Hi
I am using a partial proportional odds model (ordered) because the Brandt test showed that it violated the parallel lines assumption. However, I am having a hard time interpreting the output and writing the results section for a journal article. Would appreciate some assistance. For example, what does the following line mean?
- there are three categories of employment status so does "imposed" mean "not significant"?
- self efficacy not imposed so I can report that it does increase the likelihood of DV ie. a good sign?
Testing parallel lines assumption using the .01 level of significance...
Step 1: Constraints for parallel lines imposed for 2.Employment_Status (P Value = 0.9292)
(Note: there are 3 categories of employment status)
Step 41: Constraints for parallel lines are not imposed for
1.SelfEfficacy (P Value = 0.00122)
Wald test of parallel lines assumption for the final model:
( 1) [1]1.Employment_Status - [2]1.Employment_Status = 0
chi2( 40) = 37.58
Prob > chi2 = 0.5799
Financial_distress_~l | Coefficient Std. err. z P>|z| [95% conf. interval]
Employment_Status |
SelfEmployed | .1760828 .0916741 1.92 0.055 -.0035951 .3557607
PT | .0907362 .0753507 1.20 0.229 -.0569486 .2384209
Are there any articles showing how to report findings? My field typically reports B, SE and Exp(B) for Logistic regression methods so I am feeling lost. Thank you.
0 Response to Interpreting results using gologit2 and autofit features for Partial Proportional Odds Model
Post a Comment