Ultrahigh-dimensional variable selection plays an increasingly important role in contemporary scientific discoveries and statistical research. Among others, Fan and Lv [J. R. Stat. Soc. Ser. B Stat. Methodol. 70 (2008) 849–911] propose an independent screening framework by ranking the marginal correlations. They showed that the correlation ranking procedure possesses a sure independence screening property within the context of the linear model with Gaussian covariates and responses. In this paper, we propose a more general version of the independent learning with ranking the maximum marginal likelihood estimates or the maximum marginal likelihood itself in generalized linear models. We show that the proposed methods, with Fan and Lv [J. R. Stat. Soc. Ser. B Stat. Methodol. 70 (2008) 849–911] as a very special case, also possess the sure screening property with vanishing false selection rate. The conditions under which the independence learning possesses a sure screening is surprisingly simple. This justifies the applicability of such a simple method in a wide spectrum. We quantify explicitly the extent to which the dimensionality can be reduced by independence screening, which depends on the interactions of the covariance matrix of covariates and true parameters. Simulation studies are used to illustrate the utility of the proposed approaches. In addition, we establish an exponential inequality for the quasi-maximum likelihood estimator which is useful for high-dimensional statistical learning.
1 June 2011 in Journal of the American Statistical Association
A variable screening procedure via correlation learning was proposed by Fan and Lv (2008) to reduce dimensionality in sparse ultra-high-dimensional models. Even when the true model is linear, the m...
Individualized treatment rules recommend treatments based on individual patient characteristics in order to maximize clinical benefit. When the clinical outcome of interest is survival time, estimation is often complicated by censoring. We develop nonparametric methods for estimating an optimal individualized treatment rule in the presence of censored data. To adjust for censoring, we propose a doubly robust estimator which requires correct specification of either the censoring model or survival model, but not both; the method is shown to be Fisher consistent when either model is correct. Furthermore, we establish the convergence rate of the expected survival under the estimated optimal individualized treatment rule to the expected survival under the optimal individualized treatment rule. We illustrate the proposed methods using simulation study and data from a Phase III clinical trial on non-small cell lung cancer.
Background— In the Comparison of Medical Therapy, Pacing and Defibrillation in Heart Failure (COMPANION) trial, 1520 patients with advanced heart failure were assigned in a 1:2:2 ratio to optimal pharmacological therapy or optimal pharmacological therapy plus cardiac resynchronization therapy (CRT-P) or CRT with defibrillator (CRT-D). Use of CRT-P and CRT-D was associated with a significant reduction in combined risk of death or all-cause hospitalizations. Because mortality also was significantly reduced (optimal pharmacological therapy versus CRT-D only), an assessment of the true reduction in hospitalization rates must consider the competing risk of death and varying follow-up times. Methods and Results— To overcome the challenges of comparing treatment groups, we used a nonparametric test of right-censored recurrent events that accounts for multiple hospital admissions, differential follow-up time between treatment groups, and death as a competing risk. An end-point committee adjudicated and classified all hospitalizations. Compared with optimal pharmacological therapy, CRT-P and CRT-D were associated with a 21% and 25% reduction in all-cause, 34% and 37% reduction in cardiac, and 44% and 41% reduction in heart failure hospital admissions per patient-year of follow-up, respectively. Similar reductions were seen in hospitalization days per patient-year. The reduction in hospitalization rate for heart failure in the CRT groups appeared within days of randomization and remained sustained. Noncardiac hospitalization rates were not different between groups. Conclusion— Use of CRT with or without a defibrillator in advanced heart failure patients was associated with marked reductions in all-cause, cardiac, and heart failure hospitalization rates in an analysis that accounted for the competing risk of mortality and unequal follow-up time.
Precision medicine is a medical paradigm that focuses on finding the most effective treatment decision based on individual patient information. For many complex diseases, such as cancer, treatment decisions need to be tailored over time according to patients’ responses to previous treatments. Such an adaptive strategy is referred as a dynamic treatment regime. A major challenge in deriving an optimal dynamic treatment regime arises when an extraordinary large number of prognostic factors, such as patient’s genetic information, demographic characteristics, medical history and clinical measurements over time are available, but not all of them are necessary for making treatment decision. This makes variable selection an emerging need in precision medicine. In this paper, we propose a penalized multi-stage $A$-learning for deriving the optimal dynamic treatment regime when the number of covariates is of the nonpolynomial (NP) order of the sample size. To preserve the double robustness property of the $A$-learning method, we adopt the Dantzig selector, which directly penalizes the A-leaning estimating equations. Oracle inequalities of the proposed estimators for the parameters in the optimal dynamic treatment regime and error bounds on the difference between the value functions of the estimated optimal dynamic treatment regime and the true optimal dynamic treatment regime are established. Empirical performance of the proposed approach is evaluated by simulations and illustrated with an application to data from the STAR∗D study.
22 December 2021 in Journal of the Royal Statistical Society Series B: Statistical Methodology