a) Using the data available, try to find an interesting, statistically significant relationship suggesting that prior exposure to Trump corresponded to political behaviors in the 2016 presidential election. If you're struggling to find a statistically significant relationship, think about all the different things you can test for. You could use having seen The Apprentice, Home Alone 2, or both as your measure of prior Trump exposure. You can use support for Trump, support for Hillary Clinton, or voter turnout in 2016 as your outcome of interest. You can subset* the data to look specifically at voter subgroups of interest (e.g. women, Blacks, Southerners, rich, young, and so on). b) Once you've found a statistically significant relationship, interpret it substantively and think about what it means. Can you tell a story about how this relationship comes to be in real life? Did you learn something interesting about American electoral behavior? c) The data you just analyzed is real survey data from the 2016 Cooperative Congressional Election Study. We randomly selected one thousand respondents and shared a subset of their responses with you. However, we lied above when we said that respondents were asked whether they watched The Apprentice or Home Alone 2. We made those variables up. (Sorry, we won't lie to you again.) Furthermore, the values for those variables were generated completely at random. Explain why you were nonetheless able to find a relationship between those random variables and political behavior. Would you expect that relationship to continue to hold if we provided data on another thousand respondents and again randomly generated the exposure data?

Below is a description of variables.

id: a unique identification number assigned to each respondent

voted16: 1 if the respondent was verified (by their state) as having voted in the 2016 presidential election, 0 otherwise trump16: 1 if the respondent reported voting for the Republican candidate, Donald Trump, in 2016, 0 otherwise clinton16: 1 if the respondent reported voting for the Democratic candidate, Hillary Clinton, in 2016, 0 otherwise voted12: 1 if the respondent reports that they voted in the 2012 presidential election, 0 otherwise obama12: 1 if the respondent reported voting for the Democratic candidate, Barack Obama, in 2012, 0 otherwise romney12: 1 if the respondent reported voting for the Republican candidate, Mitt Romney, in 2012, 0 otherwise democrat: 1 if the repondent identifies as a Democrat, 0 otherwise republican: 1 if the respondent identifies as a Republican, 0 otherwise liberal: 1 if the respondent identifies as liberal, 0 otherwise conservative: 1 if the respondent identifies as conservative, 0 otherwise age: respondent's age at the time of the November 2016 election female: 1 if the respondent identifies as female, 0 otherwise white: 1 if the respondent identifies as white, 0 otherwise black: 1 if the respondent identifies as black, 0 otherwise hispanic: 1 if the respondent identifies as hispanic, 0 otherwise asian: 1 if the respondent identifies as asian, 0 otherwise income100: 1 if the respondent reports that their family income exceeds $100,000 per year, 0 otherwise church: 1 if the respondent reports attending church at least once per week, 0 otherwise south: 1 if the respondent is from a southern U.S. state, 0 otherwise apprentice: 1 if the respondent reports having watched "The Apprentice", a television show starring Donald Trump, 0 otherwise homealone2: 1 if the repsondent reports having watched "Home Alone 2", a movie featuring a cameo from Donald Trump, 0 otherwise