Interpreting distal outcomes output (...
Message/Author
 lmay80 posted on Monday, January 07, 2019 - 3:00 am
Hi

I wondered if you could help. I ran an analysis using Lanza's method for distal variables and I'm struggling to interpret the output. I'm aware of how the odds ratios are computed from the probabilities but I'm unsure which odds ratios to extract.

In my analysis I have five drinking classes and am exploring a binary outcome (Y/N). The results include five categories per five classes (example for class 1 below). As there are five versions of these (four omitted from the post), which would you recommend I interpret?

What complicates the interpretation is that class 5 all categories within class 5 show OR=1.000, and I currently don't know how I will be able to obtain the odds for class 1.

EQUALITY TESTS OF MEANS/PROBABILITIES ACROSS CLASSES

Prob S.E. Odds Ratio S.E. 2.5% C.I. 97.5% C.I.

Class 1
Category 1 0.309 0.134 1.000 0.000 1.000 1.000

Category 2 0.142 0.061 1.482 0.563 0.703 3.122

Category 3 0.104 0.201 4.445 0.000 4.445 4.445

Category 4 0.111 0.272 11.819 0.000 11.819 11.819

Category 5 0.334 0.392 0.651 0.000 0.651 0.651
 Bengt O. Muthen posted on Monday, January 07, 2019 - 11:08 am
Perhaps this FAQ on our website is helpful:

Odds ratio interpretation for categorical distal outcomes using DCAT