Survey Design How to design a survey to

Survey Design How to design a survey to get reliable results

Reliable Research • To increase reliability, sociologists work to avoid common errors in the design of research questions • Most common mistakes are using questions that are: o Double-barreled o Loaded o Threatening o Written with Built-in Assumptions o Unclear o Written with Technical Jargon

Double-Barreled Questions • Questions that make the mistake of asking two or more questions in one • Example: You ask your friend, “Is Mrs. Silverman’s class easy and interesting? ” o What is the problem with this question?

Double-Barreled Questions • Questions that make the mistake of asking two or more questions in one • Example: You ask your friend, “Is Mrs. Silverman’s class easy and interesting? ” o What is the problem with this question? o The response “yes” is unclear o Yes, it is easy? or yes, it is interesting? or yes to both?

Leading/Loaded Questions • Questions that subtly push a respondent to give a certain response • May be worded to get either a positive or negative response • Examples: (underline the loaded words) o “Should the president of the college fix the dangerous and potholed streets around campus? ” o “Should the president of the college spend even more money on repairing streets when the students are in need of those funds for classes? ”

Leading/Loaded Questions • Clip from Yes, Minister: What does this clip reveal about getting the survey results you want?

Threatening Questions • Questions that may be worded in a way that is threatening towards the respondent • Example: (underline threatening words) o “Have you ever compromised your academic integrity and violated the Milton Honor Code by cheating on an exam? ” • How would you rewrite the above question to be less threatening?

Threatening Questions • Questions that may be worded in a way that is threatening towards the respondent • Example: (underline threatening words) o “Have you ever compromised your academic integrity and violated the Milton Honor Code by cheating on an exam? ” • How would you rewrite the above question to be less threatening? o “Have you ever cheated on an exam? ”

Questions with Built-In Assumptions • Questions that assume something about the respondent or topic without knowing for sure • Examples: (identify the built-in assumption) o “How has redistricting changed Milton? ” o “Is the textbook we use for our class well-written? ”

Unclear Questions • Unclear questions assume that the respondent understands how you define a term • Examples: (underline the unclear word/wording) o “Do you study with friends often? ” o “Is Mrs. Silverman a good teacher? ” • What can you do to avoid unclear questions?

Questions With Technical Jargon • Technical jargon should also be avoided in research questions because the respondent may not be as familiar with an industry as the researcher • Examples: (underline the jargon) o o o “Is the pedagogy of this instructor effective? ” “Does Milton have PLCs? ” “Does Milton have a stronger backfield than Alpharetta? ” • Did you notice any other problems with the questions above?