Dear R-list members, I´m trying to run a S-plus source (diag.norm) from http://www.ime.usp.br/~giapaula/programas.html in R I´m having problems in the following lines: lms <- summary(fit.model) # fit.model is a glm from gaussian family s <- lms$sigma It seems that sigma is not a summary.glm object in R, isn´t it? (s is NULL) Which is the equivalent object in R? Thanks in advance. Antonio Olinto ----------------------------------------------------- -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
> > I?m having problems in the following lines: > > lms <- summary(fit.model) # fit.model is a glm from gaussian > family > s <- lms$sigmas <- lms$deviance/lms$df.residual Deviance is a more general term than standard deviation when fitting non-gaussian models. -- Sundar Dorai-Raj, Ph.D. Assistant Professor Discrete & Statistical Sciences Office: (334) 844-3647 231 Allison Lab Fax: (334) 844-3611 Auburn University Email: dorairaj at dms.auburn.edu Auburn AL 36849-5307 http://www.dms.auburn.edu/~dorairaj/ -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
On Tue, 16 Oct 2001 aolinto at bignet.com.br wrote:> Dear R-list members, > > I´m trying to run a S-plus source (diag.norm) from > http://www.ime.usp.br/~giapaula/programas.html in R > > I´m having problems in the following lines: > > lms <- summary(fit.model) # fit.model is a glm from gaussian > family > s <- lms$sigma > > It seems that sigma is not a summary.glm object in R, isn´t > it? (s is NULL) >It is a summary.glm object. They have a different structure in R. The dispersion parameter is lms$dispersion, which is the square of the residual standard deviation for a linear model, so you want s<-sqrt(lms$dispersion) -thomas Thomas Lumley Asst. Professor, Biostatistics tlumley at u.washington.edu University of Washington, Seattle -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
> > > > > I?m having problems in the following lines: > > > > lms <- summary(fit.model) # fit.model is a glm from gaussian > > family > > s <- lms$sigma > > s <- lms$deviance/lms$df.residual > > Deviance is a more general term than standard deviation when > fitting non-gaussian models.Sorry, make that "variance" rather than "standard deviation." To obtain an estimate of s, just take the sqrt. Sundar -- Sundar Dorai-Raj, Ph.D. Assistant Professor Discrete & Statistical Sciences Office: (334) 844-3647 231 Allison Lab Fax: (334) 844-3611 Auburn University Email: dorairaj at dms.auburn.edu Auburn AL 36849-5307 http://www.dms.auburn.edu/~dorairaj/ -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._