In STATA clustered standard errors are obtained by adding the option
cluster(variable_name) to your regression, where variable_name specifies the variable that defines the group / cluster in your data. The summary output will return clustered standard errors. Here is the syntax:
regress x y, cluster(variable_name)
Below you will find a tutorial that demonstrates how to calculate clustered standard errors in STATA. The tutorial is based on an simulated data that I generate here and which you can download here.
* start with an empty workspace clear all *import data into your STATA session import excel using "https://economictheoryblog.files.wordpress.com/2016/12/data.xls",first *OLS without clustered standard errors regress id_score class_size *OLS with clustered standard errors regress id_score class_size, cluster(class_id) * Note, the standard errors are much * larger with clustered standard errors
One thought on “Clustered Standard Errors in STATA”