×

A simple method for estimating interactions between a treatment and a large number of covariates. (English) Zbl 1368.62294

Summary: We consider a setting in which we have a treatment and a potentially large number of covariates for a set of observations, and wish to model their relationship with an outcome of interest. We propose a simple method for modeling interactions between the treatment and covariates. The idea is to modify the covariate in a simple way, and then fit a standard model using the modified covariates and no main effects. We show that coupled with an efficiency augmentation procedure, this method produces clinically meaningful estimators in a variety of settings. It can be useful for practicing personalized medicine: determining from a large set of biomarkers, the subset of patients that can potentially benefit from a treatment. We apply the method to both simulated datasets and real trial data. The modified covariates idea can be used for other purposes, for example, large scale hypothesis testing for determining which of a set of covariates interact with a treatment variable.

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62J07 Ridge regression; shrinkage estimators (Lasso)
PDFBibTeX XMLCite
Full Text: DOI arXiv Link

References:

[1] DOI: 10.1093/biostatistics/kxh002 · Zbl 1154.62384
[2] DOI: 10.1056/NEJMoa042739
[3] Chen W., Statistics in Medicine 31 pp 2693– (2012)
[4] DOI: 10.1080/01621459.1998.10473750
[5] DOI: 10.1198/016214501753382273 · Zbl 1073.62547
[6] DOI: 10.1214/aos/1176347963 · Zbl 0765.62064
[7] DOI: 10.1080/01621459.2000.10474271
[8] DOI: 10.1214/088342306000000466 · Zbl 1246.68180
[9] Huang J., Statistica Sinica 18 pp 1603– (2008)
[10] DOI: 10.1214/13-AOS1098 · Zbl 1292.62135
[11] DOI: 10.1214/074921707000000337 · Zbl 1176.62066
[12] DOI: 10.1214/13-AOS1098 · Zbl 1292.62135
[13] DOI: 10.1080/01621459.1989.10478874
[14] DOI: 10.1200/JCO.2006.07.1522
[15] DOI: 10.1214/12-STS400 · Zbl 1331.62350
[16] DOI: 10.1214/10-AOS864 · Zbl 1216.62178
[17] DOI: 10.2307/2335942
[18] DOI: 10.1200/JCO.2007.14.8981
[19] DOI: 10.1016/j.csda.2006.12.041 · Zbl 1161.62439
[20] DOI: 10.1161/CIRCULATIONAHA.105.592733
[21] DOI: 10.2202/1557-4679.1071
[22] DOI: 10.1093/biostatistics/kxq047
[23] Tibshirani R., Journal of the Royal Statistical Society 58 pp 267– (1996)
[24] DOI: 10.1073/pnas.082099299
[25] DOI: 10.1073/pnas.091062498 · Zbl 1012.92014
[26] DOI: 10.1214/009053607000000929 · Zbl 1138.62323
[27] DOI: 10.1214/09-EJS506 · Zbl 1327.62425
[28] DOI: 10.1214/09-AOS729 · Zbl 1183.62120
[29] DOI: 10.1214/07-AOS520 · Zbl 1142.62044
[30] DOI: 10.1214/12-STS399 · Zbl 1331.62353
[31] Zhao P., Journal of Machine Learning Research 7 pp 2541– (2006)
[32] DOI: 10.1080/01621459.2012.695674 · Zbl 1443.62396
[33] DOI: 10.1198/016214506000000735 · Zbl 1171.62326
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.