Loading...
Please wait, while we are loading the content...
Similar Documents
Model Diagnostics for Smoothing Spline ANOVA Models
| Content Provider | Semantic Scholar |
|---|---|
| Author | Gu, Chong |
| Copyright Year | 2004 |
| Abstract | Functional ANOVA decompositions can be incorporated in multivariate function estimation through the penalized likelihood method. In this article, we propose some simple diagnostics for the “testing” of selected model terms in the decomposition; the elimination of practically insignificant terms generally enhances the interpretability of the estimates, and sometimes may also have inferential implications. What we try to achieve are the tasks of the traditional likelihood ratio tests, but in the absence of sampling distributions due to the typically infinite dimensional nulls in nonparametric settings. The diagnostics are illustrated in the settings of regression, probability density estimation, and hazard rate estimation. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.stat.purdue.edu/~chong/ps/diag.ps |
| Alternate Webpage(s) | http://www.stat.purdue.edu/~chong/ps/diag1.pdf |
| Alternate Webpage(s) | http://www.stat.purdue.edu/~chong/ps/diag.pdf |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Estimated Excretory function Inferential theory of learning Kernel density estimation Sampling (signal processing) Smoothing (statistical technique) Smoothing spline likelihood ratio |
| Content Type | Text |
| Resource Type | Article |
