Question: Use the “States” dataset and SPSS for the following analysis. (30 points)

The “States” dataset includes election, demographic, and political data for all 50 states. Labels for the variables are included in the dataset, but a description of the variables is also in the Appendix (Table A-2) of Pollock (3^rd Edition).

a. Provide an appropriate measure of central tendency, an appropriate measure of dispersion, and a histogram for the variable bush04, which is the percentage of a state’s votes that were won by George Bush in the 2004 U.S. Presidential election.

b. Create a model that attempts to explain the Bush vote (bush04) among the U.S. states in the 2004 Presidential election. Your model must include at least three variables. Your grade will be based on your analysis, use of appropriate variables, and the clarity and organization of your writing.

On no more than two pages (NOT single-spaced) provide an appropriate summary of your analysis. This summary should include a reason for why you chose each variable and the relationship you expected between each variable and bush04. You should include

important information about your overall model, as well as individual variables. Discuss whether the model’s findings were what you expected.

c. One assumption of linear regression is a linear relationship between the independent variables and the dependent variable. State the other assumptions and whether or not they are met.

d. For part “d”, provide all of the SPSS syntax and output.