Class Notes (838,541)
Canada (510,933)
Todd Alway (64)

October 3, 2013 - 3N06 Lecture Notes.doc

5 Pages
Unlock Document

Political Science
Todd Alway

October 3, 2013 Political Science 3N06 POLITICAL S CIENCE 3N06 2013 L ECTURE 5A: E XPERIMENTAL METHODS O CTOBER 3, 2013 - If you want to construct a Political Science (Particularly positivist in orientation) o How do you structure your observations  So that it is reasonable to conclude that X causes Y T HERE ARE DIFFERENT TYPES OF RESEARCH DESIGN o Logical architecture; structures the way you examine the data; (positivist research) – persuasive answers - But (at least for positivist research) they all attempt to demonstrate persuasive answers to three issues • Temporality o You have to demonstrate that the cost CAME before the EFFECT; o Independent variable has to be established that it came BEFORE the dependent • Correlation o To say that there is a causal relationship between two variables; have to demonstrate that they move together; SOME MOVEMENT. • Spuriousness o Is there any other variable that can account for the CORRELATION? (E.G ice cream & Drowning) o That there are no rival explanations that might account. o Ways of structuring experimental designs so that we can rule out other explanations; - The experimental method represents the archetypal approach for positivist social science - Held up as the gold standard for establishing causal relationships between variables 1 October 3, 2013 Political Science 3N06 PRETEST  INDEPENDENT VARIABLE  POST TEST EXPERIMENT Prejudice Amongst Canadians Q. Lack of knowledge of the contribution that minorities make to society? Independent – Knowledge Dependent – Attitudes towards Minorities; Does increasing knowledge of what minorities have done for society decrease prejudice? Pre-Test Independent Variable Dependent Variable Prejudice against Show them some films Test out the change Minorities (Dependent of what minorities have (Change in Dependent Variable) contributed to Canadian Variable) society. Problem – Ruling out alternative causes; other variables that are circulating which could impact the dependent variable, other than the independent variable that was introduced. What are experiments? - There are many types, but consider the Pretest/post-test laboratory experiment - A hypothesis is stipulated – that there is a relationship between two variables - An experimental group is assembled - The dependent variable is measured - The independent variable in introduced - The dependent variable is measured again - Any change in the dependent variable (assuming internal validity) is attributed to the independent variable - Are they an effective way of testing Political Science research hypotheses? - Two issues: Internal Validity and External Validity INTERNAL V ALIDITY - How certain can we be that the independent variable is the only variable impacting the dependent variable in our experiment 2 October 3, 2013 Political Science 3N06 - “There are a number of threats to internal validity that you have to keep in mind when evaluating what the experiment actually demonstrates” - We have to rule out the other plausible variables that might have created a change; - Threats to internal validity that can affect experimental designs; - Want to be able to say that OUR VARIABLE caused changes in the DEPENDENT variable; not anything else. 1. History - Historical ev
More Less

Related notes for POLSCI 3N06

Log In


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.