Optimal dynamic treatment regimes

S. A. Murphy; Elja Arjas; C. Jennison; A. P. Dawid; D. R. Cox; Stephen Senn; Robert G. Cowell; V. Didelez; Richard D. Gill; J. B. Kadane; James M. Robins

doi:10.1111/1467-9868.00389

Optimal dynamic treatment regimes

S. A. Murphy^*, Elja Arjas, C. Jennison, A. P. Dawid, D. R. Cox, Stephen Senn, Robert G. Cowell, V. Didelez, Richard D. Gill, J. B. Kadane, James M. Robins

^*Corresponding author for this work

Research output: Contribution to journal › Article › Research › peer-review

670 Citations (Scopus)

Abstract

A dynamic treatment regime is a list of decision rules, one per time interval, for how the level of treatment will be tailored through time to an individual's changing status. The goal of this paper is to use experimental or observational data to estimate decision regimes that result in a maximal mean response. To explicate our objective and to state the assumptions, we use the potential outcomes model. The method proposed makes smooth parametric assumptions only on quantities that are directly relevant to the goal of estimating the optimal rules. We illustrate the methodology proposed via a small simulation.

Original language	English
Pages (from-to)	331-355
Number of pages	25
Journal	Journal of the Royal Statistical Society. Series B: Statistical Methodology
Volume	65
Issue number	2
DOIs	https://doi.org/10.1111/1467-9868.00389
Publication status	Published - 2003
Externally published	Yes

Keywords

Adaptive strategies
Causal inference
Dynamic programming
Multistage decisions

Access to Document

10.1111/1467-9868.00389

Cite this

@article{67cee36e78d64a7eadee187c90e14b16,

title = "Optimal dynamic treatment regimes",

abstract = "A dynamic treatment regime is a list of decision rules, one per time interval, for how the level of treatment will be tailored through time to an individual's changing status. The goal of this paper is to use experimental or observational data to estimate decision regimes that result in a maximal mean response. To explicate our objective and to state the assumptions, we use the potential outcomes model. The method proposed makes smooth parametric assumptions only on quantities that are directly relevant to the goal of estimating the optimal rules. We illustrate the methodology proposed via a small simulation.",

keywords = "Adaptive strategies, Causal inference, Dynamic programming, Multistage decisions",

author = "Murphy, {S. A.} and Elja Arjas and C. Jennison and Dawid, {A. P.} and Cox, {D. R.} and Stephen Senn and Cowell, {Robert G.} and V. Didelez and Gill, {Richard D.} and Kadane, {J. B.} and Robins, {James M.}",

year = "2003",

doi = "10.1111/1467-9868.00389",

language = "English",

volume = "65",

pages = "331--355",

journal = "Journal of the Royal Statistical Society. Series B: Statistical Methodology",

issn = "1369-7412",

publisher = "Oxford University Press",

number = "2",

}

TY - JOUR

T1 - Optimal dynamic treatment regimes

AU - Murphy, S. A.

AU - Arjas, Elja

AU - Jennison, C.

AU - Dawid, A. P.

AU - Cox, D. R.

AU - Senn, Stephen

AU - Cowell, Robert G.

AU - Didelez, V.

AU - Gill, Richard D.

AU - Kadane, J. B.

AU - Robins, James M.

PY - 2003

Y1 - 2003

N2 - A dynamic treatment regime is a list of decision rules, one per time interval, for how the level of treatment will be tailored through time to an individual's changing status. The goal of this paper is to use experimental or observational data to estimate decision regimes that result in a maximal mean response. To explicate our objective and to state the assumptions, we use the potential outcomes model. The method proposed makes smooth parametric assumptions only on quantities that are directly relevant to the goal of estimating the optimal rules. We illustrate the methodology proposed via a small simulation.

AB - A dynamic treatment regime is a list of decision rules, one per time interval, for how the level of treatment will be tailored through time to an individual's changing status. The goal of this paper is to use experimental or observational data to estimate decision regimes that result in a maximal mean response. To explicate our objective and to state the assumptions, we use the potential outcomes model. The method proposed makes smooth parametric assumptions only on quantities that are directly relevant to the goal of estimating the optimal rules. We illustrate the methodology proposed via a small simulation.

KW - Adaptive strategies

KW - Causal inference

KW - Dynamic programming

KW - Multistage decisions

UR - http://www.scopus.com/inward/record.url?scp=0038107066&partnerID=8YFLogxK

U2 - 10.1111/1467-9868.00389

DO - 10.1111/1467-9868.00389

M3 - Article

AN - SCOPUS:0038107066

SN - 1369-7412

VL - 65

SP - 331

EP - 355

JO - Journal of the Royal Statistical Society. Series B: Statistical Methodology

JF - Journal of the Royal Statistical Society. Series B: Statistical Methodology

IS - 2

ER -

Optimal dynamic treatment regimes

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this