Statistical Treatment Rules for Heterogeneous Populations

Statistical Treatment Rules for Heterogeneous Populations

An important objective of empirical research on treatment response is to provide decision makers with information useful in choosing treatments. This paper studies minimax-regret treatment choice using the sample data generated by a classical randomized experiment. Consider a utilitarian social plan...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:Econometrica. - Wiley. - 72(2004), 4, Seite 1221-1246
1. Verfasser: Manski, Charles F. (VerfasserIn)
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2004
Zugriff auf das übergeordnete Werk:Econometrica
Schlagworte:Finite sample theory Large-deviations theory Minimax regret Randomized experiments Risk Social planner Statistical decision theory Treatment response Mathematics Information science mehr... Behavioral sciences Political science
LEADER 01000caa a22002652 4500
001 JST028784936
003 DE-627
005 20240620164915.0
007 cr uuu---uuuuu
008 150324s2004 xx |||||o 00| ||eng c
035 |a (DE-627)JST028784936 
035 |a (JST)3598783 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Manski, Charles F.  |e verfasserin  |4 aut 
245 1 0 |a Statistical Treatment Rules for Heterogeneous Populations 
264 1 |c 2004 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
520 |a An important objective of empirical research on treatment response is to provide decision makers with information useful in choosing treatments. This paper studies minimax-regret treatment choice using the sample data generated by a classical randomized experiment. Consider a utilitarian social planner who must choose among the feasible statistical treatment rules, these being functions that map the sample data and observed covariates of population members into a treatment allocation. If the planner knew the population distribution of treatment response, the optimal treatment rule would maximize mean welfare conditional on all observed covariates. The appropriate use of covariate information is a more subtle matter when only sample data on treatment response are available. I consider the class of conditional empirical success rules; that is, rules assigning persons to treatments that yield the best experimental outcomes conditional on alternative subsets of the observed covariates. I derive a closed-form bound on the maximum regret of any such rule. Comparison of the bounds for rules that condition on smaller and larger subsets of the covariates yields sufficient sample sizes for productive use of covariate information. When the available sample size exceeds the sufficiency boundary, a planner can be certain that conditioning treatment choice on more covariates is preferable (in terms of minimax regret) to conditioning on fewer covariates. 
540 |a Copyright 2004 Econometric Society 
650 4 |a Finite sample theory 
650 4 |a Large-deviations theory 
650 4 |a Minimax regret 
650 4 |a Randomized experiments 
650 4 |a Risk 
650 4 |a Social planner 
650 4 |a Statistical decision theory 
650 4 |a Treatment response 
650 4 |a Mathematics  |x Applied mathematics  |x Statistics  |x Applied statistics  |x Descriptive statistics  |x Statistical sampling  |x Sampling methods  |x Random sampling 
650 4 |a Mathematics  |x Applied mathematics  |x Statistics  |x Applied statistics  |x Descriptive statistics  |x Measures of variability  |x Sample size 
650 4 |a Information science  |x Data products  |x Datasets  |x Test data 
650 4 |a Behavioral sciences  |x Psychology  |x Cognitive psychology  |x Decision theory  |x Statistical decision theory 
650 4 |a Political science  |x Political philosophy  |x Social contract  |x State of nature 
