[R-sig-ME] Power calculations for lmer mixed designs

Diana Michl dmichl at uni-potsdam.de
Mon Jun 19 15:06:58 CEST 2017


Dear List,

I want to do a power calculation on a mixed model as described here by 
Ben Bolker: https://rpubs.com/bbolker/11703

However, there are three things I can't figure out:

- The qlogis function, I don't get what it does exactly and what to 
enter instead of 0.7 as in the example

|beta <- c(qlogis(0.7), -0.2)|

- What exactly the resulting graphs mean, both here and in my own 
example. What does the read bar at -0.2 tell me? Is there a way to give 
power as a number between 0 and 1?
- How to do this for more than 1 treatment (my attempts to do it for 4 
all failed, I seem to miss places in the exampe I need to change. For 
example, I tried adding values to the beta-qlogis line above and others, 
but it gave errors)

Thanks very much for any input!


Diana

-- 
Diana Michl, M.A.
PhD candidate
International Experimental
and Clinical Linguistics
Universität Potsdam
www.ling.uni-potsdam.de/staff/dmichl
www.duoinfernale.eu


	[[alternative HTML version deleted]]



More information about the R-sig-mixed-models mailing list