Syndicate content

cluster RCTs

When should you cluster standard errors? New wisdom from the econometrics oracle

David McKenzie's picture

In ancient Greek times, important decisions were never made without consulting the high priestess at the Oracle of Delphi.  She would deliver wisdom from the gods, although this advice was sometimes vague or confusing, and was often misinterpreted by mortals. Today I bring word that the high priestess and priests (Athey, Abadie, Imbens and Wooldridge) have delivered new wisdom from the god of econometrics on the important decision of when should you cluster standard errors. This is definitely one of life’s most important questions, as any keen player of seminar bingo can surely attest. In case their paper is all greek to you (half of it literally is), I will attempt to summarize their recommendations, so that your standard errors may be heavenly.

Sampling weights matter for RCT design?

Berk Ozler's picture

One of the most important things while designing an intervention is to try to ensure that your study will have enough statistical power to test the hypotheses you're interested in. Picking a large enough sample is one of a variety of things to increase power. Another is block stratified randomization, of which paired randomization is the extreme.