Exercise 5. Attitude toward school vouchers and presidential vote
Analysts of voting behavior often attempt to explain voting behavior on the basis of certain policy issues. The argument is that voters choose between candidates based on their issue positions. Voters with more conservative positions on these issues should be more likely to vote for Republican candidates, while those who have more liberal positions should be more likely to vote for Democratic candidates. One such issue in recent elections is whether government school vouchers should be used to fund education. Perhaps that issue influenced how some people voted. To examine this possibility, we can look at a table that relates attitude on school vouchers (V137) to presidential vote. For the reasons suggested in Exercise 1, you should use the recoded version of V002 that you created for that exercise, so that you examine only the major-party vote (i.e., only the Bush and Kerry voters).
After examining Table 5A, you should conclude that those who favored school vouchers had a greater propensity to for Bush than those who opposed vouchers. Does this mean that voters cast their ballots in part on the basis of this issue, or is there something else that might cause this relationship? In social science research, we have to be careful about attributing causality. Often, two variables are associated not because one affects the other but because both are influenced by some third variable, commonly referred to as an extraneous or confounding variable.
One possible extraneous or confounding variable is party identification. The relationship in Table 5A could be due to the fact that both variables are affected by party identification. To examine this possibility, one needs to construct a three-variable table that shows the relationship between attitude on school vouchers, presidential vote, and party identification. To keep the table simple and to ensure that you have a sufficient N for each column, you should recode V137 so that it has just two categories (favor and oppose) and use the recoded version of party identification that you created for exercise one (Democrats, independents, and Republicans).
In this example, the relationship between attitude toward school vouchers and presidential vote is extremely weak once we control for party identification. This tells us that the original relationship between attitude toward vouchers and vote is basically spurious.