Acta mathematica scientia,Series A ›› 2012, Vol. 32 ›› Issue (2): 297-311.

• Articles • Previous Articles     Next Articles

Inferences in a Censored Single-index Model with Empirical Likelihood

 YANG Yi-Ping1, XUE Liu-Gen2, CHENG Wei-Hu2   

  1. 1.College of Mathematics and Statistics, Chongqing Technology and Business University, Chongqing 400067;
    2.College of Applied Sciences, Beijing University of Technology, Beijing 100124
  • Received:2009-09-28 Revised:2010-09-16 Online:2012-04-25 Published:2012-04-25
  • Supported by:

    国家社科基金(11CTJ004)、国家自然科学基金(11126332, 11101452)、重庆市自然科学基金(CSTC2011JJA00014)、重庆市教委科学技术研究项目(KJ110720)、北京市自然科学基金(1102008)和广西自然科学基金(2010GXNSFB013051)资助

Abstract:

Empirical  likelihood method for single-index models with randomly censored data is investigated. An estimated empirical likelihood for the parameters by using a synthetic data approach is developed. An adjusted empirical log-likelihood ratio function is proven  to be asymptotically standard chi-squared, and the corresponding confidence regions of the parameters are then constructed. Furthermore,
 since the index is of norm 1, this constraint is used to reduce the dimension of parameters, which increases the accuracy of the confidence regions.  A simulation study indicates that compared with a normal approximation method, the proposed method works better in terms of coverage probabilities and areas of confidence regions.

Key words: Censored data, Single-index model, Empirical likelihood,  , χ2-distribution

CLC Number: 

  • 62G05
Trendmd