A crossvalidation method for estimating conditional densities

Jianqing Fan Tsz Ho Yim

Statistics Theory and Methods mathscidoc:1912.43292

Biometrika, 91, (4), 819-834, 2004.12
We extend the idea of crossvalidation to choose the smoothing parameters of the double-kernel local linear regression for estimating a conditional density. Our selection rule optimises the estimated conditional density function by minimising the integrated squared error. We also discuss three other bandwidth selection rules, an ad hoc method used by Fan et al. (1996), a bootstrap method of Hall et al. (1999) for bandwidth selection in the estimation of conditional distribution functions, modified by Bashtannyk & Hyndman (2001) to cover conditional density functions, and finally a simple approach proposed by Hyndman & Yao (2002). The performance of the new approach is compared with these three methods by simulation studies, and our method performs outstandingly well. The method is illustrated by an application to estimating the transition density and the Value-at-Risk of treasury-bill data.
No keywords uploaded!
[ Download ] [ 2019-12-21 11:35:26 uploaded by Jianqing_Fan ] [ 326 downloads ] [ 0 comments ]
  title={A crossvalidation method for estimating conditional densities},
  author={Jianqing Fan, and Tsz Ho Yim},
Jianqing Fan, and Tsz Ho Yim. A crossvalidation method for estimating conditional densities. 2004. Vol. 91. In Biometrika. pp.819-834. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20191221113526434755852.
Please log in for comment!
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved