Websurvey

1
E-Survey Workshop Guidelines I and Practice
??? ????????????
2
What is Electronic Survey?

• Email Survey
• Web-based Survey

Why E-Survey?
The rapid development of surveys on the WWW is
leading some to argue that soon internet surveys
will replace traditional methods of survey data
collection. Major advantages have been mentioned
cost savings, speed, limited geographical
constraint, ease of contacting respondents, more
efficient data processing, ability for
customization. Others are urging caution or even
voicing skepticism about the future role Web
surveys will play.
3
Promises and Challenges

• Promises
• Strong reach / Penetration
• Fast response speed
• Low cost
• Response flexibility
• Control of anonymity
• Minimized data-entered error
• Minimized interviewer bias

4
Promises and Challenges

• Challenges
• Generalizability and Response Rate
• response rate to internet based surveys have
  been declining over the past 10 years
• Accessibility
• no national or global online directory of email
  addresses exist
• Design Concerns
• use design survey response features judiciously
  to maximize data quality and minimize error

5
Sources of Errors in Web-based Survey

• Coverage Error
• The result of all units in a defined population
  not having a known nonzero probability of being
  included in the sample drawn to represent the
  population. A mismatch between the target
  population and the frame population.

6
Sources of Errors in Web-based Survey

• Coverage Error
• Universal coverage of the Web remains quite
  limited. Coverage error represents the biggest
  threat to the representativeness of sample
  surveys conducted via the internet.
• Some populations do not exhibit large coverage
  problems employees of certain organizations,
  members of professional organizations, certain
  types of businesses, students at many
  universities and college, and groups with high
  levels of education

7
Sources of Errors in Web-based Survey

• Sampling error
• The result of surveying a sample of the
  population rather than the entire population. Not
  all members of the frame population are measured.

8
Sources of Errors in Web-based Survey

• Sampling error

• While coverage error refers to people missing
  from the frame, sampling error arises during the
  process of selecting a sample from the frame
  population, necessitating a means of identifying
  people on the frame.
• A misguided assumption behind many Web surveys
  that large samples necessarily mean more valid
  responses.

9
Sources of Errors in Web-based Survey

• Measurement error
• The result of inaccurate responses that stem
  from poor question wording, poor interviewing
  survey mode effects and/or some aspect of the
  respondents behavior.

10
Sources of Errors in Web-based Survey

• Measurement error
• Measurement error is the deviation of the answers
  of respondents from their true values on the
  measure.
• The appearance of a survey can vary from
  respondent to respondent because of different
  browser settings, user preferences, variations in
  hardware, and so on.
• There is much work to be done to determine
  optimal designs for different groups of
  respondents and types of surveys.

11
Sources of Errors in Web-based Survey

• Non-response error
• The result of non-response from people in the
  sample, who, if they had responded, would have
  provided different answers to the survey
  questions than those who did respond to the
  survey.

12
Sources of Errors in Web-based Survey

• Non-response error
• Non-response error arises through the fact that
  not all people included in the sample are willing
  or able to complete the survey.
• Non-response error is a function of both the
  rates of non-response and of the differences
  between respondents and non-respondents on the
  variables of interest.
• There is at present little experimental
  literature on what works and what does not, in
  terms of increasing response rates to web surveys.

13
Types of Web survey (Couper, 2001)

• Probability-based Web-based surveys
• Intercept surveys
• List-based samples of high coverage populations
• Mixed-mode designs with choice of completion
  method
• Pre-recruited panels of internet users
• Probability samples of full population
• Non-Probability-based Web-based survey
• Polls as entertainment
• Unrestricted self-selected surveys
• Volunteer opt-in panels

14
Seven Response Types for Web-based Surveys
(Bosnjak and Tuten, 2001)

• Unit non-responders
• Complete responders
• Answering drop-outs
• Lurkers
• Lurking drop-outs
• Item non-responders
• Item non-responding dropouts

15
Seven Response Types for Web-based Surveys
(Bosnjak and Tuten, 2001)
Source Bosnjak and Tuten,2000 (http//ascusc.org/
jcmc/vol6/issue3/boznjak.html)
16
Design of Web-bases Surveys (Dillman and Bowker,
2001)

• Introduce the web questionnaire with a welcome
  screen (Non-response error)
• Provide a PIN number (Sampling, Coverage)
• First question should be interesting to most
  respondents, easily answered, and fully visible
  on the first screen of the questionnaire.
  (Non-response)
• Present each question in a conventional format
  similar to that normally used on paper
  self-administered questionnaires. (Measurement,
  Non-response)

17
Design of Web-bases Surveys (Dillman and Bowker,
2001) (Cont.)

• Restrain the use of color so that figure/ground
  consistency and read-ability are maintained,
  navigational flow is unimpeded, and measurement
  properties of questions are maintained.
  (Measurement)
• Avoid differences in the visual appearance of
  questions that result from different screen
  configurations, operating systems, browsers,
  partial screen displays and wrap-around text.
  (Coverage, Measurement, Non-response)

18
Design of Web-bases Surveys (Dillman and Bowker,
2001) (Cont.)

• Provide specific instructions on how to take each
  necessary computer action for responding to the
  questionnaire and other necessary instructions at
  the point where they are needed. (Non-response)
• Use drop-down boxes sparingly, consider the mode
  implication, and identify each with a click
  here instruction. (Measurement)
• Do not require respondents to provide an answer
  to each question before being allowed to answer
  any subsequent ones. (Non-response)

