论文信息 - The nonexistence of moments of some kernel regression estimators

The nonexistence of moments of some kernel regression estimators

In the setting of nonparametric density estimation, it is seen that the moments of kerneL based estimators (with high order kerneLs) may not exist. Thus the popuLar error criterion of mean square error may be useLess in this setting.

Wolfgang Hardle | W. Hardle

[1] G. S. Watson,et al. Smooth regression analysis , 1964 .

[2] E. Nadaraya. On Estimating Regression , 1964 .

[3] W. Härdle,et al. Optimal Bandwidth Selection in Nonparametric Regression Function Estimation , 1985 .

[4] G. Collomb. Estimation Non-paramétrique de la Régression: Revue Bibliographique@@@Estimation Non-parametrique de la Regression: Revue Bibliographique , 1981 .

[5] E. Parzen. On Estimation of a Probability Density Function and Mode , 1962 .

[6] H. Müller,et al. Kernel estimation of regression functions , 1979 .