Create a new version of the variable and recode it in a way that you like.

Task: It is your third day of your internship at the campaign of a candidate for Congress. Your supervisor wants a new analysis of public opinion on government spending. She asks you to look at the 2016 GSS again, but this time she wants you to focus on one of the government spending variables. She wants you to use contingency tables and/or bar charts to examine how three independent variables (personal characteristics) affect attitudes toward whether we should be spending more or less on that item.

·         Choose a government spending item (any of the variables that start with nat).

·         Create a new version of the variable and recode it in a way that you like.

o   Turn any “Don’t Know” or “No Answer” responses into missing values (remember that Stata uses a period “.” to represent a missing value).

o   If you recode this variable into a dummy variable to create a bar chart, code it 0 for No and 100 for Yes. (You can make either “too much” or “too little” your Yes.)

·         Choose three independent variables that you think might affect attitudes toward spending on this item.  Obvious choices include sex, race, age, education (educ), religion (use relig), religious attendance (attend), party identification (partyid), and liberalism-conservatism (polviews). Remember to make sure that you understand how each variable is coded; you may need to recode it.

·         First, describe public opinion for the data set as a whole. 

·         Second, create at least two contingency tables. Be sure you know whether your independent variable is the column variable or the row variable.

o   If your independent variable is the column variable, have Stata print only the column percentages. (Use the nofreq option.) When writing up your description of the table, compare column percentages in the top or bottom row.

If your independent variable is the row variable, have Stata print only the row percentages. (Use the nofreq option.) When writing up your

Sample Answer

For this task, I will choose the government spending item “NATSPEND”, which represents attitudes on spending on national defense. I will recode this variable to create a dummy variable, where 0 represents the belief that we are spending too much on national defense and 100 represents the belief that we are spending too little on national defense.

For the independent variables, I will choose sex, race, and age. I will make sure to properly recode these variables so that they are in the appropriate format for analysis.

To describe public opinion for the data set as a whole, I will use the “mean” command to calculate the average response for the NATSPEND variable. This will give me a sense of whether the overall public opinion is that we are spending too much or too little on national defense.

Next, I will create contingency tables to examine how the independent variables of sex, race, and age are related to attitudes towards national defense spending. I will set NATSPEND as the row variable and sex, race, and age as the column variables, and have Stata print only the column percentages. This will allow me to compare the column percentages Order a customized and more comprehensive answer here

Finally, I will create bar charts to visualize the results of the contingency tables. I will set NATSPEND as the dependent variable and sex, race, and age as the independent variables, and use the “graph bar” command Order a customized and more comprehensive answer here