Class Notes (807,235)
Canada (492,664)
Todd Alway (64)

October 17,2013-3N06 Lecture Notes.doc

3 Pages
Unlock Document

McMaster University
Political Science
Todd Alway

3N06 Political Science October 17, 2013 Political Science 3N06 2012 Lecture 6c Surveys - What kind of strategy? Non-probabilistic or probabilistic strategies? - Good or bad surveys - Those that are based on social techniques / VS - Those that lie to you and have a specific agenda. - Particular kinds of wording in surveys that is designed to produce a specific response; - Any time you are considering of evaluating or constructing a survey, you need to think about the sampling strategy; You have to make sure that you have a good sample; Think about the questions that you are asking; - Can use a survey to describe a population; surveys can be used to test hypothesis to see whether or not variables are related to each other; What is a Survey? - A method designed to measure (variously) the characteristics, attitudes, and opinions of a sample of a population - Relies on self-assessment on the part of respondents o IE what do you think about… - Can be administered by mail, telephone, internet, or via an in-person interview o All of which have their own strengths and weaknesses - Before a survey is administered, you must first design a questionnaire - (1) STEP - Designing a Questionnaire - Poorly conceived survey questions are the key source of error in many surveys - In many cases they are a larger source of error than sampling error - “Garbage in, garbage out” A) O PEN -ENDED OR CLOSED -ENDED Q UESTIONS ? C LOSED -ENDED QUESTIONS OFFER RESPONDENTS A CHOICE BETWEEN PRE DETERMINED ANSWERS - There are several different types of closed-ended questions (multiple choice, Likert scale, thermometer scale, etc) - Close ended questions make it easy to compare answers o Useful for quantitative analysis o But forces respondents into a limited number of response categories that may not align with the way that respondents view themselves or the world o Frames the issues according to the researcher’s biases and predispositions o POSITIVIST/ANALYSIS (Closed-ended questions)  Need to have ways of measuring.  Agree/Disagree  Different choices  Thermometer scales; - The researcher can make it clear what is being asked; the degree of clarity will help ensure that you can get the information that you are looking for - It is very easy to aggregate close-ended questions; - Overreliance on close-ended questions can create problems; - There’s a way of framing the issue that can lead a respondent to answer it, o Creating an answer that did not exist, before it was asked; o Might not reflect what people actually think; 1 3N06 Political Science October 17, 2013 O PEN-ENDED QUESTION ALLOW THE RESPONDENT TO ANSWER AS THEY SEE FIT - Answers to questions are not pre-chosen by the researcher - Used primarily (although not exclusively) by qualitative researchers - But, comparing answers between respondents become difficult - And articulate and literate respondents are likely to provide more detail, possibly biasing the survey results - You have to write your answer, certain kinds of people will respond more than others; - Biased SAMPLE; - Survey designer asking a question, but not telling the survey respondents how to answer. B) W ORDING YOUR QUESTIONS - Questionnaires are based on languag
More Less

Related notes for POLSCI 3N06

Log In


Don't have an account?

Join OneClass

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

Sign up

Join to view


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.