GAMLj-Logistic Mixed Effects Regression PSE/Threshold values

Discuss statistics related things
Post Reply
tutkuoztel
Posts: 17
Joined: Mon Apr 22, 2019 11:57 am

GAMLj-Logistic Mixed Effects Regression PSE/Threshold values

Post by tutkuoztel »

hello,

I'm trying to calculate the point of subjective equality (PSE)/threshold value (i.e., the x axis value for the p = 0.5) of the logistic mixed effects function fits. to do this, I take the inverse of the logistic regression function p(which should be equated to 0.5) = 1/1+e^-(ß0+ß1X), and isolate X which brings X = -ß0/ß1. however, when I calculate X with this formula and check the result from the graphs, the obtained values from the formula and the graph do not seem to match. I suspect that this discrepancy is a result of implementation differences between the standard logistic regression versus the logistic mixed effects regression.

any suggestions for such a calculation for logistic mixed effects?

thanks so much in advance, tutku
User avatar
mcfanda@gmail.com
Posts: 452
Joined: Thu Mar 23, 2017 9:24 pm

Re: GAMLj-Logistic Mixed Effects Regression PSE/Threshold va

Post by mcfanda@gmail.com »

Hi
I've run a couple of tests and the PSE derived from the results seems ok. Would you share an example (.omv file) in which the results look odd?
Post Reply