My problem is I have data with both categorial and numerical data, currently only the categorical number contains missing data, was wondering do I make a new dataframe containing only the categorical columns?
How would you use Latent Class Model specifically poLCA to impute the missing data? http://www.sscnet.ucla.edu/polisci/faculty/lewis/pdf/poLCA-JSS-final.pdf The reason why I chose not to use Multiple Imputation(MI) is because according to [http://blogs.iq.harvard.edu/sss/archives/2008/09/a_handy_trick_f.shtml] "MI packages assume the Multivariate Normal Distribution which may not hold for certain types of categorical and binary data. Yucel Recai, Yulei He, and Alan Zaslavsky point out in their May 2008 article in The American Statistician, naive rounding MI imputations can bias estimates, particularly when the underlying data are asymmetric or multimodal." However instead of using Yucel Recai, Yulei He, and Alan Zaslavsky's rounding strategy [ http://amstat.tandfonline.com/doi/pdf/10.1198/000313008X300912] , I opted for the Latent Class Model: http://spitswww.uvt.nl/~vermunt/ginkel2007.pdf Who are the authors of the R package poLCA. Thanks Chris [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
