Class Notes (838,379)
Todd Alway (64)
Lecture

# Political Science 3N06 2013 L10.docx

6 Pages
79 Views

School
Department
Political Science
Course
POLSCI 3N06
Professor
Todd Alway
Semester
Fall

Description
Experimental methods Political Science 3N06 2013 Lecture 10: Pre-test-------------independent variable------------Post test  Measure your dependent variable- apply independent variable  problems of inference- there can be some internal validity issues  the environment can be affected by more external factors that may effect the dependent variable  external variables might affect it; maturational changes over the course of the experiment  they can make our internal validity rather low  raises certain questions; if you want to be more confident to how to rule out all the other variables? introduce a control group o separate set of subjects o the control group will not be affected by the independent variable o they have to be exactly the same as the experimental group o need to equalize the two groups o the independent variable accounts for it o the control group helps to knock out other variables o if the groups differ; than external variables will have different affects  Some of the limitations of a one group pretest/post-test design can be countered by using a control group o A group that should resemble the experimental group in every aspect but one – it is not exposed to the independent variable  Scores between the control group and the experimental group can be compared – with the difference being attributed to the independent variable  Using a control group can increase the internal validity of an experiment  Threats to the internal validity of an experiment continued:  9. Selection Bias o Control groups only form a control when they are effectively equivalent to the experimental group o “Selection bias” (in this context) implies that the control and experimental group are not equivalent o If so, then the difference in scores in the post-test (between groups) may be reflecting the difference in subjects, not the effect of the independent variable that we are interested in o the internal validity is at threat if the control group and experimental group are different  Ways to enhance pre-test group equivalence A) Probability sampling o We will discuss probability sampling next lecture o random sampling; take random samples and split them within the two groups o it is difficult to do; hard to get people o there are certain limitations B) Random assignment o Individuals in the sample are assigned to the control or the experimental group on the basis of random chance alone o As long as the groups are of a sufficient size, random assignment should equalize their average characteristics o random group; and divide them randomly in the control and experiment group o any purely random process; using chance and chance alone o it is more likely to equalize the groups o the size of the group has to be significantly large o have at least 30 subjects o works better; when the group is larger o the bigger your sample the less likely the mismatch of data C) Matching o Where groups are small, random assignment may not work to equalize the experimental and control groups o In that case, matching individuals into pairs (on the basis of shared characteristics)  And then splitting the pairs – with one member going into the control and one into the experimental group  May be the more appropriate option o Although even here – which characteristics should be relevant for the matching process? o when you cannot rely on random chance to make the two groups equal o tempt to match the experimental group in pares to separate
More Less

Related notes for POLSCI 3N06
Me

OR

Join OneClass

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

Join to view

OR

By registering, I agree to the Terms and Privacy Policies
Just a few more details

So we can recommend you notes for your school.