Re: [Gretl-users] Multiple Imputation analysis
Nathan Paxton schrieb:
I don't need to use gretl to do the actual MI, but I wonder if there's
any facility in gretl for doing analysis on separate MI-generated
datasets and then combining the results according to the Rubin rules.
That is, can gretl be told easily to run a procedure m times for the m
existing datasets and then combine the results to get 1 parameter estimate?
Hi Nathan,
opening datasets (the 'open' command) is not allowed in loops (yet?).
Would it be feasible for you to somehow combine the data into one gretl
dataset, or is this part of the problem?
A workaround I could imagine is to work with matrices; that is, store
the different datasets in simple ASCII matrix files as explained in the
help for mread() and mwrite(). It is possible to load those matrices in
a loop, and it is usually fairly easy to convert them to regular
datasets once they're loaded.
HTH,
sven