"Blocking Reduces, if not Removes, Attrition Bias"

Dartmouth Events

"Blocking Reduces, if not Removes, Attrition Bias"

Kentaro Fukumoto PhD, Political Science Dept., Washington Univ., St Louis, does research on political methodology, legislative studies, electoral studies, and Japanese politics.

Tuesday, February 17, 2015
12:15pm-1:45pm
Silsby 215
Intended Audience(s): Public
Categories: Lectures & Seminars

If a unit is compromised (e.g. missing, non-compliance) in experimental data with blocking, some scholars recommend deleting the other units in the same block, saying this leads to unbiased estimates. Others, however, criticize the blockwise deletion, arguing that it can result in biased estimates if the compromising mechanism is not independent of the potential outcomes. This paper arbitrates this controversy by exact calculation of the simplest case and simulation.

For more information, contact:
Mathematics and Social Sciences Program

Events are free and open to the public unless otherwise noted.