Saturday, March 18, 2017

Stata Tip: Never Ever Copy-Paste, Use Outreg2 and Tabstat To Their Fullest

Yes, we all know about outreg2 (I hope), but most of us don't use it to its fullest potential (I think). My graduate student sent me this handy little PowerPoint presentation on outreg2 (thank you, Sam). I had no idea you could use outreg2 to make nice tables of descriptive statistics. 

I have been using the tabstat command to make tables of descriptive statistics. Only recently, I learned that it becomes so much more useful when using the longstub option along with it. Have a look at the tabstat help for more details. 

My favorite outreg2 option? addstat! See the outreg2 help for more details, but I will leave you with one useful thing you can do with it: Imagine you have a regression table showing the results of your analysis conducted on several different samples (sample1, sample2, etc.)  You probably want to show the mean of your dependent variable in the different samples. What to do? 

regress y x if sample=1
sum y if sample=1
outreg2 using TableName, addstat(Dependent Variable, rmean)

Then do the same for the other samples. Voila! The mean of the dependent variable shows up just below the R-squared! 

Saturday, March 11, 2017

Structural vs. Quasi-Experimental Econometrics: Does it Need to be Winner Take All?

My blog focuses on quasi-experimental econometrics because, well, that's what I do and so that's what I can (hopefully) say something useful about. Yes, I'm a huge fan of "Mostly Harmless"-style analyses, but those techniques are not the only ways we can learn about the world using data. 

In a recent blog entry, Noah Smith provides a really nice description of the structural and quasi-experimental styles of analysis. After going through the pluses and minuses of each, he concludes: "So why not do both things? Do quasi-experimental studies. Make structural models. Make sure the structural models agree with the findings of the quasi-experiments. Make policy predictions using both the complex structural models and the simple linearized models, and show how the predictions differ."

I think that's the right advice for the profession, but what if you're a first or second year PhD student? Well, then I think you do have to make a decision. Let's say, for example, you're a graduate student at UConn, and you want to write a dissertation on the impact of immigration policies on natives. Should you work mostly with me or with Hyun Lee? I think the answer depends on which techniques you'd like to learn. Regardless of the path you take, you are absolutely responsible for knowing the limitations of your analyses. 

Thursday, March 2, 2017

How to Write an Economics Paper, Step by Step

By this time in the semester, students in my labor class should be making real progress on their research papers. While trying to think of ways to help them, I came across this fabulously detailed guide, written by Plamen Nikolov, on how to write papers. It's funny that a lot of these things I don't even think about anymore. I guess they just come naturally (well, sometimes) after years of reading papers. But the students in class need to write a paper now, and so these tips will hopefully be useful. 

Some favorites: 
1. Keep sentences short. Monosyllabic words are best. 
2. It is not necessary to cite every single paper in the literature. The main point is to set your paper off against the 4-5 most closely related current papers. 
3. Leave policy implications to the introduction and conclusion. 
4. It is better to acknowledge shortcomings than to make overly broad unsupported statements. 

Colleagues, what are the most annoying/funny mistakes your students make when writing their first paper?