An open secret and an open sin in economics is that many empirical studies are difficult to replicate, even when journals supposedly require authors to make their data publicly available. Here is how you replicate a Wolfers paper: You go to his web page you download the data and often the code, you run it - and damn it you get exactly what is in the journal. I have done this several times and every time I am shocked that this actually works. (And before being accused of being a hypocrite let me acknowledge that I too have sinned but under Justin's example I am resolved to do better in the future.)
Related;
Do Economics Journal Archives Promote Replicable Research?
Death Penalty Data
The Divorce Myth
No comments:
Post a Comment