APPROPRIATE KERNEL REGRESSION ON A COUNT EXPLANATORY VARIABLE AND APPLICATIONS

被引：0

作者：

Kokonendji, Celestin C. ^{[1
]}

Kiesse, Tristan Senga ^{[1
]}

Demetrio, Clarice G. B. ^{[2
]}

机构：

[1] Univ Pau, LMA UMR CNRS 5142, Pau, France

[2] Univ Sao Paulo, ESALQ, Piracicaba, SP, Brazil

来源：

ADVANCES AND APPLICATIONS IN STATISTICS | 2009年 / 12卷 / 01期

基金：

巴西圣保罗研究基金会;

关键词：

count data; cross-validation; discrete kernel est imator; discrete triangular distribution; nonparametric regression;

D O I：

暂无

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

We propose an appropriate nonparametric regression on a single count regressor using a recent discrete kernel approach. We adapt the Nadaraya-Watson estimator to this discrete kernel for smoothing the regression function on count data. Some properties are studied; in particular, the bandwidth selection is investigated through the cross-validation method. The proposed regression, in addition to being simple, easy to implement and effective, outperforms the competing usual regressions for small and moderate sample sizes. Using simulations and two examples from real life, the importance and the performance of discrete kernels are pointed out and compared with the optimal continuous kernel.

引用

页码：99 / 125

页数：27

共 23 条

[1]

Bierens H. J., NON LINEAR REGRESSIO, P269

[2]

Bosq D., 1987, THEORIE LESTIMATION

[3] Probability density function estimation using gamma kernels [J].