Democracy and Social Science
II
Professor
Jeff Grynaviski
Winter 2003 (Prepared February
12, 2003)
Homework #4. Due February 20, 2003
Use the data set (Excel
format) and codebook
(rich text format) for an abridged version of the 1996 National Election Study
from the last homework assignment.
Your assignment for
this week is as follows:
Use SPSS to perform the following exercises:
- Follow
last week’s instructions to create a “proxy” variable for vote choice
using the Clinton and Dole feeling thermometer scores.
- Estimate
three bivariate regressions, including at least one regression with a
dummy variable.
- Estimate
a multiple regression including the same three variables included in the
regressions from step 2.
- Summarize
your findings from step 3, explaining the magnitude of the effect of the
independent variables and whether or not they are statistically significant.
Then, compare the results from the simple and the multiple regressions. In
particular, discuss whether any of the regression coefficients in the
multiple regression became significant or insignificant, changed signs,
etc. Explain why you think that occurred
- Estimate
a second multiple regression, this time interacting the dummy variable with
both of the other independent variables.
- Interpret
the results of the model with interaction terms, focusing on whether or
not the regression coefficients are stable for the different categories of
the dummy variable.