In corporate finance and asset pricing empirical work, researchers are often confronted with panel data. In these data sets, the residuals may be correlated across firms or across time, and OLS standard errors can be biased. Historically, researchers in the two literatures have used different solutions to this problem. This paper examines the different methods used in the literature and explains when the different methods yield the same (and correct) standard errors and when they diverge. The intent is to provide intuition as to why the different approaches sometimes give different answers and give researchers guidance for their use.
Programming advice. I have posted brief instructions on how I programmed the standard errors discussed in this paper. I program in Stata, so most of the code is in Stata. Other researchers have contributed code for estimating standard errors in other language and I have posted the code and links as well. I hope that that this will make it easier for researchers to use these methods. I also posted the simulation program I used (written in Stata) and a short description of the program..
Supplementary tables. Not all of the paper’s results are included in the paper’s tables. Additional tables, including those referred to in the paper (e.g. results available from author) are contained in this file. I have posted these additional tables and results in case readers are interested. Descriptions follow the tables