Dear, My dataset consists out of 5 imputed files (that I did not imputed myself). Is was wondering what is the best way to analyse them in R. I am aware that packages to perform multiple imputation (like Mice & Amelia) exist, but they are used to perform MI. As my data is already imputed, I would like to know how I can split it and how I should obtain pooled regression results. If I can use the existing MI packages, how should I define my imputation variable? Kind regards, -- View this message in context: http://r.789695.n4.nabble.com/multiple-imputed-files-tp4702289.html Sent from the R help mailing list archive at Nabble.com.
Hi,
I think you want the {mitools} package.
http://cran.r-project.org/web/packages/mitools/mitools.pdf. Anthony
Damico's site, asdfree.com, has a lot of good code examples using various
government datasets.
Nate
On Mon, Jan 26, 2015 at 5:23 AM, hnlki <annelies.hoebeeck at ugent.be>
wrote:
> Dear,
>
> My dataset consists out of 5 imputed files (that I did not imputed myself).
> Is was wondering what is the best way to analyse them in R. I am aware that
> packages to perform multiple imputation (like Mice & Amelia) exist, but
> they
> are used to perform MI. As my data is already imputed, I would like to know
> how I can split it and how I should obtain pooled regression results. If I
> can use the existing MI packages, how should I define my imputation
> variable?
>
> Kind regards,
>
>
>
>
> --
> View this message in context:
> http://r.789695.n4.nabble.com/multiple-imputed-files-tp4702289.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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.
>
[[alternative HTML version deleted]]
hi nate and annelies, the survey of consumer finances and consumer expenditure survey folders both have examples of how to run a glm on multiply-imputed survey data.. but these examples are specifically for complex sample survey data, which might not be what you're working with. :) https://github.com/ajdamico/usgsd/search?utf8=%E2%9C%93&q=svyglm On Mon, Jan 26, 2015 at 10:30 AM, N F <arjunamusic at gmail.com> wrote:> Hi, > I think you want the {mitools} package. > http://cran.r-project.org/web/packages/mitools/mitools.pdf. Anthony > Damico's site, asdfree.com, has a lot of good code examples using various > government datasets. > > Nate > > On Mon, Jan 26, 2015 at 5:23 AM, hnlki <annelies.hoebeeck at ugent.be> wrote: > > > Dear, > > > > My dataset consists out of 5 imputed files (that I did not imputed > myself). > > Is was wondering what is the best way to analyse them in R. I am aware > that > > packages to perform multiple imputation (like Mice & Amelia) exist, but > > they > > are used to perform MI. As my data is already imputed, I would like to > know > > how I can split it and how I should obtain pooled regression results. If > I > > can use the existing MI packages, how should I define my imputation > > variable? > > > > Kind regards, > > > > > > > > > > -- > > View this message in context: > > http://r.789695.n4.nabble.com/multiple-imputed-files-tp4702289.html > > Sent from the R help mailing list archive at Nabble.com. > > > > ______________________________________________ > > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > > 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. > > > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > 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. >[[alternative HTML version deleted]]
Thank you for your answers. In fact I am using the HFCS dataset, but I need 3-SLS and SUR. Does the code work with system.fit as well? My 5 imputed files are stacked together in one dataset. In order to use <imputationList> (mitools) I need several imputed datasets. Does that mean that I have to split my dataset first, in order to create the imputationList? -- View this message in context: http://r.789695.n4.nabble.com/multiple-imputed-files-tp4702289p4702321.html Sent from the R help mailing list archive at Nabble.com.