Block what you can, except when you shouldn't

10/26/2020
by   Nicole E. Pashley, et al.
0

Several branches of the potential outcome causal inference literature have discussed the merits of blocking versus complete randomization. Some have concluded it can never hurt the precision of estimates, and some have concluded it can hurt. In this paper, we reconcile these apparently conflicting views, give a more thorough discussion of what guarantees no harm, and discuss how other aspects of a blocked design can cost, all in terms of precision. We discuss how the different findings are due to different sampling models and assumptions of how the blocks were formed. We also connect these ideas to common misconceptions, for instance showing that analyzing a blocked experiment as if it were completely randomized, a seemingly conservative method, can actually backfire in some cases. Overall, we find that blocking can have a price, but that this price is usually small and the potential for gain can be large. It is hard to go too far wrong with blocking.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/03/2021

A Causality-based Graphical Test to obtain an Optimal Blocking Set for Randomized Experiments

Randomized experiments are often performed to study the causal effects o...
research
06/26/2019

Rerandomization and Regression Adjustment

Randomization is a basis for the statistical inference of treatment effe...
research
06/21/2023

Optimal allocation of sample size for randomization-based inference from 2^K factorial designs

Optimizing the allocation of units into treatment groups can help resear...
research
11/01/2019

The Potential Gains of Macrodiversity in mmWave Cellular Networks with Correlated Blocking

At millimeter wave (mmWave) frequencies, signals are prone to blocking b...
research
03/31/2021

What do Indian Researchers download from Sci-Hub

Recently three foreign academic publishers filed a case of copyright inf...
research
09/01/2021

Small Strong Blocking Sets by Concatenation

Strong blocking sets and their counterparts, minimal codes, attracted lo...

Please sign up or login with your details

Forgot password? Click here to reset