|
|
|
|
|
|
|
|
|
|
|
Crosstabs |
A Computer Program for Analyzing Political Data
|
The sidebar on page 295 asks you to use the CROSSTABS program to assess the relationship between the strength of citizens' party identifications and when they decided how to vote for president. Go to Houghton Mifflin's CROSSTABS online page to run the program. (Ask your instructor for the appropriate Username and Password to enter.) As in the assignment for Chapter 8, select the VOTERS dataset, which contains data from 1,714 respondents on about 50 variables related to voting in the 1996 presidential election.
The variables you want are listed under the "Political Orientation" and "Voting Behavior" menus. You will be trying to discover whether strong partisans decide how to vote earlier in an election campaign than weak partisans or independents. In causal language, strength of party identification is the cause and time of voting decision is the effect. Expressed in another way, party identification is the independent variable and time of decision is the dependent variable.
The convention for constructing analytical tables in social research is to place dependent variables along the rows of a table, independent variables along the columns, and then compute percentages according to the column totals so that the total percentages in each column sum to 100%.
According to this convention, you should place the time of voting decision in the rows of your crosstab table, party identification in the columns, and choose "% by Cols" in the "Display" menu.
