Message-ID: <CACk-te2-YbFC6dF36w2eioAjnOq6KAAkbcyaQatyWtkwFYEG_g@mail.gmail.com>
Date: 2013-11-29T15:58:49Z
From: Bert Gunter
Subject: Lasso function that can handle NA values
In-Reply-To: <50C6EDB5-3AAF-416D-801D-36A47D1E1F41@gmail.com>
?na.omit
??
But it is certainly true that omitting missing values first and
analyzing the remaining data can:
1. Leave you with no data to analyze
2. Result in biased and misleading conclusions if the missingness
mechanism is related to the covariates.
In general, handling data with missing values properly can be a very
difficult or even insoluble problem. You may wish to consult with a
local statistician knowledgeable in such matters (I am not, for
example).
Cheers,
Bert
On Fri, Nov 29, 2013 at 6:12 AM, Laura Buzdugan <laubuzdugan at gmail.com> wrote:
> Hi everyone,
>
> I have a large dataset with missing values. I tried using glmnet, but it seems that it cannot handle NA values in the design matrix. I also tried lars, but I get an error too. Does anyone know of any package for computing the lasso solution which handles NA values?
> ______________________________________________
> R-help at 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.
--
Bert Gunter
Genentech Nonclinical Biostatistics
(650) 467-7374