Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/253
Title: | Local polynomial estimation in multiparameter likelihood models | Authors: | AERTS, Marc CLAESKENS, Gerda |
Issue Date: | 1997 | Source: | Journal of the American Statistical Association, 92(440). p. 1536-1545 | Abstract: | The purpose of this article is to extend local oneparameter models to multiparameter likelihood models. The main motivation is the need for nonparametric alternatives to parametric dose-response models for clustered binary data. Such data arise in developmental toxicity studies, designed to assess the potential adverse effects of drugs and other exposures on developing fetuses of pregnant rodents (dams). A typical experiment includes a control group and some dosed groups with special attention for the low doses. Exposure usually occurs early in gestation, the dams are sacrificed prior to term, and the uterine contents examined for defects. The analysis of the resulting binary data (malformation yes/no) must account for the litter effect induced by the clustering of offspring within dams. Different types of models (marginal, conditional, and random-effects models) are available. (For a recent survey, see Pendergast et al. 1996.) Next to the malformation probability, these models all include one or more parameters to describe the association between outcomes. More details are given in Section 2 | Document URI: | http://hdl.handle.net/1942/253 | Link to publication/dataset: | http://www.amstat.org/publications/jasa/index.cfm?fuseaction=AERTSdec1997 | ISI #: | 000071132200035 | Type: | Journal Contribution | Validations: | ecoom 1999 |
Appears in Collections: | Research publications |
Show full item record
WEB OF SCIENCETM
Citations
46
checked on May 2, 2024
Page view(s)
108
checked on Jun 7, 2023
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.