Central Limit Theorem in action

I had my #lafecon213 students run Monte Carlo simulations in class yesterday using a program we wrote in Stata. After we’d done the general one, I told them to change something about it and see how it affected the sampling distribution of the coefficient estimates. One student decided to run 100,000 repetitions of the simulation, not realizing what a time suck it would be. It took most of the rest of my lecture (surprisingly long, now that I think about it; perhaps I should complain to IT? I just tried it, pretty sure he did 1,000,000 repetitions), but when he finally had a histogram, I put it up on the big screens in my awesome smart classroom, broke into a huge grin and exclaimed, “isn’t it pretty?!”

If they didn’t think I was crazy before, they definitely do now. It took at least three minutes for them to stop laughing at me.

You have to admit it’s really pretty, no?

Monte Carlo reps output

Advertisements

Another seminar, another live-tweeting session

We’ve been having lots of seminars here at Lafayette this month. It’s been super fun to read my students’ tweets as they go along, so here again, I’ve storified last week’s seminar for you all, this time by Michael Clark of Trinity College. This time, we were lucky to have my colleague Chris Ruebeck tweeting alongside the students. I think he enjoyed it, too.

Note-taking, live-tweeting, and first week of class update

My twitter assignment for my econometrics classes has garnered a bit of attention over the last few weeks. As we had our first assignment, reading Charles Wheelan‘s Naked Statistics, along with the regular assignments, my students interacted with each other,

with Lafayette College communications and library accounts,

with Alison Byerly, president of Lafayette College,

with some of my colleagues, and even with Stata. My favorite post of the week came when a student tweeted at me to ask whether a follow from Stata earned him extra points.

I’ll let you guess what the answer was.

Lafayette College has a social media working group, a relatively informal gathering of social media practitioners on campus, who asked me and another professor to come by and give a short presentation on how we were using twitter in the classroom. Last semester, Chris Phillips had students live-tweet his seminar on Moby Dick, while my assignments are mostly out of class, at least at this point.

A few days later, a colleague tweeted an article on a new psychology paper showing that students process information better, and get more nuance, when they take longhand notes as opposed to typing verbatim a professor’s lecture. While this justifies my reluctance to give out class notes, it also got me thinking about whether live-tweeting would be more like longhand notes or like typing notes. One of the participants in our twitter in the classroom discussion asked Chris whether the students who live-tweeted did better or worse than the others. He didn’t feel he could really make a statement either way (he already knew one of the students, not to mention the statistical power issue with a small sample size), but it’s a question worth asking. Assuming we take the study at face value, does the power of note-taking come with the physical process of writing out letters? Or is there something particularly damaging about typing verbatim that limits processing? And which process does live-tweeting, where you are typing, but have to process and condense information fairly quickly, mimic more closely?

h/t @betsylevyp

Prof. Fletcher’s Guide to Tweeting in the Classroom

The past few months have been full of new research projects and new ideas for me. I’m exploring sexualized violence among Colombian ex-combatants, obesity during pregnancy, and female labor force participation in the American South. I just got a small grant from Lafayette’s Digital Humanities Mellon Foundation Grant to study the last of these and I couldn’t be more excited.

Teaching-wise, I’m also ramping up the innovation. In particular, I’ve been thinking a lot about how to have my students read and interact more next semester. I’ve settled on twitter. In the past, I’ve asked them to blog, and it’s been fantastic, though I think it works better with smaller classes. This Spring, I’m trying out tweeting to see if I can’t engender some networking skills while focusing on brevity.

Here is Professor Fletcher’s Guide to Twitter for my students, specific to this semester. It includes some assignments and some general guidelines, assuming they either know the basics or can figure them out fairly quickly. Comments, thoughts, ideas, are much appreciated.

Happy New Year!

Preliminary Regression Presentations

I am more than halfway through my seventh time teaching something called Econometrics or Quantitative Research Methods or Applied Statistics or whatever you’d like to call it. I’ve taught it now at a few different levels, each requiring more or less work, more or less writing, more or less math, more or less me being totally overwhelmed by grading.

