I am new to using R. Currently, I am using the logistf package to run logistic regression analysis. When I run the following line of code: attach(snpriskdata) logisticpaper<-logistf(sascasecon~saspackyrs+newsbmi+EDUCATION+sasagedx+sasflung+condobst+sasadultasprev) I get the following error message: Error in sum(y) : invalid 'type' (character) of argument What does this error message mean? All of my variables are in numeric format. Thank you for your input. Alison Van Dyke Wayne State University
logistf error message
3 messages · Van Dyke, Alison, Frank E Harrell Jr
7 days later
I'm new to R and to validation of logistic regression models via bootstrapping. I see that there are various approaches to bootstrapping, and I am wondering (1) which approach would be best for internal validation of predictive discrimination, (2) are there any good resources that could be recommended to explain the optimal approach, and (3) what packages in R should I use to achieve this approach. Many thanks for the input. Alison Van Dyke MD/PhD Candidate, Class of 2011 Cancer Biology Wayne State University avandyk at med.wayne.edu
Van Dyke, Alison wrote:
I'm new to R and to validation of logistic regression models via bootstrapping. I see that there are various approaches to bootstrapping, and I am wondering (1) which approach would be best for internal validation of predictive discrimination, (2) are there any good resources that could be recommended to explain the optimal approach, and (3) what packages in R should I use to achieve this approach. Many thanks for the input. Alison Van Dyke MD/PhD Candidate, Class of 2011 Cancer Biology Wayne State University avandyk at med.wayne.edu
One possibility: library(Design) ?validate.lrm
Frank E Harrell Jr Professor and Chair School of Medicine
Department of Biostatistics Vanderbilt University