similar to: manipulating multiply imputed data sets

I'm stumbling my way through manipulating data in multiply imputed datasets, and have run into a problem translating code I used to run on my pre-imputed dataset to multiple datasets. The imputation runs just fine, as does the reading of the mi data sets into an imputationList. I run into trouble, though, when I try to construct a scale across all the data sets. Is there a simple way to do

Can someone help me understand this results? > levels(as.factor(miset1$facts_convict)) [1] "1" "1" "2" "3" "4" "5" "6" converting to numeric and back doesn't seem to help: > levels(as.factor(as.numeric(miset1$facts_convict))) [1] "1" "1" "2" "3" "4" "5"

R-users & helpers: I am using Amelia, mitools and cmprsk to fit cumulative incidence curves to multiply imputed datasets. The error message that I get "Error in eval(expr, envir, enclos) : invalid 'envir' argument" occurs when I try to fit models to the 50 imputed datasets using the "with.imputationList" function of mitools. The problem seems to occur

I'm importing a lot of text tables of data (from Latent Gold) that includes hashes in some of the column names ("Cluster#1", "Cluster#2", etc.). Is there an easy way to strip the offending hashes out before pushing the text into a table or data frame? I thought I'd use gsub, e.g., but can't figure out how to read in a text file without reading it into a table or

Hi folks, I'm just learning how to use maps. As an initial foray, I'm mapping the states that have "duty to retreat" (blue) and "stand your ground" (red) self-defense standards. Here is my extremely naive script: dtr <- c('alabama', 'arizona', 'conneticut', 'delaware', 'dist of columbia' , 'hawaii',

This is a simple problem that has stumped me: I'm trying to loop through a few dozen variable names in graphs. I've tried various approaches like this: attach(mydata) ivs <- c("oneiv", "anotheriv", "yetanotheriv") dvs <- c("onedv", "anotherdv", "yetanotherdv") for (iv in ivs) { for (dv in dvs) { graphname <- paste(iv,

# I've tried to make this easy to paste into R, though it's probably so simple you won't need to. # I have some data (there are many more variables, but this is a reasonable approximation of it) # here's a fabricated data frame that is similar in form to mine: my.df <- data.frame(replicate(10, round(rnorm(100, mean=3.5, sd=1)))) var.list <- c("dv1",

R-helpers: I am using R 2.5 on Windows XP, packages all up to date. I have run into an issue with the MIcombine function of the mitools package that I hoped some of you might be able to help with. I will work through a reproducible example to demonstrate the issue. First, make a dataset from the pbc dataset in the survival package --------------- # Make a dataset library(survival) d <-

Hey there I am estimating a multilevel model using lmer. I have 5 imputed datasets so I am using mitools to pool the estimates from the 5 > > datasets. Everything seems to work until I try to use > MIcombine to produced pooled estimates. Does anyone have any suggestions? The betas and the standard errors were extracted with no problem so everything seems to work smoothly up until

Hi all, I am hardly an expert, so I expect that this code is not the easiest/ most efficient way of getting where I want. Any suggestions in that direction would also be helpful. I am working on panel analysis with five imputed datasets, generated by Amelia. To do panel analysis, it seemed that the plm package was the best, providing a convenient wrapper for fixed and random effects

Hi, When I include a categorical variable (RACE with 3 levels - "white", "black" and "other") in my logistic regression model, the correlation matrix of the coefficients gets messed up. I get something like: ----------------------------------------- Correlation of Coefficients: ( A L RACEb AGE , 1 LWT , 1 RACEblack 1

Hi, I'm using geeglm function to account for the repeated measure. fit1<- geeglm( binary.outcome ~ age + race + gender + fever.yes.no, data=mydata, id=ID, family=binomial, corstr="exchangeable") summary(fit1)$coef gives too large estimates and standard deviation: Estimate Std.err Wald Pr(>|W|) (Intercept) 3.07e+16

Hope some can help me. I have a PSTN coming into TDM400 into Asterisk. We also have direct telephones connected to the PSTN bypassing the Asterisk. When a call comes in on the PSTN the direct connected phones ring first and if no one picks up , Asterisk picks and get routed to internal sip phones. I am not able to find what I should tune to make the calls always go through asterisk without the

I have a PSTN line coming into FXO port 4 on a TDM400P. Incoming calls are not being picked up. I don't find anything unusual in asterisk log. I am clueless where I should look. I also find zapata-additional.conf empty. The trouble started when the system was accidentally shut down and rebooted. Any help ? How do I diagnose if the TDM400P is not fried ? Thanks, -braman

As an alternative to Latent GOLD, I'm wondering if anyone knows of and R package that can manage Latent Class Analysis with mixed variable types (continuous, ordinal, and nominal/binary). [[alternative HTML version deleted]]

Hello, I am looking at the job satisfaction data below, from a problem in Agresti's book, and I am not sure where the degrees of freedom come from. The way I am fitting a binomial model, I have 168 observations, so in my understanding that should also be the number of fitted parameters in the saturated model. Since I have one intercept parameter, I was thinking to get 167 df for the Null

I'm coming from the AMOS world and am wondering if there is a simple way to do multiple hypothesis testing in the manner of BIC analyses in AMOS using the sem package in R. I've read the documentation, but don't see anything in there except for basic BIC scores. Perhaps someone has devised a simple way to compare the relative likelihood of all possible path-fittings within a

I've been playing around with various table tools, trying to construct a fairly simple cross-tab. It shouldn't be hard, but for some reason it turning out to be (for me). If I want to see how many men and how many women agree with a agree/disagree question (coded 1,0), I can do this: >attach(mydata) >mytable <- table(male, q1.bin) # gender and a binary response variable

Hi, I'm new to R and using it for Cox survival analysis. Thanks to this great forum I learned how to compute the HR with its confidence interval. My question would be: Is there any way to get the p-value for a hazard ratio in addition to the confidence interval? Thanks, Thierry -- Thierry Panje Visiting Student Researcher Department of Psychology Stanford

# I'm new to R and am trying to get the hang of how it handles # dataframes & loops. If anyone can help me with some simple tasks, # I'd be much obliged. # First, i'd like to generate some random data in a dataframe # to efficiently illustrate what I'm up to. # let's say I have six variables as listed below (I really # have hundreds, but a few will illustrate the point). #