This semester, I am not having students blog. Instead, we’re taking more in class time to discuss readings. The other big change I made is that instead of having students turn in their preliminary regression results last week, I had them make five-minute presentations to the class. It was an experiment and it was one of those experiments that made me feel like a teaching God. I can’t recommend it enough (based on my sample of 18 students, but only 1 cluster (class)). Presentations are great because you can grade them as you go, but additionally, they allowed each student in the course to learn from the others’ missteps. I had students fill out peer evaluations (anonymously) so they get additional feedback than just mine and they have to really understand what they’re doing in order to present it to the class.

I think they enjoyed it, too!

Honor Codes, Cheating and Social Norms

I spent lunchtime yesterday at a gathering of students and faculty put on by Lafayette Student Government. One of the suggested topics for conversation was the possible implementation of an Honor Code. It’s apparently an extremely contentious issue and while each member of the group I encountered had different perceptions of honor codes, one of the biggest takeaways from the conversation was that social norms, or the “culture of cheating” plays a big role. How individuals perceive the actions of their peers wields influence in how much cheating actually occurs.

Today, one of the New Yorker blogs highlighted cheating and this paragraph stood out to me:

Social norms, too, play an important role in the decision to cheat: if cheating seems more widely accepted, people are more likely to be dishonest; the reverse is true as well. In one set of experiments, psychologists at the University of North Carolina at Chapel Hill and Duke University found that if someone had obviously cheated, by finishing a problem-solving task much more quickly than would be possible had he completed it honestly, other people in the room became more likely to cheat as well—but only if they perceived the cheater to be like them. If the cheater seemed different—in this case, if he wore a rival school’s T-shirt—students became far less likely to cheat. In the case of the Long Island students, it seems that, while relatively few students actually cheated, most were aware that it was a regular occurrence. It was a student, in fact, who first brought the alleged cheating to the attention of a Great Neck counsellor. Cheating was a known, somewhat accepted norm; little wonder that it swept through five separate schools.

We didn’t really come to any conclusions. I’ve been at schools where the Honor Code meant you had to sign something saying you didn’t cheat on each test or paper and at schools where the professor wasn’t allowed to be in the room. One colleague noted the Honor Code at another college was inhibiting to learning and trust because students would turn each other in for any kind of collaboration, even that which was sanctioned by the professor.

Ultimately, though, it was a good opportunity to encourage student government to take initiative. Any change in the culture or implementation of an Honor Code has to come from them to be credible.

Primes and Probability

At the suggestion of a colleague, I recently started reading Charles Wheelan’s Naked Statistics: Stripping the Dread from the Data. So far, it’s a fun, demystifying sort of book, the kind I hope my students will enjoy (watch out Lafayette Economics, I’m coming, and I will make you read). It rests on the twin ideas that statistics can be fun and statistics are incredibly useful to explain, to tell stories.

The book was high in my mind this morning when I read this deliciously accessible Slate piece by Wisconsin professor Jordan Ellenberg about an advance in prime numbers by a University of New Hampshire mathematician. Economists like to make lots of bad jokes about how they are failed physicists, who are in turn failed mathematicians, so while it interests me, I wasn’t expecting to really understand the discovery when someone riffed on twitter about primes.

What’s so wonderful about this really intense mathematical discovery, at least according to the mathematician author of this piece, is that it’s really about statistics, which I can totally get my head around. The theory goes that primes come in infinitely many ‘twin pairs,’ like 3 and 5 or 17 and 19, and the intuition lies in that we can think about primes as random numbers.

And a lot of twin primes is exactly what number theorists expect to find no matter how big the numbers get—not because we think there’s a deep, miraculous structure hidden in the primes, but precisely because we don’t think so. We expect the primes to be tossed around at random like dirt.

Zhang didn’t quite prove the twin pairs theorem, but he made an important step towards proving it, it seems, and understanding probability and statistics is key to getting there.