similar to: MASS::loglm - exploring a collection of models with add1, drop1

Dear R-help community, I am working with multidimensional contingency tables and I am having trouble getting loglm to run on all dimensions without typing out each dimension. I have generated random data and provided output for the results I want below: d1.c1 <- rnorm(20, .10, .02) d1.c2 <- rnorm(20, .10, .02) d2.c1 <- rnorm(20, .09, .02) d2.c2 <- rnorm(20, .09, .02) d3.c1 <-

The null loglinear model is an intercept-only model for log frequency, log(f) = \mu For a one-way table the test of the null model is the same as the chisq.test. This can be fit using loglin(), but I don't think there is any way to specify this using MASS::loglm > t1<- margin.table(Titanic,1) > t1 Class 1st 2nd 3rd Crew 325 285 706 885 > loglin(t1, NULL) 0

loglm() is a port of an original written for S-PLUS. The fact that it carries only a reference to the data frame is neither intentional nor unintentional, but an unnoticed side-effect. I can see advantages both ways. (I'm not so sure, either, that what you say is standard behaviour for model fitting functions really is so universal.) It would not be too hard to come up with a version that

Bug report: there is a problem with loglm (or some underlying code) when used with updating within a function. For example, this code works as expected, when used outside a function: ------------------------------------------------- library(MASS)

I have numerous replicated goodness-of-fit experiments (observed compared to expected counts in categories) and these replicates are nested within a factor. The expected counts in each cell are external (from a scientific model being tested). The calculations I need within each level of the nesting factor are a heterogeneity G test, with the total G and the pooled G across replicates. Then I

Dear R-helpers, Im trying to fit a Log-linear model on a dataset with bird counts from 60 sites over 14 years for 12 months each (factors for the models). One of the aims is to predict the missing values in this dataset with model predictions. Ive first tried to work with GLM's, that worked fine except for models with one or more interaction-terms. The GLMs run, run .. for hours. So I

Dear all, sorry to bother you all with this but I've been trying to use the loglm in MASS package (v2.8.0) and cannot get any sensible output. I'm wondering am I doing something very foolish or missing something obvious. For example, I tried the documentation help(loglm) example - here's the code # Case 1: frequencies specified as an array. sapply(minn38,

Dear R Help, I have noticed some inconsistent behaviour of add1 and drop1 with a weighted linear model, which affects the interpretation of the results. I have these data to fit with a linear model, I want to weight them by the relative size of the geographical areas they represent. _________________________________________________________________________________________ > example

I can use data() to find the available datasets in a package, but I'd like to extract and display some additional information for each dataset than what is provided by data(), e.g., class() and dim() for datasets for which these are available. I'm stuck on using using lapply properly with objects, rather than the names of objects that I get from data() Example: > DS <-

I use rsync to backup my system, using a command-line such as the following: > rsync [src] [dst] -a --link-dest --size-only In this case, [src] is produced by a command that makes no attempt to preserve timestamps ("svnadmin hotcopy", in this case). That's why I use --size-only. Here's the rub: identical files aren't hard-linked like I expect them to be. They're full

Dear all, i need help about comparing 2 alpha cronbach. How to derive W statistic. Are alpha cronbach and Hoyt's method using ANOVA identical? Thank you for your help. Regards --------------------------------- Luggage? GPS? Comic books? [[alternative HTML version deleted]]

I received the following email note re: the vcdExtra package > A vcd update has shown that packages TIMP and vcdExtra are not > declaring their dependence on colorspace/MASS: see > > http://cran.r-project.org/web/checks/check_results_vcdExtra.html But, I can't see what to do to avoid this, nor understand what has changed in R devel. Sure enough, CRAN now reports errors in

When I run net add groupmap rid=512 ntgroup="Domain Admins" UNIXgroup="ntadmins" i get this error: adding entry for group Domain Admins failed! The error isn't very specific and the log doesn't show any error. I look in the log (log level -1 in slapd.conf) and I can tell it is able to search. I can post the syslog if you need it. I think their is an error in my

I am using R 2.1.1 under Mac OS 10.3.9. Two related problems (see notes 1. and 2. below) are illustrated by results of the following: y <- rnorm(10) x <- z <- 1:10 is.na(x[9]) <- TRUE lm0 <- lm(y ~ 1) lm1 <- lm(y ~ 1, weights = rep(1, 10)) add1(lm0, scope = ~ x) ## works ok add1(lm1, scope = ~ x) ## error lm2 <- lm(y ~ 1, offset = 1:10) add1(lm0, scope = ~ z) ##

David, Thanks. The reason add1.lm (and drop1.lm) do not support offsets is that lm did not when they were written, and the person who added offsets to lm did not change them. (I do wish they had not added an offset arg and just used the formula as in S's glm.) That is easy to add. For the other point, some care is needed if 'x' is supplied and the upper scope reduces the number

Should the F statistic be the same when using add1() on models created by lm and glm(family=gaussian)? They are in the single-degree-of-freedom case but not in the multiple-degree-of-freedom case. MASS:addterm shows the same discrepancy. It looks like the deviance (==residual sum of squares) gets divided by the number of degrees of freedom for the term twice in add1.glm. Using anova() on the

I am trying to fit a nonlinear regression model to data. There are several predictor variables and 8 parameters. I will write the model as Y ~ Yhat(theta1,...,theta8) OK, I can do this using nls() - but "only just" as there are not as many observations as might be desired. Now the problem is that we have a factor "Site" and I want to include a corresponding error

I was wondering if there is anyway to have Add1() display the coefficient estimates for each candidate predictor along with the F test. This is for lm() btw. Thanks -- View this message in context: http://r.789695.n4.nabble.com/Add1-w-coef-estimates-tp2279662p2279662.html Sent from the R help mailing list archive at Nabble.com.

Hello, I have a question about the add1() function and quasilikelihoods for GLMs. I am fitting quasi-Poisson models using glm(, family = quasipoisson). Technically, with the quasilikelihood approach the deviance does not have the interpretation as a likelihood-based measure of sample information. Functions such as stepAIC() cannot be used. The function add1() returns the change in the scaled

Se ha borrado un texto insertado con un juego de caracteres sin especificar... Nombre: no disponible Url: https://stat.ethz.ch/pipermail/r-help/attachments/20070521/f7808713/attachment.pl