Using mutiply imputed data in NLME
On Tue, 1 Mar 2005, Shige Song wrote:
For example Will NLME work with mitools written by Thomas Lumley?
Yes, but since the coefficients are not just returned by the coef() function you will need to use the full MIextract/MIcombine approach rather than the shortcut of just using MIcombine() on the list of models. -thomas
Shige On Mon, 28 Feb 2005 13:02:54 -0500, Doran, Harold <HDoran at air.org> wrote:
Well, I may be missing something but why don't you call each dataframe from within a loop and save the results in a new data frame each time? -----Original Message----- From: r-help-bounces at stat.math.ethz.ch [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Shige Song Sent: Monday, February 28, 2005 12:18 PM To: R-help at stat.math.ethz.ch Subject: [R] Using mutiply imputed data in NLME Dear All, I am doing a growth modeling using NLME. I have three levels in my data: observation, individual, household. About half of my total sample have missing values in my household-level covariates. Under this situation, the best way to go is probably to multiply impute the data (for, say, 5 times), estimate the same model separately on each model using LME function, and merge the results. My question is: given the multiply imputed data sets have already been generated, is there a simple way to automate the process of estimating the mixed model and merging the results? HLM has similar features... Thanks! Best, Shige
______________________________________________ R-help at stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
______________________________________________ R-help at stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Thomas Lumley Assoc. Professor, Biostatistics tlumley at u.washington.edu University of Washington, Seattle