|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
Thresholds in a nominal model |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
Jon Heron posted on Tuesday, June 21, 2011 - 5:50 am
|
|
|
Apologies for such a simple question, but I have been banging my head against this for hours. When you fit an LCA to ordinal data, the resulting thresholds are logits and I can easily show the conversion to probabilities. When the manifest data are nominal the thresholds are different. I've tried all the conversions I can think of but cannot get back to probabilities - please can you put me out of my misery? many thanks, Jon |
|
Jon Heron posted on Tuesday, June 21, 2011 - 8:09 am
|
|
|
p444 of the user guide has come to my rescue. I'm sure that wasn't there earlier :-S |
|
Back to top |
|
|