%PDF-1.4
%
1 0 obj
<>stream
application/pdf
Taylor & Francis
10.1080/01621459.2017.1340887
en
Journal of the American Statistical Association, 2018. doi:10.1080/01621459.2017.1340887
Approximate dynamic programming
Backward induction
Bayesian additive regression trees
Gibbs sampling
Potential outcomes
A Bayesian Machine Learning Approach for Optimizing Dynamic Treatment Regimes
Thomas A. Murray
Ying Yuan
Peter F. Thall
Journal
Journal of the American Statistical Association
Copyright 2018 Taylor & Francis
0162-1459
1537-274X
113
523
1255
1267
10.1080/01621459.2017.1340887
https://doi.org/10.1080/01621459.2017.1340887
LaTeX with hyperref package
2018-10-08T12:35:25-07:00
2018-10-08T12:35:25-07:00
2018-09-12T17:41:50+05:30
AM
Approximate dynamic programming,Backward induction,Bayesian additive regression trees,Gibbs sampling,Potential outcomes
iText 4.2.0 by 1T3XT
10.1080/01621459.2017.1340887https://doi.org/10.1080/01621459.2017.13408872017-06-26truewww.tandfonline.com10.1080/01621459.2017.1340887www.tandfonline.comtrue2017-06-2610.1080/01621459.2017.1340887
endstream
endobj
4 0 obj
<>stream
xYɎ]5ݿx$-4(l}U$i!r՟V
[e*MtxsNUualjRD>ZMQݷƸ1[{JU=:xfU8>s'[y~{!e9g8G<5]?=3
\o{uät0|Unb"O2؋:]3C<|uLP
zfdGܲO3>e4hCõ
?B,wwίʩfğHtG#,@ʺYV]]vaVDH/UɂKecQ l\"]t /QKs쮄
-=ﯼ&c{[v/#פ6Su}x_"We3&lj
C&t3iPΑCsnAI4Ѻ
ZڌaPl2WiMPu~iOADB9#H$+tD{Lx
};f15M}vA+[\TS" BԇD[퀐WKbECmDLkCѰ7t[Dhue䨡\:e
.ݕmZVZB5gB;'ahב+;ZOKRxY98F6"+d-#d-1*I2% eThfq[,~.BnzNɐ{yilbz~y8-
ς`Yn#P\Je00%$LH'Ja5+69dvYz吽ѳQvc̰/R-ћW
,*g7evMxZ^x,SNLePʨ,hJȑbxt*q+\Sޮl;20OZ
>)LG@cq:S4'yu̲p]BZ-Cmq;:~Ӯbn'ӯcĝ@NȬ eb@,E,
ZsisUa,ڱySDHȸunW
|m!<"P9|}#߀Y~}3v-7l XhUKl)z3Ĺu
4,|ꦞ#sd&.[E`MMu_MC`FU !JߩF1fI)K Ҿ8#]La+;af"K:5_+}iـj3agNpF@/#}kvTF`-
B$G}XaH{_:.-^SP`
ۂeatkW
fԃo",en9d$*箎4oKD;ZY$ݚ&&֎^@6ҵI]^{^Za̓rulm:1z돳.E Oag3s2*~
;6.R&mz_8~̎[51@ja-{DQ:AŨ=%eǖFqo76];vgO