650 4 |a Mathematics  |x Applied mathematics  |x Statistics  |x Applied statistics  |x Descriptive statistics  |x Central tendencies  |x Population mean 
650 4 |a Mathematics  |x Pure mathematics  |x Probability theory  |x Random variables 
650 4 |a Mathematics  |x Applied mathematics  |x Game theory  |x Minimax 
650 4 |a Mathematics  |x Pure mathematics  |x Probability theory  |x Probability interpretations  |x Frequentism 
650 4 |a Mathematics  |x Applied mathematics  |x Statistics  |x Applied statistics  |x Descriptive statistics  |x Statistical sampling  |x Sampling methods  |x Data sampling 
655 4 |a research-article 
773 0 8 |i Enthalten in  |t Econometrica  |d Wiley  |g 72(2004), 4, Seite 1221-1246  |w (DE-627)270425721  |w (DE-600)1477253-X  |x 14680262  |7 nnns 
773 1 8 |g volume:72  |g year:2004  |g number:4  |g pages:1221-1246 
856 4 0 |u https://www.jstor.org/stable/3598783  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_JST 
912 |a GBV_ILN_11 
912 |a GBV_ILN_20 
912 |a GBV_ILN_22 
912 |a GBV_ILN_23 
912 |a GBV_ILN_24 
912 |a GBV_ILN_31 
912 |a GBV_ILN_32 
912 |a GBV_ILN_39 
912 |a GBV_ILN_40 
912 |a GBV_ILN_60 
912 |a GBV_ILN_62 
912 |a GBV_ILN_63 
912 |a GBV_ILN_65 
912 |a GBV_ILN_69 
912 |a GBV_ILN_70 
912 |a GBV_ILN_73 
912 |a GBV_ILN_74 
912 |a GBV_ILN_90 
912 |a GBV_ILN_95 
912 |a GBV_ILN_100 
912 |a GBV_ILN_105 
912 |a GBV_ILN_110 
912 |a GBV_ILN_120 
912 |a GBV_ILN_138 
912 |a GBV_ILN_150 
912 |a GBV_ILN_151 
912 |a GBV_ILN_161 
912 |a GBV_ILN_170 
912 |a GBV_ILN_171 
912 |a GBV_ILN_184 
912 |a GBV_ILN_187 
912 |a GBV_ILN_213 
912 |a GBV_ILN_224 
912 |a GBV_ILN_230 
912 |a GBV_ILN_266 
912 |a GBV_ILN_285 
912 |a GBV_ILN_293 
912 |a GBV_ILN_370 
912 |a GBV_ILN_374 
912 |a GBV_ILN_602 
912 |a GBV_ILN_636 
912 |a GBV_ILN_702 
912 |a GBV_ILN_2001 
912 |a GBV_ILN_2003 
912 |a GBV_ILN_2004 
912 |a GBV_ILN_2005 
912 |a GBV_ILN_2006 
912 |a GBV_ILN_2007 
912 |a GBV_ILN_2008 
912 |a GBV_ILN_2009 
912 |a GBV_ILN_2010 
912 |a GBV_ILN_2011 
912 |a GBV_ILN_2014 
912 |a GBV_ILN_2015 
912 |a GBV_ILN_2018 
912 |a GBV_ILN_2020 
912 |a GBV_ILN_2021 
912 |a GBV_ILN_2025 
912 |a GBV_ILN_2026 
912 |a GBV_ILN_2027 
912 |a GBV_ILN_2031 
912 |a GBV_ILN_2034 
912 |a GBV_ILN_2037 
912 |a GBV_ILN_2038 
912 |a GBV_ILN_2044 
912 |a GBV_ILN_2048 
912 |a GBV_ILN_2049 
912 |a GBV_ILN_2050 
912 |a GBV_ILN_2055 
912 |a GBV_ILN_2056 
912 |a GBV_ILN_2057 
912 |a GBV_ILN_2059 
912 |a GBV_ILN_2061 
912 |a GBV_ILN_2064 
912 |a GBV_ILN_2068 
912 |a GBV_ILN_2088 
912 |a GBV_ILN_2093 
912 |a GBV_ILN_2106 
912 |a GBV_ILN_2107 
912 |a GBV_ILN_2108 
912 |a GBV_ILN_2110 
912 |a GBV_ILN_2111 
912 |a GBV_ILN_2113 
912 |a GBV_ILN_2118 
912 |a GBV_ILN_2119 
912 |a GBV_ILN_2122 
912 |a GBV_ILN_2129 
912 |a GBV_ILN_2143 
912 |a GBV_ILN_2144 
912 |a GBV_ILN_2147 
912 |a GBV_ILN_2148 
912 |a GBV_ILN_2152 
912 |a GBV_ILN_2153 
912 |a GBV_ILN_2188 
912 |a GBV_ILN_2190 
912 |a GBV_ILN_2232 
912 |a GBV_ILN_2336 
912 |a GBV_ILN_2470 
912 |a GBV_ILN_2472 
912 |a GBV_ILN_2507 
912 |a GBV_ILN_2522 
912 |a GBV_ILN_2548 
912 |a GBV_ILN_2932 
912 |a GBV_ILN_2940 
912 |a GBV_ILN_2947 
912 |a GBV_ILN_2949 
912 |a GBV_ILN_2950 
912 |a GBV_ILN_4012 
912 |a GBV_ILN_4035 
912 |a GBV_ILN_4037 
912 |a GBV_ILN_4046 
912 |a GBV_ILN_4112 
912 |a GBV_ILN_4125 
912 |a GBV_ILN_4126 
912 |a GBV_ILN_4242 
912 |a GBV_ILN_4246 
912 |a GBV_ILN_4249 
912 |a GBV_ILN_4251 
912 |a GBV_ILN_4305 
912 |a GBV_ILN_4306 
912 |a GBV_ILN_4307 
912 |a GBV_ILN_4313 
912 |a GBV_ILN_4322 
912 |a GBV_ILN_4323 
912 |a GBV_ILN_4324 
912 |a GBV_ILN_4325 
912 |a GBV_ILN_4326 
912 |a GBV_ILN_4333 
912 |a GBV_ILN_4334 
912 |a GBV_ILN_4335 
912 |a GBV_ILN_4336 
912 |a GBV_ILN_4338 
912 |a GBV_ILN_4346 
912 |a GBV_ILN_4393 
912 |a GBV_ILN_4700 
951 |a AR 
952 |d 72  |j 2004  |e 4  |h 1221-1246