Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*overdispersion\s+in\s+logistic\s+regression\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*overdispersion\s+in\s+logistic\s+regression\s*$/: 4 ]

Total 4 documents matching your query.

1. overdispersion in logistic regression (score: 1): Author: mtexeira@agro.uba.ar; Date: Mon, 11 Jul 2005 15:07:52 -0300; Everybody knows how can I correct for overdispersion in a logistic regression problem ? thanks Marcos Texeira; /archives/html/s-news/2005-07/msg00054.html (6,830 bytes)
2. Re: overdispersion in logistic regression (score: 1): Author: Sundar Dorai-Raj <sundar.dorai-raj@pdf.com>; Date: Mon, 11 Jul 2005 13:13:12 -0500; Everybody knows how can I correct for overdispersion in a logistic regression problem ? thanks Marcos Texeira Use the quasi family: fit <- glm(Kyphosis ~ 1, quasi("logit", "mu(1-mu)"), kyphosis) summ; /archives/html/s-news/2005-07/msg00055.html (7,968 bytes)
3. Re: overdispersion in logistic regression (score: 1): Author: Tim Hesterberg <timh@insightful.com>; Date: 13 Jul 2005 17:24:39 -0700; I would typically estimate parameters ignoring the over-dispersion, then specified the dispersion when calling summary(). I don't recall if I estimated the dispersion myself, or passed dispersion =; /archives/html/s-news/2005-07/msg00085.html (7,666 bytes)
4. Re: overdispersion in logistic regression (score: 1): Author: Spencer Graves <spencer.graves@pdf.com>; Date: Thu, 14 Jul 2005 10:30:32 -0700; Have you tried "family=quasi"? See "?glm", "?family", "?anova.glm", and "args(anova.glm)". In particular, you want 'test="Chisq"' or even 'test="F"'. spencer graves Everybody knows how can I correct; /archives/html/s-news/2005-07/msg00090.html (9,128 bytes)

Current List: 1 - 4
Page: [1]