02 data collection

Upload: nicole-diane-bajao-otayde

Post on 05-Apr-2018

222 views

Category:

Documents


0 download

TRANSCRIPT

  • 7/31/2019 02 Data Collection

    1/47

    Statistical DataCollection &

    Sampling

    Techniques

  • 7/31/2019 02 Data Collection

    2/47

    2

    It is a capital mistake to theorize

    before one has data.

    -Sir Arthur Conan Doyle as SherlockHolmes

  • 7/31/2019 02 Data Collection

    3/47

    How important is it?

    Data collection is an extremely importantpart of any research because the

    conclusions of a study are based on whatthe data reveal.

    There are several ways of collecting data.The choice of procedures usually dependson the objectives and design of the studyand the availability of time, money andpersonnel.

  • 7/31/2019 02 Data Collection

    4/47

    Examples of data

    Demographic information such as age,sex, household size, civil status orreligion.

    Social and economic information such aseducational attainment, health status,extent of participants in socialorganizations, occupation, income,

    housing condition and the like.

    Scores in exams, grades, etc.

  • 7/31/2019 02 Data Collection

    5/47

    Types of Research Data

    Generally classified as:1. quantitative or

    2. qualitative

    Types based on their source:

    1. Primary

    2. Secondary

  • 7/31/2019 02 Data Collection

    6/47

    Quantitative and Qualitative Data

    1. Quantitative Data

    - are information which can becounted or expressed in numericalvalues.

    Ex: age, grades, income, test score,number of children, level ofsatisfaction, amount of sales, lengthof service, etc.

  • 7/31/2019 02 Data Collection

    7/47

    2. Qualitative Data

    These are descriptive information which hasno numerical values.

    Ex: attitude or perception towards something,

    process used in accomplishing an activity, apersons experiences, ones idea about

    certain concepts, situation, or phenomenonlike drug abuse , family planning,

    immunization, etc.

  • 7/31/2019 02 Data Collection

    8/47

    Primary and Secondary data

    According to source, data mayalso be classified as Primary or

    secondary. Two importantquestions to be considered are:Who will provide that data?

    Where will the data be collected?

  • 7/31/2019 02 Data Collection

    9/47

    Primary Data

    These are informationcollected directly from thesubjects being studied,such are people, areas, or

    objects

  • 7/31/2019 02 Data Collection

    10/47

    Primary Data - Examples

    o Surveys

    o Focus groups

    o Questionnaireso Personal interviews

    o Experiments and observational

    study

  • 7/31/2019 02 Data Collection

    11/47

    Secondary Data

    These are information collected

    from other available sources, like

    recent censuses, or data collectedby large scale national or worldwide surveys, such as agriculture

    and industry surveys, demographicand health surveys, data ofcompleted studies.

  • 7/31/2019 02 Data Collection

    12/47

    Secondary DataExamples of

    Sources

    o City/municipal health offices

    o Vital Statistics birth, death certificates

    o

    Hospital, clinic, school nurse recordso Private and foundation databases

    o City and government records

    o Surveillance data from governmentprograms

    o Census, NSO, etc.

  • 7/31/2019 02 Data Collection

    13/47

    Techniques of Collecting Data

    The choice of the best way to collect datadepends largely on the type of data to becollected and the source of data. Before

    starting to collect data, a researchershould decide:

    A. What data to collect,

    B. Where or from whom the data will beobtain,

    C. What instrument/s or device/s to use incollecting the data.

  • 7/31/2019 02 Data Collection

    14/47

    METHODS OF COLLECTING DATA:

    1. Surveys

    a. Interview method

    b. Indirect/questionnaire method2. Registration method3. Observation method

  • 7/31/2019 02 Data Collection

    15/47

    15

    Survey Types

    Surveys can be

    descriptive or explanatory

    involve entire populations or samplesof populations

    capture a moment or map trends

    can be administered in a number ofways

  • 7/31/2019 02 Data Collection

    16/47

    16

    Survey Construction

    Survey construction involves

    formulating questions and response

    categorieswriting up background information

    and instruction

    working through organization andlength

    determining layout and design

  • 7/31/2019 02 Data Collection

    17/47

    less expensive than an interview.

    Less time - consuming

    Can cover greater number of respondents

    Can easily gather data.

    Can give confidential response since theycan answer them in private.

    Answers obtained are free from anyinfluence from the interviewer.

  • 7/31/2019 02 Data Collection

    18/47

    Yield limited responses. Cannot ask morequestions

    Mailed questionnaire -less turn-out/ High

    proportion of non-return Can be influenced by coaching.

    Tends to yield wrong information since it givesincomplete information

    Questionnaires cannot be used on illiteraterespondents.

  • 7/31/2019 02 Data Collection

    19/47

    a face to face interaction between thedata collector (the interviewer), andthe source of information (the

    respondent).The interviewer directly asks the

    respondent questions from a

    prepared instrument, which is calledan Interview Schedule.

  • 7/31/2019 02 Data Collection

    20/47

    20

    involves asking respondents a series ofopen-endedquestions

    can generate both standardized

    quantifiable data, and more in-depthqualitative data

    However, the complexities of people

    and the complexities of communicationcan create many opportunities formiscommunication andmisinterpretation

  • 7/31/2019 02 Data Collection

    21/47

    21

    Interview Types

    Interviews can range from

    formal to informal

    structured to unstructuredcan be one on one or involve

    groups

  • 7/31/2019 02 Data Collection

    22/47

    The interviewer can observe thebody language of the respondent.

    The interviewer can probe forclarification of ambiguousresponses.-raise as many questions

    Interview is effective for semi-literateor illiterate respondents.

    The expected response rate in aninterview is high.

