[1]  Comte F. Kernel deconvolution of stochastic volatility models. Journal of Time Series Analysis, 2004, 25:  563--582

[2]  Fan J, Yao Q, Cai Zh. Adaptive varing-coefficient linear models. Journal of the Royal Statistical Society, Series B, 2003, 65: 57--80

[3]  Hardle W, Tsybakov A. Local polynomial estimators of volatility function in nonparametric autoregression. Journal of  Econometrics, 1997, 81: 223--242

[4]  Stefanski L A, Carroll R J. Deconvolution-based score tests in measurement error models. Ann Statist, 1991,  19: 249--259

[5]  Ango Nze P. Critéres d'ergodicité de quelques modéles à représentation markovienne. Comptes Rendus des Seances de I'Academie des Sciences Paris, 1992, 315: 1301--1304

[6]  Nummelin E, Tuominen P. Geometric ergodicity of Harris-recurrent Markov chains with applications to renewed theory. Stochastic Processes and their Applications, 1982, 12: 187--202

[7] Tweedie  R L. Sufficient conditions for ergodicity and geometric ergodicity of Markov chains on a general state space. Stochastic Process and their Applications, 1975, 3: 385--403

[8]  Tsybakov A B. Robust reconstruction of functions by the local-approximation method. Problems of Information Transmission, 1986, 22: 133--146

[9]  Allen D M. The relationship between variable and data augmentation and a method of prediction.  Technometrics, 1974, 16: 125--127

[10]  Stone  M. Cross-validatory choice and assessment of statistical predictions (with disscussion). Journal of the Royal Statistical Society (Series B), 1974, 36: 111--147

[11]  Fan J, Truong Y K. Nonparametric regression with errors in variables. Ann Statist, 1993, 21: 1900--1925

[12]  Davydov Yu A. Mixing conditions for Markov chains. Theory of Probability and its Applications, 1973, 18: 312--328

[13]  Lipster R Sh, Shirjaev A N. A functional central limit theorem for martingales. Theory of Probability and its Applications, 1980, 25: 667--668