Skip to main page content
U.S. flag

An official website of the United States government

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021;116(534):690-693.
doi: 10.1080/01621459.2020.1833887. Epub 2021 Apr 1.

Discussion of Kallus (2020) and Mo et al (2020)

Muxuan Liang  1 , Ying-Qi Zhao  1
Affiliations

Discussion of Kallus (2020) and Mo et al (2020)

Muxuan Liang et al. J Am Stat Assoc. 2021.

Abstract

We discuss the results on improving the generalizability of individualized treatment rule following the work in Kallus [1] and Mo et al. [5]. We note that the advocated weights in Kallus [1] are connected to the efficient score of the contrast function. We further propose a likelihood-ratio-based method (LR-ITR) to accommodate covariate shifts, and compare it to the CTE-DR-ITR method proposed in Mo et al. [5]. We provide the upper-bound on the risk function of the target population when both the covariate shift and the contrast function shift are present. Numerical studies show that LR-ITR can outperform CTE-DR-ITR when there is only covariate shift.

Keywords: Generalizability; covariate shift; density-ratio estimation; efficient score.

PubMed Disclaimer

Similar articles

See all similar articles

Cited by

References

    1. Kallus N [2020], ‘More efficient policy learning via optimal retargeting’, Journal of the American Statistical Association pp. 1–13.
    1. Kanamori T, Hido S and Sugiyama M [2009], ‘A least-squares approach to direct importance estimation’, The Journal of Machine Learning Research 10, 1391–1445.
    1. Liang M and Yu M [2020], ‘A semiparametric approach to model effect modification’, Journal of the American Statistical Association (just-accepted), 1–33.
    1. Liu Y, Wang Y, Kosorok MR, Zhao Y and Zeng D [2018], ‘Augmented outcome-weighted learning for estimating optimal dynamic treatment regimens’, Statistics in Medicine 37(26), 3776–3788. - PMC - PubMed
    1. Mo W, Qi Z and Liu Y [2020], ‘Learning optimal distributionally robust individualized treatment rules’, Journal of the American Statistical Association (just-accepted), 1–40. - PMC - PubMed

LinkOut - more resources