Application Data\SPSS\UDL

IBM SPSS Collaboration and Deployment Services Enterprise View Driver

The IBM® SPSS® Collaboration and Deployment Services Enterprise View Driver--available toIBM® SPSS® Collaboration and Deployment Services customers--allows you to access data fromthe IBM® SPSS® Collaboration and Deployment Services Enterprise View. Use of the IBM SPSS

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 37/38

Collaboration and Deployment Services Enterprise View Driver requires the Statistics Adapter optionand a connection to a IBM® SPSS® Collaboration and Deployment Services Repository.

The driver uses Data Provider Definitions (DPD) to access data. A DPD maps the virtual table andcolumn definitions from an application view to the physical tables where data resides, whether in adata warehouse, an operational data store, or an online transactional database. DPD's are definedagainst particular ODBC data sources. To use a DPD, you must have an ODBC data source (definedon the machine that will access the data) with the same name, and which connects to the samedata store, as the one referenced in the DPD. Contact your IBM SPSS Collaboration andDeployment Services administrator to obtain the necessary information.

Once you have added the necessary ODBC data sources, you can access your data with the IBMSPSS Collaboration and Deployment Services Enterprise View Driver.

Select IBM SPSS Collaboration and Deployment Services Enterprise View Driver from the list of ODBCData Sources.

Click Next.

If there is no current connection to a repository, the Connect dialog box opens, allowing you toestablish a connection. Once a connection is established, the IBM SPSS Collaboration andDeployment Services Enterprise View Driver Details dialog box opens.

Select the Application View containing the desired data.

Select the environment that specifies the desired subset of data from the application view. Forexample, when analytic is selected, only those application view columns defined as analytic areavailable. The environment specifies which data providers are available. The default environment isanalytic.

Select from the list of available Data Provider Definitions for the selected application view andenvironment.

Select the label for the desired version of the application view.

Click Continue.

This takes you to the next step of the wizard.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.9.3. Selecting Data Fields

The Select Data step controls which tables and fields are read. Database fields (columns) are readas variables.

If a table has any field(s) selected, all of its fields will be visible in the following Database Wizardwindows, but only fields that are selected in this step will be imported as variables. This enablesyou to create table joins and to specify criteria by using fields that you are not importing.

Displaying field names. To list the fields in a table, click the plus sign (+) to the left of a tablename. To hide the fields, click the minus sign (–) to the left of a table name.

To add a field. Double-click any field in the Available Tables list, or drag it to the Retrieve Fields InThis Order list. Fields can be reordered by dragging and dropping them within the fields list.

To remove a field. Double-click any field in the Retrieve Fields In This Order list, or drag it to the

6/18/13 Help

upendra_laptop:58451/help/advanced/print.jsp?topic=/../nav/0&confirmed=true 38/38

Available Tables list.

Sort field names. If this check box is selected, the Database Wizard will display your availablefields in alphabetical order.

By default, the list of available tables displays only standard database tables. You can control thetype of items that are displayed in the list:

• Tables. Standard database tables.

• Views. Views are virtual or dynamic "tables" defined by queries. These can include joins ofmultiple tables and/or fields derived from calculations based on the values of other fields.

• Synonyms. A synonym is an alias for a table or view, typically defined in a query.

• System tables. System tables define database properties. In some cases, standard databasetables may be classified as system tables and will only be displayed if you select this option.Access to real system tables is often restricted to database administrators.

Note: For OLE DB data sources (available only on Windows operating systems), you can selectfields only from a single table. Multiple table joins are not supported for OLE DB data sources.

© Copyright IBM Corporation 1989, 2012.

\n\ \n\ Next\n\ \n\ \n\ "); }

1.3.1.9.4. Creating a Relationship between Tables

The Specify Relationships step allows you to define the relationships between the tables for ODBCdata sources. If fields from more than one table are selected, you must define at least one join.

Establishing relationships. To create a relationship, drag a field from any table onto the field towhich you want to join it. The Database Wizard will draw a join line between the two fields,indicating their relationship. These fields must be of the same data type.

Auto Join Tables. Attempts to automatically join tables based on primary/foreign keys or matchingfield names and data type.

Join Type. If outer joins are supported by your driver, you can specify inner joins, left outer joins,or right outer joins.

• Inner joins. An inner join includes only rows where the related fields are equal.

• Outer joins. In addition to one-to-one matching with inner joins, you can also use outer joins tomerge tables with a one-to-many matching scheme. For example, you could match a table inwhich there are only a few records representing data values and associated descriptive labelswith values in a table containing hundreds or thousands of records representing surveyrespondents. A left outer join includes all records from the table on the left and, from the tableon the right, includes only those records in which the related fields are equal. In a right outerjoin, the join imports all records from the table on the right and, from the table on the left,imports only those records in which the related fields are equal.

© Copyright IBM Corporation 1989, 2012.