similar to: summary of the effects after logistic regression model

I am trying to extract significance levels out of a robcov+ols call. For background: I am analysing data where multiple measurements(2 per topic) were taken from individuals(36) on their emotional reaction (dependent variable) to various topics (3 topics). Because I have several emotions and a rotation to do on the topics, I'd like to have the results pumped into a nice table.

Hello, I have a problem with creating an identity matrix for glmnet by using the contrasts function. I have a factor with 4 levels. When I create dummy variables I think there should be n-1 variables (in this case 3) - so that the contrasts would be against the baseline level. This is also what is written in the help file for 'contrasts'. The problem is that the function

I want to compute confidence intervals for the random effect estimates for each subject. From checking on postings, this is what I cobbled together using Orthodont data.frame as an example. There was some discussion of how to properly access lmer slots and bVar, but I'm not sure I understood. Is the approach shown below correct? Rick B. # Orthodont is from nlme (can't have both nlme and

> library(MASS) > attach(bacteria) > table(y) y n y 43 177 > y<-1*(y=="y") > table(y,trt) trt y placebo drug drug+ 0 12 18 13 1 84 44 49 > library(lme4) > model1<-lmer(y~trt+(week|ID),family=binomial,method="PQL") Error in match.arg(method, c("Laplace", "AGQ")) : 'arg' should be one of

Hi! I need to run ols regressions with Huber-White sandwich estimators and the correponding standard errors, without an intercept. What I'm trying to do is create an ols object and then use the robcov() function, on the order of: f <- ols(depvar ~ ind1 + ind2, x=TRUE) robcov(f) However, when I go f <- ols(depvar ~ ind1 + ind2 -1, x=TRUE) I get the following error: Error in

Hi R-helpers I have a dataframe DF (lets say with the variables, y, x1, x2, x3, ..., clust) containing relatively many NAs. When I fit an ordinal regression model with the function lrm from the Design library: model.lrm <- lrm(y ~ x1 + x2, data=DF, x=TRUE, y=TRUE) it will by default delete missing values in the variables y, x1, x2. Based on model.lrm, I want to apply the robust covariance

Hello List, I'm trying to do a paired t-test, and I'm wondering if it's consistent with equations. I have a dataset that has a response and two treatments (here's an example): ID trt order resp 17 1 0 1 0.0037513592 18 2 0 1 0.0118723051 19 4 0 1 0.0002610251 20 5 0 1 -0.0077951450 21 6 0 1 0.0022339952 22 7 0 2

Hi, I am trying to figure out exactly what the bootcov() function in the Design package is doing within the context of clustered data. From reading the documentation/source code it appears that using bootcov() with the cluster argument constructs standard errors by resampling whole clusters of observations with replacement rather than resampling individual observations. Is that right, and is

Hi, I'm having some problems regarding the packages lme4 and nlme, more specifically in the denominator degrees of freedom. I used data Orthodont for the two packages. The commands used are below. require(nlme) data(Orthodont) fm1<-lme(distance~age+ Sex, data=Orthodont,random=~1|Subject, method="REML") anova(fm1) numDF DenDF F-value p-value (Intercept) 1

If I wanted to fit a logit model and account for clustering of observations, I would do something like: library(Design) f <- lrm(Y1 ~ X1 + X2, x=TRUE, y=TRUE, data=d) g <- robcov(f, d$st.year) What would I do if I wanted to do the same thing with a probit model? ?robcov says the input model must come from the Design package, but the Design package appears not to do probit? Thanks very

Hi all, To follow up on an older thread, it was suggested that the following would produce confidence intervals for the estimated BLUPs from a linear mixed effect model: OrthoFem<-Orthodont[Orthodont$Sex=="Female",] fm1OrthF. <- lmer(distance~age+(age|Subject), data=OrthoFem) fm1.s <- coef(fm1OrthF.)$Subject fm1.s.var <- fm1OrthF. at bVar$Subject fm1.s0.s <-

Hello, R users, I have two factors (treat, section) anova design experiment where there are 3 replicates. The objective of the experiment is to test if there is significant difference of yield between top (section 9 to 11) and bottom (section 9 to 11) of the fruit tree under treatment. I found that there are interaction between two factors. I wonder if I can contrast means from levels of

Dear Thomas Lumley, and R-help list members, I have read your article "Network meta-analysis for indirect treatment comparisons" (Statist Med, 2002) with great interest. I found it very helpful that you included the R code to replicate your analysis; however, I have had a problem replicating your example and wondered if you are able to give me a hint. When I use the code from the

Hello, R experts, I have a list called dataHP which has 30 elements (m1, m2, ..., m30). Each element is a 7x6 matrix holding yield data from two factors experimental design, with treatment in column, position in row. For instance, the element 20 is: dataHP[[20]] col1 col2 col3 trt1 trt2 trt3 [1,] 22.0 20.3 29.7 63.3 78.5 76.4 [2,]

I am confused whether Student's sleep data "show the effect of two soporific drugs" or Control against Treatment (one drug). The reason is the next: > require(stats) > data(sleep) > attach(sleep) > extra[group==1] numeric(0) > group [1] Ctl Ctl Ctl Ctl Ctl Ctl Ctl Ctl Ctl Ctl Trt Trt Trt Trt Trt Trt Trt Trt Trt [20] Trt Levels: Ctl Trt > sleep$group [1] 1 1 1 1 1

I am trying to define groupings from levels of factor variables and this the warning message that R give "& not meaningful for factors". The nature of my task is this. I have a variable stage which has the levels (1B, 2A, 2B) - these are the AJCC TNM stages of cancer, and another variable diameter with factor levels ("=< 4", "4 - 6.5, > 6.5; limit values are

Hi, I'm playing with moving some of my lattice graphics into ggplot2, and I'd like to ask how to achieve a couple of things, both of which are fully illustrated in self-contained code (and mostly minimal, although that left quite a bit) following this written description. 1. I quite often like to use a 'ghosted' reference across facets - for example, in my example program below,

Dear, I have a dataset with 4 subjects (see ID in example), and 4 treatment (see TRT in example) which are tested on 2 locations and in 3 blocs. By using Lattice dotplot, I made a graph that shows the raw data per location and per bloc. In that graph, I would like to have a reference line per bloc that refers to the first treatment (T1). However, I can not find how to do that. I can make

Hello, I probably have a syntax error in trying to generate an expected survival curve from a weighted cox model, but I can't see it. I used the help sample code to generate a weighted model, with the addition of a "weights=albumin" argument (I only chose albumin because it had no missing values, not because of any real relevance). Below are my code with the resulting error

First a statistical issue: The survfit routine will produce predicted survival curves for any requested combination of the covariates in the original model. This is not the same thing as an "adjusted" survival curve. Confusion on this is prevalent, however. True adjustment requires a population average over the confounding factors and is closely related to the standardized