surveys 600530017 602530008 602530013 2013/12/09
TRANSCRIPT
Surveys
授課老師: 洪新原 老師報 告 者: 600530017 鄧任
宏602530008 蔡秉廷602530013 傅翊宸
日 期: 2013/12/09
Data Collection Approach:Impact on the Research Process
2
Selecting a Communication Data Collection Method
3
Communication Approach(1/2)
• The communication approach involves surveying or interviewing people and recording their responses for analysis.– A survey is a measurement process used to collect
information during a highly structured interview.– Questions are carefully chosen or crafted,
sequenced, and precisely asked of each participant.– The goal of the survey is to derive comparable data
across subsets of chosen sample so that similarities and differences can be found.
4
Communication Approach(2/2)
• Versatility• Efficiency• Geographic coverage
Strengths
• ErrorWeaknesses
5
Error Sources
Measurement Questions and
Survey InstrumentsInterviewer Participant
Error in Communication Research(1/2)
6
Error in Communication Research(2/2)
• Researchers cannot help a business decision maker answer a research question if they:1) Select or craft inappropriate questions2) Ask them in an inappropriate order3) Use inappropriate transitions and instructions to
elicit information
7
Interviewer Error
• A major source of sampling error and response bias, is caused by numerous actions:1) Failure to secure full participant cooperation (sampling
error).2) Failure to record answers accurately and completely (data
entry error).3) Failure to consistently execute interview procedures.4) Failure to establish appropriate interview environment.5) Falsification of individual answers or whole interviews.6) Inappropriate influencing behavior.7) Physical presence bias.
8
Participant Error
• Three broad conditions must be met by participants to have a successful survey:1) The participant must possess the information
being targeted by the investigative questions.2) The participant must understand his or her role
in the interview as the provider of accurate information.
3) The participant must have adequate motivation to cooperate.
9
Participation-Based Errors
• Three factors influence participation:1) The participant must believe that the experience
will be pleasant and satisfying.2) The participant must believe that answering the
survey is an important and worthwhile use of his or her time.
3) The participant must dismiss any mental reservations that he or she might have about participation.
10
Factors Influencing Participant Motivation
Source: Influenced by Robert L. Kahn and Charles F. Cannell, "Interviewing", in David L. Sills, ed., Internation Encyclopedia of the Social Sciences, vol. 8, p. 153. Copyright © 1968 by Crowell Collier and Macmillan, Inc. 11
Nonresponse Error
• In surveys, nonresponse error occurs when the responses of participants differ in some systematic way from the responses of nonparticipants.1) The researcher cannot locate the person.2) The researcher is unsuccessful in encouraging
that person to participate.
12
Response-Based Errors(1/2)
• Response errors is generated in two way: when the participant fails to give a correct answer or fails to give the complete answer.
• If we ask participants to report on events that they have not personally experienced, we need to assess the replies carefully.
• Participants also cause error by responding in such a way as to unconsciously or consciously misrepresent their actual behavior, attitudes, preferences, motivations, or intentions (response bias).
13
Response-Based Errors(2/2)
• Participants create response bias when they modify their responses to be socially acceptable or to save face or reputation with the interviewer (social desirability bias), and sometimes even in an attempt to appear rational and logical.
• One major cause of response bias is acquiescence - the tendency to be agreeable.
• Participants may also interpret a question or concept differently from what was intended by the researcher. This occurs when the researcher uses words that are unfamiliar to participant. Thus, the individual answers a question that is different from the one the researcher intended to ask.
14
Self-Administered Surveys
• Self-administered surveys– Mail survey(Fax & Courier service)– Intercept studies– Computer-delivered(also labeled CASIs)– Disk-by-Mail survey
15
Self-Administered Surveys• The Web as a Survey Research VenueAdvantages• Short turnaround of results.• Ability to use visual stimuli.• Ability to do numerous surveys over time.• Ability to attract participants who wouldn’t
participate in another research project.• Participants feel anonymous.• Shortened turnaround from questionnaire
draft to execution of survey.
16
Self-Administered Surveys• The Web as a Survey Research VenueDisadvantages• Recruiting the right sample is costly and time-
consuming.• Converting surveys to the web can be expensive.• It takes technical as well as research skill to field a
Web survey.• While research is more compatible with numerous
browsers, the technology isn’t perfect
17
Evaluation of the Self-Administered Surveys
• It cost less than surveys via personal interview.Costs
• It can contact participants who might otherwise be inaccessible.
