Class Notes (838,689)
Canada (511,049)
POL2156 (26)
Lecture 8

Lecture 8 - Survey Construction
Premium

4 Pages
61 Views
Unlock Document

Department
Political Science
Course
POL2156
Professor
Stephanie Mullen
Semester
Fall

Description
Nov. 6, 2013 Survey Construction Objectives  Learn how to write survey questions  Revisit the difference between Nominal, Ordinal, and Interval levels of measurement  Understand how levels of measure are reflected in the answers to survey questions. You should always strive for the highest level of measurement that is useful for the research question at hand. Important Points on Writing Survey Questions  Use neutral language (this avoids bias or leading)  Be clear (what is your income – unclear – family, individual, gross, after-tax income?)  Keep response categories mutually exclusive & exhaustive (no overlap in categories and have all choices available as a category – “other” & “no response”)  Select the highest reliable level of measurement (not always possible – income) st  Pay close attention to question order (what comes 1 will contaminate what comes after & leave intrusive questions to the end of the survey)  Minimize defensive reaction. (In some cases it is important to assure respondents that a socially incorrect response is alright) Open-Ended vs Closed-Ended Questions  Open-Ended Advantages: o Allows for a greater range of answers o The respondent is not limited to or biased by preset response categories and may provide answer that lead the researcher into new theoretical waters  Open-Ended Disadvantages: o There are many possible answer to any given questions, making data entry difficult o Respondents will spend more time on open questions, making the questions less efficient o Comparison between individuals can be complicated  Close-Ended Advantages: o Respondents can answer questions quickly o It is easy to compare the responses of different individuals o Data entry is less complex  Close-Ended Disadvantages: o Asks respondents to give a simple response to a very complex issue, and by providing categories for the respondent, may encourage the statement of opinion or knowledge where none actually exists Intensity Measures One-Directional Intensity Scale  Many concepts/variable cannot be simply characterized in a yes/no dichotomy, therefore an intensity measure is useful in capturing how strongly respondents feel about certain issues at the point in time that the survey was conducted  The response categories is simply a number scale usually from 1-7  No labels are attached to the 1 or 7, such as Strongly Disagree and Strongly Agree – although we can imply that the lower number means that the issue is not important o not as important as other issues to them. Matrix Format  Instead of asking a direct question for each IV, Control, and DV you are interested in, you can develop statements which you want respondents to give their feelings on and
More Less

Related notes for POL2156

Log In


OR

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


OR

By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.


Submit