Exercise 3: Attitude toward social security privatization and presidential vote
Studies of voting behavior often attempt to explain voting behavior on the basis of certain policy issues. The hypothesis is that voters choose between candidates based on their issue positions. One public policy issue that has received attention in recent years is whether the Social Security program should be partially privatized. This was an issue that was discussed during the Bush administration, and perhaps that issue influenced how some people voted in 2008. To examine this possibility, we can look at a table that relates attitude on Social Security privatization (V086) 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 Obama and McCain voters).
After examining Table 3A, you should conclude that those who favored Social Security privatization had a greater propensity to for McCain than those who opposed it. Does this prove 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 a confounding variable.
One possible confounding variable is party identification. The relationship in Table 3A could be due to both variables being affected by party identification. To examine this possibility, you need to construct a three-variable table that shows the relationship between attitude on Social Security privatization, presidential vote, and party identification. To keep the table simple and to have a sufficient N for each column, you should recode V0861 so that it has just three categories (favor, neutral, 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 Social Security privatization and presidential vote is extremely weak once we control for party identification. This tells us that the original relationship between the attitude and the vote is basically spurious.
1V086 has five response categories, running from strongly favor to strongly oppose. While these five categories are fine for the two-variable table that you generated to start this exercise, keeping all five categories of V086 will create some problems when you generate a three-variable table in which party identification is a control variable. The result will be a table in which there are too few respondents in many table columns, making the percentages in those columns unreliable estimates of population patterns. Also, the table will be somewhat complex and perhaps a little too hard to interpret. Recoding V086 so that it has only three categories—favor, neutral, and oppose—will solve these problems. Thus, you should recode V086 so that those who strongly favor and those who simply favor privatization are combined into one category. The same should be done with those who oppose and those who strongly oppose the policy.