Sample Accessibility
• It can take more time to collect facts.Time constraints
• It provide more anonymity than other communication modes.Anonymity
• The type and amount of information that can be secured is a major limitation of self-administered surveys.
Topic Coverage18
Maximizing Participation in the Self-Administered Survey(1/3)
The key points of the survey process where the response may break down
• The wrong address, e-mail or postal.• The envelope or fax cover sheet may look like junk
mail.• Lack of proper instructions for completion.• A participant may find no convincing inducement.• A participant may temporarily set the questionnaire
aside.
19
Maximizing Participation in the Self-Administered Survey(2/3)
Using Total Design Method(TDM) to minimize the burden on participants by designing questionnaires
• Are easy to read.• Offer clear response directions.• Include personalized communication.• Provide information about the survey via advance
notification.• Encourage participants to respond.
20
Maximizing Participation in the Self-Administered Survey(3/3)
Several practical suggestions of methodological article which can improve response rate
• Advance notification of the delivery of a self-administered questionnaire.
• Reminders after the delivery of a self-administered questionnaire .
• Clearly specified return directions and devices .• Monetary incentives for participation.• An appeal for participant is essential.
21
Self-Administered Survey Trends(1/5)
Computer surveying is surfacing.• At trade shows, it provides a stimulus for
attendees to visit a particular exhibit, and gives the exhibitor detailed information for evaluating the productivity.
• In companies, it is used to evaluate employee polices and behaviors.
• On web sites, it is used to find registration procedures and full-scale surveying.
22
Self-Administered Survey Trends(2/5)
The Web-based questionnaire:• A measurement instrument both delivered and
collected via the Internet.• It has the power of computer-assisted telephone
interview systems, but without the expense of network administrators, specialized software, or additional hardware.
• Most software products has the design features that allow custom survey creation and modification.
23
Self-Administered Survey Trends(3/5)
• Two primary options:– A proprietary solutions offered through research
firms.• Problem formulation, questionnaire design, etc.• Supplier’s staff generate the questionnaire HTML code.• Supplier’s staff hosts the survey at their server.• Supplier’s staff provides data consolidation and reports.
24
Self-Administered Survey Trends(4/5)
• Two primary options:– An off-the-shelf software designed for researchers
who possess the knowledge and skills.– Advantages• Questionnaire design in a word processing environment.• Ability to import questionnaire forms from text files.• A coaching device to guide you through question and
response formatting.• Question and scale libraries.• Flexible analysis and reporting mechanisms.
25
Self-Administered Survey Trends(5/5)
• A Web survey is much less expensive than conventional survey research.
• Any instrument may be configured as an e-mail questionnaire.
• The computer-delivered survey has made it possible to use many of the suggestions for increasing participation.
26
27
Survey via Telephone Interview
• The telephone survey is still the workhouse of survey research.
• Telephone service penetration access to participants through low-cast , efficient means has made telephone interviewing a very attractive alternative for researches.
28
Evaluation of the Telephone Interviewing
• One study reports that sampling and data collection costs for telephone surveys can run from 45 to 64 percent lower than costs for comparable personal interview
29
Evaluation of the Telephone Interviewing
Computer-assisted telephone interview(CATI)• CATI works with a telephone number management
system to select numbers, dial the sample , and enter responses.
Computer-administered telephone• Unlike CATI, there is no human interviewer.• A computer calls the phone number, conducts the
interview, places data into a file for later tabulation, and terminates the contact .
30
Evaluation of the Telephone Interviewing
• CATI is often compared to the self-administered questionnaire and offers the advantage of enhanced participant privacy .
• Study found that rejection of this mode of data collection affects the refusal rate.
• Noncontact rate is a ratio of potential but unreached contacts to all potential contacts
• Refusal rate refers to the ratio of contacted participants to all potential contacts
31
Disadvantages of the Telephone Survey
• Inaccessible households• Inaccurate or nonfunctioning numbers• Limitation on Interview length• Limitation on use of visual or complex question• Ease of interview termination• Less participant involvement• Distracting physical environment
32
Disadvantages of the Telephone Survey
Inaccessible households
• rural households • households with incomes below the poverty line• more households are using filtering devices and services• the number of inaccessible individuals continue to increase
as cellular/wireless phone use increases
A random dialing procedure is designed to reduce some of this bias.
