Reproducibility of imputations

Welcome to the forum for REALCOM users. Feel free to post your question about REALCOM here. The Centre for Multilevel Modelling take no responsibility for the accuracy of these posts, we are unable to monitor them closely. Do go ahead and post your question and thank you in advance if you find the time to post any answers!

Go REALCOM (Developing multilevel models for REAListically COMplex social science data) >> http://www.bristol.ac.uk/cmm/software/realcom/
Post Reply
BrennanK
Posts: 2
Joined: Wed Oct 09, 2013 1:40 pm

Reproducibility of imputations

Post by BrennanK »

Hi,

I'm using Realcom Impute for a research project I'm working on (using the realcomImpute command from Stata), and was wondering about the reproducibility of the imputations.

If I run Realcom on the same dataset twice, will the imputations be the same for both? If not, is there a way to set a seed so that the imputations are the same regardless of when/where Realcom is run?

Many thanks,
Brennan
ChrisCharlton
Posts: 1351
Joined: Mon Oct 19, 2009 10:34 am

Re: Reproducibility of imputations

Post by ChrisCharlton »

Realcom-Impute does not have a way of setting a random number seed however according to http://www.mathworks.co.uk/help/matlab/ ... artup.html Matlab, which Realcom-Impute is written in, will always have the same random number state after it is started up. This means that if you do exactly the same sequence of operations in two instances of Realcom-Impute you should get the same results.
BrennanK
Posts: 2
Joined: Wed Oct 09, 2013 1:40 pm

Re: Reproducibility of imputations

Post by BrennanK »

Thanks Chris, much appreciated.
Post Reply