19
Design of Web-bases Surveys (Dillman and Bowker,
2001) (Cont.)

• Provide skip directions in a way that encourages
  marking of answers and being able to click to the
  next applicable question. (Measurement)
• Construct web questionnaires so they scroll from
  question to question unless order effects are a
  major concern, and/or telephone and web survey
  results are being combined. (Coverage,
  Measurement, Non-response)
• When the number of answer choices exceeds the
  number that can be displayed in a single column
  on one screen, consider double-banking with an
  appropriate grouping device to link them
  together. (Measurement)

20
Design of Web-bases Surveys (Dillman and Bowker,
2001) (Cont.)

• Use graphical symbols or words that convey a
  sense of where the respondent is in the
  completion process, but avoid ones that require
  significant increases in computer memory.
  (Coverage, Non-response)
• Exercise restraint in the use of question
  structures that have known measurement problems
  on paper questionnaires, e.g. check-all-that-apply
  and open-ended questions. (Measurement,
  Non-response)

21
Other Web Survey Design Suggestion Zanutto (2001)

• Use a cover letter with the questionnaire
• Make the survey simple, and have it take no
  longer than 20 minutes
• Give an estimated time that it will take to
  complete the survey
• Be sure the first question is interesting, easy
  to answer, and related to the topic of the survey
• Be concerned about privacy issues for the
  respondents and the data that is collected.
• Allow an alternate mode of completion if people
  are concerned about privacy, i.e. print and mail
  in the survey.

22
E-Survey Workshop Part III ????
???????????? ???
23
????Web-survey
24
??????????
25
The Advantage of Web-Survey

• Cost saving
• Ease of contacting respondents
• More efficient data processing
• Ability for customization

26
How to designSTEP1Introduction
27
STEP2Layout

• (1)??????
• ??????
• ????
• ????
• (2)??????
• ??????800600,???????????????????

28
STEP3Webpage Component

• Frame(??)
• Radio(???)
• Checkbox(???)
• Drop-Down(???)
• Text(???)
• Hyperlink(???)

29
STEP4Save Result

• ???
• ??HTML??,????????? FrontPage?Dreamwaver?,????????
  ???,?????????????????,??????
• ???
• ?????????????,???????????????????,???????????????
  ??????????,????ASP?PHP?JAVA?

30
STEP5Analyze Result

• ???????????coding??????
• ?????????????????
• (??.txt, .csv??????????)

31
STEP BY STEP Form (??)
32
STEP BY STEP Form
33
STEP BY STEP Pixels(????)
34
STEP BY STEP Pixels
35
STEP BY STEP Table(??)
36
STEP BY STEP Table
37
STEP BY STEP Table
38
STEP BY STEP Radio Button
39
STEP BY STEP Radio Button
40
STEP BY STEP Radio Button
?? Q1 ? 1 ? 0 ??????
41
STEP BY STEP Radio Button
42
STEP BY STEP Check Box
43
STEP BY STEP Check Box
?? Q2_1 ??? 1 ??????
44
STEP BY STEP Check Box
45
STEP BY STEP Dropdown
46
STEP BY STEP Dropdown
47
STEP BY STEP Dropdown
?? Q3 ???? ??? ?????01 ???????
48
STEP BY STEP Dropdown
49
STEP BY STEP Dropdown
???? ????????,???????,????
50
STEP BY STEP Text Box
51
STEP BY STEP Text Box
?? Q4 ????50 ?????
52
STEP BY STEP Text Box
???? ??????
53
STEP BY STEP ??
54
STEP BY STEP ??
55
STEP BY STEP ??
56
STEP BY STEP ??
57
STEP BY STEP ??
58
STEP BY STEP Submit
59
STEP BY STEP Submit
60
STEP BY STEP Saving
61
STEP BY STEP Saving
???? ???????tab????
62
STEP BY STEP Saving
????URL Thank_you.html
63
STEP BY STEP Saving
???? 1.????????????? 2.????????????????
64
??????

• ???????????????,????????
• ?????????????,????????????????????????,???????????
  ?????????????????
• ?????????????,??????
• ?????Dillman?web-survey????,?????????????

65
Reference

• Bosnjak, M. M. and Tuten, T. L., 2001.
  Classifying Response Behaviors in Web-Based
  Surveys Journal of Comupter-Mediated
  Communication, Vol6, No.3, at http//www.ascusc.or
  g/jcmc/vol6/issue3/boznjak.html.
• Couper, M. P., 2000. Web Surveys a Review of
  Issues and Approaches Public Opinion Quarterly,
  Vol64, No.4, pp.464-481.
• Dillman, D. A., 2000. Mail and Internet Surveys
  The Tailored Design Methods. Second edition. New
  York Wiley.
• Dillman, D. A., 2002. Navigating the Rapids of
  Change Some Observations on Survey Methodology
  in the early 21st century presidential address
  to the American Association for Public Opinion
  Research.
• Dillman, D. A. and Bowker, D. K., 2001. The Web
  Questionnaire Challenge to Survey Methodologists
  at http//survey.sesrc.wsu.edu/dillman/zuma_paper_
  dillman_bowker.pdf.

66
Reference

• Dillman, D. A., Tortora, R. D. and Bowker, D.,
  1998. Principle for Constructing Web Surveys
  Pullman, Washington. SESRC Technical Report
  98-50, at http//survey.sesrc.wsu.edu/dillman/pape
  rs/websurveyppr.pdf.
• Smith, T. W., 2001. Are Representative Internet
  Surveys Possible? proceedings of Statistics
  Canada Symposium.
• Sheehan, K. B., 2002. Online Research
  Methodology Reflections and speculations
  Journal of Interactive Advertising, Vol3, No.1.