Exercise 14 – Designing a Survey

Exercise 14 – Designing a Survey

Writing questions for a survey is kind of an art form, but there several general rules you can follow for well written survey.

The first thing you should do when formulating a survey is to make questions that use plain and simple words. Refrain from using words that have double meanings because they can be misunderstood. Watch out for ‘double-barreled questions” as this kind of question can make a respondent agree on one part and may disagree on the other. For instance, the question is: “Do you plan to take a vacation this year and go on a Caribbean cruise?” The respondent can say yes to taking a vacation but probably not to go on a Caribbean cruise. What will happen? You will be given an answer that is not valid.

Questions should be relevant to the population being studied. In general you wouldn’t ask students at UNCG about their retirements plans, starting Tilapia farms, or the cost of heating oil. You would ask them about courses they take, extra curricular, or future job prospects.

Short items are best. People don’t like long surveys. In fact, they stop taking a survey that is too long. This is known as survey fatigue.

Question Rules
1. Remember your purpose – to test a hypothesis.
2. If in doubt, throw it out
3. Keep your questions simple
4. Avoid vague issues/ concepts
5. If a question can be misinterpreted, it will be
6. Include only one topic per question (avoid “double-barreled” questions)
7. Avoid leading questions
8. Consider alternate ways to ask sensitive questions
9. Make sure the respondent has enough information

In this assignment you will develop your preliminary questions for your survey. You’ve already done most of this work in previous exercises. In addition to your own questions, everyone will also ask for the following demographic information so you won’t need to create questions for these:

  1. Sex
    1. What is your sex?  Male  Female
  2. Age
    1. How old are you? Years
  3. Marital status
    1. Are you: Married/Civil Union, Living together as an unmarried couple,  Divorced, Widowed, Separated, Single/Never been married
  4. Employment status
    1. Are you currently: Employed for wages, Self-employed, Out of work for more than 1 year, Out of work for less than 1 year, A homemaker, A student, Retired, Unable to work
  5. Education
    1. What is the highest degree you have completed? Less than High School, High School Diploma or GED, Some college or technical school, Associate’s Degree, Bachelor’s Degree, Graduate Degree.
  1. What is your race/ethnicity (select all that apply)?

1 Black/ African American                   2 Asian/ Pacific Islander

3 Non-Hispanic White/ Anglo            4 Hispanic/ Latino

5 Near East Asian/ Arab-American   6 Native American/ American Indian

7 Other  ___________________________________

I would like for you to now answer the following:

  1. Restate your hypothesis (I promise, this is the final time. You should incorporate any revisions or edits based on previous feedback)
  2. Tell me again what  you’ve chosen for your dependent variable… give it a variable name and a label just as they do in the GSS
  3. What is your your independent variable? Again, a variable name and a label.
  4. Now state the exact question that will measure your dependent variable. (Include any answer choices)
  5. State the question that will measure your independent variable. (Include any answer choices)
  6. Explain how these two questions will test your hypothesis.
  7. What other things will you need to know?
  8. How will you ask these questions? Be specific, give me a variable name, label, question, and the answer choices. (no more than three)

Okay, we now have the rudiments of a survey questionnaire. In the following activities we will be programming an online survey instrument using Qualtics (uncg.qualtrics.com). Your instructor will have set up an account for you. II want you to visit the Qualtric tutorials at: Create A Survey and begin playing with the features. Go ahead and make a few sample survey questions just to get the hang of it. In the next few exercises we will create a more formal survey to be sent out to your friends and peers.

%d bloggers like this: