I am currently trying to figure out how to calculate statistical power of models and estimates in a linear mixed model with two levels using REML. There is no guidance in MLwin on this topic, is there any literature or advice anyone can direct me towards.
Cheers
Steve
Statistical power of mixed models
Re: Statistical power of mixed models
MLPowSim may be what you're looking for. There is information about it on the CMM website (http://www.cmm.bristol.ac.uk/learning-t ... l#mlpowsim) and more extensive information and the download on Bill Browne's website (http://seis.bris.ac.uk/~frwjb/esrc.html).
I haven't used it myself, but I've had a look at the manual in the past and it looks very flexible in the kinds of models it can provide power calculations for and the kinds of specifications you can make about your sample.
I haven't used it myself, but I've had a look at the manual in the past and it looks very flexible in the kinds of models it can provide power calculations for and the kinds of specifications you can make about your sample.