  • 7/31/2019 02 Data Collection

    23/47

    More expensive because of travel cost.

    Skilled interviewer is required. Trainingis needed for those who lack experience

    and/ or those who are not yet skilled inconducting interviews.

    Time-consuming

    May give bias response to theinterviewer which for him can satisfy theinterviewer.

  • 7/31/2019 02 Data Collection

    24/47

    In-depth interview

    To answer Howand Whyquestions

    USE FGD OR KII.

    1. Example: In a Study about domestic violence, with avictim as key informant, the interviewer may ask:

    Some people believe that men have the right to

    discipline their wives. Do you share the same belief?(Probe) Why or why not?

    2. In a study on students attitude towards cheating inclass, with teachers as key informants, the interviewermay ask:

    Why do you think student cheat? (Probe) Can youexplain what you mean by habit?

    Is cheating rampant in your classes? How rampant it is?(Probe) Why is it so?

    Focus Group Discussion (FGD)

  • 7/31/2019 02 Data Collection

    25/47

    Observation - oldest

    A. Participant Observation

    B. Non-Participant Observation

    Content Analysis

  • 7/31/2019 02 Data Collection

    26/47

    Observation

    relies on the researchers ability to gatherdata through their senses - and allowsresearchers to document actual behaviourrather than responses related to behaviour

    However, the observed can act differentlywhen surveilled, and observations can betainted by a researchers worldview

    Hawthorne's effect

  • 7/31/2019 02 Data Collection

    27/47

    Observation Types

    Observation can range from

    non-participant to participant

    candid to covertfrom structured to unstructured

  • 7/31/2019 02 Data Collection

    28/47

    Experimentation explores causeand effect relationships by

    manipulating independent variablesin order to see if there is acorresponding effect on a

    dependent variable

  • 7/31/2019 02 Data Collection

    29/47

    Experimentation

    Pure experimentation requires both

    a controlled environment and the

    use of a randomly assigned controlgroup

    This can be difficult to achieve in

    human centred experimentsconducted in the real-world

  • 7/31/2019 02 Data Collection

    30/47

  • 7/31/2019 02 Data Collection

    31/47

    Data collection choice

    What you must ask yourself:

    Will the data answer my research

    question?

  • 7/31/2019 02 Data Collection

    32/47

    Data collection choice

    To answer that

    You much first decide what your

    research question isThen you need to decide what

    data/variables are needed to

    scientifically answer the question

  • 7/31/2019 02 Data Collection

    33/47

    Data collection choice

    If that data exist in secondary form,

    then use them to the extent you

    can, keeping in mind limitations.But if it does not, and you are able

    to fund primary collection, then it is

    the method of choice.

  • 7/31/2019 02 Data Collection

    34/47

  • 7/31/2019 02 Data Collection

    35/47

    Main aim: to obtain a samplethat is representative of the

    target population

  • 7/31/2019 02 Data Collection

    36/47

    - attempt to select units such

    that each has a definable

    probability of being chosen.

    - attempts to ensure that each

    unit has the same chance ofbeing included as every other

    unit in the sample frame.

  • 7/31/2019 02 Data Collection

    37/47

    - are all sampling procedures in which theunits that make up the sample are

    collected with no specific probability

    structure in mind.Examples: volunteer respondents, most

    easily accessible (in geographical terms,

    payment for participation, considered by

    the researcher as in some way typical ofthe target population, units are chosen

    with no obvious design

  • 7/31/2019 02 Data Collection

    38/47

    38

    Methods of Sampling

    Simple Random sampling

    Systematic sampling

    Convenience sampling Stratified sampling

    Quota Sampling

  • 7/31/2019 02 Data Collection

    39/47

    39

    Simple Random Sampling Selection so that each individual member has an

    equal chance of being selected (eg. Roll of dice,random number tables, fishbowl method)

    Systematic Sampling Select some starting point and then select every

    kth element in the population

  • 7/31/2019 02 Data Collection

    40/47

    40

    Convenience Sampling Use results that are easy to get

  • 7/31/2019 02 Data Collection

    41/47

    41

    Stratified Sampling First need to split the population into sub-populations Draw a sample from each stratum

  • 7/31/2019 02 Data Collection

    42/47

    - interviews, mail surveys, telephone

    surveys are some examples.

    - is based on defining the distribution of

    characteristics required in the sample,and selecting respondents until a quota

    has been filled.

    Example: 50 women, 50 men

  • 7/31/2019 02 Data Collection

    43/47

    Assignment : by pair (1 yellow

    paper)

    Look for 5 theses (published orunpublished, local or international) at thelibrary or the internet.

    Cite the title of the study and the authorsproperly.

    Identify the IV and the DV of the study.

    Identify the sampling method used in thestudy

    NOTE: No Same Study Please

  • 7/31/2019 02 Data Collection

    44/47

    Study:

    Demographics vs. epidemiology

    Latest Philippine Demographic profile

    National Health Situation

    Top ten leading cause of deaths

    Formulas and computations on:

    Mortality rate (infant & maternal)

    Morbidity rate

    Crude birth rate

    Crude death rate

    Incidence rate

  • 7/31/2019 02 Data Collection

    45/47

    5 members per group

    Submit a letter to the medical director ofany hospital in Midsayap (MDC,AMADO, COHESCO, Pesante) to allow

    you to interview their billing and recordspersonnel.

    Submit to me a copy of the letterapproved by the medical director.

    Topics co ered

  • 7/31/2019 02 Data Collection

    46/47

    Topics covered:

    1. Population census

    2. Percentage of occupancy3. Mortality/morbidity rates

    4. Computation of bills (Length of

    stay/discharge)5. Miscellaneous rates

  • 7/31/2019 02 Data Collection

    47/47

    -end -