Research and Analysis Examples Using R

Gambler's Fallacy

We've all seen the player who has rolled several low scores on to hit rolls in a D&D session who says "the odds are getting better of me rolling a 20" or the player who has rolled six sevens in a row playing Craps who picks up the dice and says "the odds of me rolling seven again are 1/(some huge number)." In both cases, the individual is wrong and is committing the "Gambler’s Fallacy.” While it is true that given a sufficiently large sample (and we are talking thousands of rolls) that the die rolls of a player will tend toward the mean, it is important to remember that prior die rolls have no influence on future die rolls. Dice don’t have memories and actively change their future behavior based on past performance.

We can test this phenomenon via simulation, then reproduce it, and finally we can replicate it with a slightly different simulation.

Fundraising and the McCarthy Vote

It took Kevin McCarthy 15 votes to finally win his bid to become Speaker of the House. There was a core group of people who opposed him that was composed of people from the Freedom Caucus of the Republican Party. What might be some of the reasons they opposed him? Was it ideology? Narcissism? Not receiving acknowledgement for hard work on behalf of the party? Not receiving party support?

The current leadership is Kevin McCarthy (Speaker), Steve Scalise (Majority Leader), Tom Emmer (Majority Whip), Elise Stefanik (Conference Chair), Gary Palmer (Policy Committee Chair).

Boebert was on the Budget and Natural Resources Committees. She is now on the Oversight and Accountability and Natural Resources Committees.

GOP Newsletters and Newsmax

Dr. Lindsay McCormack at the Stevens Institute of Technology hosts one of the most useful resources I've found on the internet regarding communication between Legislators and their Constituents with her Newsletter Database. In it, you can find all the newsletters Members of Congress send their constituents which lets you examine messaging, issues of importance, political polarization. It's truly a gold mine. Recently, she posted a histogram showing the frequency over time of legislators mentioning Newsmax in their newsletters. Her post was around the time that AT&T/Direct TV opted to drop the service, but the data was not so it was able to show that Republicans were the ones promoting the website. This has implications for those who study media and polarization and that got me wondering whether those with higher DW-Nominate scores were more likely to tweet about Newsmax. 

My hypothesis? The number of posts a Member of Congress sends out to constituents mentioning Newsmax will tend to be higher as the DW-Nominate score increases.

My plot of this demonstrated that the trend was "in general" true, but that there were some interesting outliers which made it more like a distribution than a linear relationship. I might do a new plot based on 2nd Dimension scores because of how many of the McCarthy defectors were clustered on that dimension, but I have not done that yet.

Here are the files associated with this experiment.

Poole Polarization Materials

Multidimensional Scaling Slides