Sample splitting with Markov chains
Schick, Anton
Bernoulli, Tome 7 (2001) no. 6, p. 33-61 / Harvested from Project Euclid
Sample splitting techniques play an important role in constructing estimates with prescribed influence functions in semi-parametric and nonparametric models when the observations are independent and identically distributed. This paper shows how a contiguity result can be used to modify these techniques to the case when the observations come from a stationary and ergodic Markov chain. As a consequence, sufficient conditions for the construction of efficient estimates in semi-parametric Markov chain models are obtained. The applicability of the resulting theory is demonstrated by constructing an estimate of the innovation variance in a nonparametric autoregression model, by constructing a weighted least-squares estimate with estimated weights in an autoregressive model with martingale innovations, and by constructing an efficient and adaptive estimate of the autoregression parameter in a heteroscedastic autoregressive model with symmetric errors.
Publié le : 2001-02-14
Classification:  contiguity,  efficient estimation,  ergodicity,  heteroscedastic autoregressive model,  nonparametric autoregressive model,  semi-parametric models,  stationary Markov chains,  V-uniform ergodicity,  weighted least-squares estimation
@article{1080572338,
     author = {Schick, Anton},
     title = {Sample splitting with Markov chains},
     journal = {Bernoulli},
     volume = {7},
     number = {6},
     year = {2001},
     pages = { 33-61},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1080572338}
}
Schick, Anton. Sample splitting with Markov chains. Bernoulli, Tome 7 (2001) no. 6, pp.  33-61. http://gdmltest.u-ga.fr/item/1080572338/