Questionnaire Design 2
Often misused words generate misleading thoughts Herbert Spencer
The STOCK / LIVESTOCK Case
The range of error due to
use of imprecise words
may be as high as 20 to 30
percent.
Relevance and Accuracy
What
Layout When (Sequence)
How(Phrasing)
Questionnaire Design 3
The Steps in a Survey Project
Establish the goals of the project
Determine your sample - Whom to interview
Choose interviewing methodology - How to interview
Create your questionnaire
Questionnaire Design 4
The Interviewing Methods
Personal Interviews Telephone Surveys Email Surveys Internet/Intranet (Web Page) Surveys
Choice of survey method will depend on several factors : Speed, Cost, Internet Usage,
Literacy Levels, Sensitive Questions
Questionnaire Design 5
Question Types Researchers use three basic types of questions: multiple
choice, numeric open end and text open end. Examples of
each kind of question follow:
Questionnaire Design 7
Designing the Questionnaire
It’s all about the questions…
Effect of a given word Balance in question wording Don’t know answers – offered or volunteered? Using scales Question order Pre-testing
Questionnaire Design 8
To have a hotline For GOVERNMENT to set up a hotline
The Effect of One Word
Kaiser Family Foundation/Harvard University National Survey of Americans’ Views on Consumer Protections in managed Care, January 1998
How important do you think it isto have a hotline telephone number people can call to get help when they have problems with their health plan?
How important do you think it is for the GOVERNMENT to set up a hotline telephone number people can call to get help when they have problems with their health plan?
Very Important Somewhat Important Not too important Not at all important
Questionnaire Design 9
BALANCE in Question Wording
What’s wrong with these questions?
• Do you support the India taking military action against Pakistan?
• If you heard that Candidate X supported stricter gun control laws, would that make you more likely to vote for her?
• Did you happen to vote in the presidential election in 2000?
Questionnaire Design 10
Balance in Question Wording
Bad questions, improved:
• Do you support or oppose the India taking military action against Pakistan?
• If you heard that Candidate X supported stricter gun control laws, would that make you more likely to vote for her, less likely to vote for her, or wouldn’t it make much difference?
• Did you happen to vote in the presidential election in 2000, or not?
Questionnaire Design 11
Don’t Know Answers – offered or volunteered?
4%
54%
42%
NPR/Kaiser Family Foundation/Kennedy School of Government Education Survey, June 1999 (conducted June 25 – July 19, 1999)
Do you favor or oppose the government offering parents money or "vouchers" to send their children to private or religious schools, or public schools outside their district?
Do you favor or oppose the government offering parents money or "vouchers" to send their children to private or religious schools, or public schools outside their district, or haven’t you heard enough about that to have an opinion?
31%
36%
33%
Favor
Oppose
No opinion
Favor
Oppose
No opinion
Questionnaire Design 12
Using scales – getting to “the most”
Now, I’m going to read you some different health care issues. As I read each one, please tell me how important you think it is for the President and Congress to deal with this issue – very important, somewhat important, not too important, or not important at all.
Source: Kaiser Family Foundation Health Poll Report
53%
64%
74%
81%
81%
Making Medicare more financially sound for future generations
Increasing the number of Americans covered by health insurance
Helping states with the cost of Medicaid
Lowering the cost of medical malpractice insurance for physicians
When forced to choose…
Which of the following issues you say are very important do you think is most important?*
Percent saying “very important” Percent saying “most important”
*Also includes those who named only one issue as “very important”
Helping people age 65 and over pay for prescription medicines
11%
8%
27%
19%
27%
Questionnaire Design 13
How questions can affect one another
• Ask general questions before specific priority questions in order to obtain unbiased responses (e.g. most important problem facing the nation) – FUNNEL TECHNIQUE
• Pay attention to how one question might influence answers to future questions:
In considering whether or not to vote for a political candidate, how important is the candidate’s position on HIV/AIDS in making your choice?
What do you think are the two most important health care issues for the government to address?
Questionnaire Design 14
Testing the Questionnaire
Pre-testing The last step in questionnaire design is to test a questionnaire
with a small number of interviews before conducting your main interviews. Ideally, you should test the survey on the same kinds of people you will include in the main study. This kind of test run can reveal unanticipated problems with question wording, instructions to skip questions, etc. It can help see if the interviewees understand your questions and giving useful answers.
If you change any questions after a pre-test, you should not combine the results from the pre-test with the results of post-test.
Defining an RHS Sample Group (2014)
TOTAL # STUDENTS = 336
Total Grade 9s = 81 (Female = 49, Male = 32)
81 ÷ 336 x 100 = 24.1% of sample group
49 ÷ 81 X 100 = 60.5% 100 - 60.5 = 39.5%
Total Grade 10s = 91 (Female = 36, Male = 55)
Total Grade 11s = 82 (Female = 37, Male = 45)
Total Grade 12s = 82 (Female = 41, Male = 41)Questionnaire Design 15