oes Religious Attendance Matter For Partisanship? People routinely say that “social issues”
statistics
Description
Problem 1 Does Religious Attendance Matter For Partisanship? People routinely say that “social issues” matter more in US politics than “economics.” For the most part, the social issues in question are deeply entangled with religiosity. So, we will use statistics to ask whether religion or family income does a better job of predicting a person’s party identification. To do this, we will rely on the General Social Survey, which you can analyze at: http://sda.berkeley.edu/sdaweb/analysis/?dataset=gss14
First, let us test whether religiosity affects partisanship. We will use the variable ATTRELIG, which
you can find under the menu on the left, under RESPONDENT BACKGROUND VARIABLES and then
submenu Religious Attendance and Identity. Click View at the top after selecting ATTRELIG to see the
question wording. For partisanship, we will use PARTYID. Type that variable’s name into the box at the
top of the left-hand column and press view to see what it means, as well.
Let us set up a 95% confidence interval for the difference in means on partisanship between the group
that attended a religious service in the last week and the group that did not. Click Means on the right
hand side of the SDA page. Type PARTYID as the dependent and ATTRELIG as the independent variables
(labeled in SDA as “Row”). Construct a difference in means confidence interval using the reported means,
standard errors, and numbers of cases. (In creating this confidence interval, note that the Means command
has already provided you with the mean for each group, the standard error for each group, and the number
of cases for each group. Your job is just to combine those into a confidence interval of some sort.) Show
your work, report your results, and explain what they mean.