33
Disadvantages of the Telephone Survey
Inaccurate or nonfunctioning numbers• several methods have been developed to overcome the
deficiencies of directories.• choosing phone number by random dialing of
combination of directories and random dialing
Limitation on Interview length• 10 minutes has generally been thought of as ideal, but
interviews of 20 minutes or more are not uncommon
34
Disadvantages of the Telephone Survey
Limitation on use of visual or complex question• visual or complex question is possible with personal
interviewing , CASI ,or WWW survey.• interviewers have supplied these prior to a prescheduled
interview via fax , email , or the Internet.
Ease of interview termination
• participants find it easier to terminate a phone interview.public reason to investigative report of wrongdoing and unethical behavior
35
Disadvantages of the Telephone Survey
Less participant involvement• telephone surveys can result in less through
responses• persons interviewed by phone find the experience
to be less rewarding than personal interview
Distracting physical environment• replacement of home or office phones with cellular
and wireless phone also raises concerns
36
Telephone Survey Trends
• Future trends in telephone surveying bear watching.• Other findings suggested 1. individuals with answering machines were more likely to participate. 2. machine use was more prevalent on weekends than on weekday evenings 3. machines were more commonplace in urban than in rural.• Telemarketers might be the catalyst , but legitimate research
will suffer
37
Survey via Personal Interview
• A survey via personal interview is a two-way conversation between a trained interviewer and a participant
38
Evaluation of the Personal Interview Survey
Advantages• depth of information and detail• have more control than other kinds of
communication studies• computer-assisted personal interview (CAPI) for
using special scoring devices and visual materials
39
Evaluation of the Personal Interview Survey
Disadvantages• personal interviewing is costly in terms of both
money and time• Some unwilling to invite strangers into homes• Interviewer bias possible
Exception • Survey via intercept interviews that targets in
centralized locations reduce costs (interviewers, training, effectiveness)
Selecting an Optimal Survey Method
Self-Administered Survey
TelephoneSurvey
Survey viaPersonal Interview
Advantages • Access inaccessible participants
• Incentives for higher response rates
• Lowest-cost• Geographic coverage• Minimal staff needed• Perceived anonymity• Reflection time
• Lower costs than personal interview
• Wide geographic coverage
• Fewer Interviewers
• Reduced interviewer bias
• Fast completion time
• Good cooperation rates
• Interviewer can probe and explain
• Visual aids possible
• Interviewer can prescreen
• CAPI possible
40
Self-Administered Survey
TelephoneSurvey
Survey viaPersonal Interview
Dis-advantages
• Low response rates in some modes
• No interviewer intervention
• Cannot be too long• Cannot be too
complex• Requires accurate list
• Response rate is lower than for personal interview
• Higher costs if geographically dispersed sample
• Limited Interview length
• Response may be less complete
•High costs•Need for highly trained interviewers•Time consuming•Labor-intensive•Some unwilling to invite strangers into homes•Interviewer bias possible
Selecting an Optimal Survey Method
41
• In an inaccessible participants situation, the telephone interview, mail survey, or computer-delivered survey should be considered.
• If data must be collected very quickly, the mail survey would likely be ruled out because of lack of control over the returns
• In an objective which requires extensive questioning and probing, the survey via personal interview should be considered.
Selecting an Optimal Survey Method
42
• If none of the choices turns out to be a particularly good fit, it is possible to combine the best characteristics of two or more alternatives into a hybrid survey.
• Although this decisions will incur the costs of combined modes, the flexibility of tailoring method to your unique needs is often an acceptable trade-off.
Selecting an Optimal Survey Method
43
• All researchers are confronted by the practical realities of cost and deadlines.
• As Exhibit 10-5 suggests, a conclusion was made as follows.
Surveys via personal interview
Telephone surveys
Self-administered surveys
Cost High Middle Lost
Time-consuming High Middle Lost
Selecting an Optimal Survey Method
44
• Most of the time, an optimal method will be apparent, however managers’ needs for information often exceed their internal resources.
• So managers will seek assistance from research vendors of survey-related services.
• Outsourcing Survey Services
Selecting an Optimal Survey Method
45
• Outsourcing Survey Services– Commercial suppliers of research services vary
from full-service operations to specially consultants.
– The exploratory work, design, sampling, data collection, or processing and analysis may be contracted separately or as a whole.
– Research firms also offer special advantages that their clients do not typically maintain in-house.
Selecting an Optimal Survey Method
46
Thank you for your listening
47