This note adds to the recent research project on treatment choice under ambiguity. I generalize the Manski (Journal of Econometrics, in press) analysis of minimax regret treatment choice by considering a more general setting and, more importantly, by solving for the treatment rule given finitely many (as opposed to two) treatments. The most interesting finding is that with three or more undominated treatments, the minimax regret treatment rule may assign the same treatment to all subjects; thus, the most salient feature of the two-treatment case does not generalize.I thank Chuck Manski, the co-editor, and especially an anonymous referee for helpful comments. Financial support through the Robert Eisner Memorial Fellowship, Department of Economics, Northwestern University, in addition to a Dissertation Year Fellowship, The Graduate School, Northwestern University, is gratefully acknowledged.
[1]
C. Manski.
Partial Identification of Probability Distributions
,
2003
.
[2]
C. Manski.
Statistical treatment rules for heterogeneous populations
,
2003
.
[3]
Larry Wasserman,et al.
Computing bounds on expectations
,
1992
.
[4]
Charles F. Manski,et al.
Minimax-regret treatment choice with missing outcome data
,
2007
.
[5]
P. Walley.
Statistical Reasoning with Imprecise Probabilities
,
1990
.
[6]
Anne Lohrli.
Chapman and Hall
,
1985
.
[7]
Robust Monopoly Pricing: The Case of Regret
,
2005
.
[8]
Karl H. Schlag,et al.
How to Minimize Maximum Regret in Repeated Decision-Making
,
2004
.
[9]
William A. Brock,et al.
Profiling Problems with Partially Identified Structure
,
2006
.