Dear all,
I am using gologit2 on my imputed data (m=50, n=1359):
My dependent variable is ordinal and has 5 categories.
Followingly, I would like to use the overall p-values for the variables of the partial proportional odds models (in this example x1 x2 x3) as suggested by Williams (2016) Understanding and interpreting generalized ordered logit models , p.10; Table 2, footnote.
The literature further states to use
To be honest, I am rather clueless on how this mi syntax would look like and already tried to use the command (mi xeq:) test and also a foreach loop with mi xeq.
Any help is very much appreciated. Thank you in advance!
Johanna
I am using gologit2 on my imputed data (m=50, n=1359):
Code:
mi estimate: gologit2 dep.var x1-x6, difficult npl(x1 x2 x3)
Followingly, I would like to use the overall p-values for the variables of the partial proportional odds models (in this example x1 x2 x3) as suggested by Williams (2016) Understanding and interpreting generalized ordered logit models , p.10; Table 2, footnote.
The literature further states to use
a test of the joint significance of all coefficients for the variable that are in the model. (p.10)
Any help is very much appreciated. Thank you in advance!
Johanna
