TY - JOUR
T1 - Composite Estimation for Single-Index Models with Responses Subject to Detection Limits
AU - Tang, Yanlin
AU - Wang, Huixia Judy
AU - Liang, Hua
N1 - KAUST Repository Item: Exported on 2020-10-01
Acknowledged KAUST grant number(s): OSR-2015-CRG4-2582
Acknowledgements: The authors would like to thank two anonymous reviewers, an associate editor and the editor for constructive comments and helpful suggestions. This research was partially supported by National Natural Science Foundation of China (NSFC) grants 11301391 and 11526133 (Tang), NSFC grant 11529101 (Liang), National Science Foundation (NSF) grant DMS-1418042 (Liang), NSF CAREER AwardDMS-1149355 (Wang) and the OSR-2015-CRG4-2582 grant from KAUST (Wang and Tang).
This publication acknowledges KAUST support, but has no KAUST affiliated authors.
PY - 2017/11/3
Y1 - 2017/11/3
N2 - We propose a semiparametric estimator for single-index models with censored responses due to detection limits. In the presence of left censoring, the mean function cannot be identified without any parametric distributional assumptions, but the quantile function is still identifiable at upper quantile levels. To avoid parametric distributional assumption, we propose to fit censored quantile regression and combine information across quantile levels to estimate the unknown smooth link function and the index parameter. Under some regularity conditions, we show that the estimated link function achieves the non-parametric optimal convergence rate, and the estimated index parameter is asymptotically normal. The simulation study shows that the proposed estimator is competitive with the omniscient least squares estimator based on the latent uncensored responses for data with normal errors but much more efficient for heavy-tailed data under light and moderate censoring. The practical value of the proposed method is demonstrated through the analysis of a human immunodeficiency virus antibody data set.
AB - We propose a semiparametric estimator for single-index models with censored responses due to detection limits. In the presence of left censoring, the mean function cannot be identified without any parametric distributional assumptions, but the quantile function is still identifiable at upper quantile levels. To avoid parametric distributional assumption, we propose to fit censored quantile regression and combine information across quantile levels to estimate the unknown smooth link function and the index parameter. Under some regularity conditions, we show that the estimated link function achieves the non-parametric optimal convergence rate, and the estimated index parameter is asymptotically normal. The simulation study shows that the proposed estimator is competitive with the omniscient least squares estimator based on the latent uncensored responses for data with normal errors but much more efficient for heavy-tailed data under light and moderate censoring. The practical value of the proposed method is demonstrated through the analysis of a human immunodeficiency virus antibody data set.
UR - http://hdl.handle.net/10754/626683
UR - http://doi.wiley.com/10.1111/sjos.12307
UR - http://www.scopus.com/inward/record.url?scp=85032897206&partnerID=8YFLogxK
U2 - 10.1111/sjos.12307
DO - 10.1111/sjos.12307
M3 - Article
SN - 0303-6898
VL - 45
SP - 444
EP - 464
JO - Scandinavian Journal of Statistics
JF - Scandinavian Journal of Statistics
IS - 3
ER -