Proportional and Non-Proportional Odd... PreviousNext
Mplus Discussion > Categorical Data Modeling >
Message/Author
 Darrin Aase posted on Wednesday, August 05, 2009 - 8:44 am
I've searched the discussion board and not found any posts on this in a couple of years. First, is there an example of testing the proporitonal odds assumption in MPlus for an ordinal outcome, specifically with longitudinal data? Second, is there yet a way to estimate a non-proportional odds model?

Thanks,
Darrin
 Bengt O. Muthen posted on Wednesday, August 05, 2009 - 1:09 pm
No direct test of this in Mplus yet. Non-proportional odds model is on the to-do list.
 Salmi Md Zahid posted on Tuesday, February 13, 2018 - 12:53 am
Im a beginner user of MPLUS. I would like to know if we can run analysis for Partial proportional Odds Model using latest version of MPLUS? Im not so sure which chapter i should refer to..
 Tihomir Asparouhov posted on Wednesday, February 14, 2018 - 4:52 pm
Mplus implements the Brant test.

Take a look at

http://www.jstor.org/stable/2532457?seq=1#page_scan_tab_contents

https://books.google.dk/books?id=CHvSWpAyhdIC&pg=PA143&lpg=PA143&dq=Brant+test&source=bl&ots=WiIkYPB8kK&sig=_BLIzXuR_5JqyRYXKa9PPZK77xE&hl=da&sa=X&ei=vr-nUYixC87Kswar5YGYCQ#v=onepage&q=Brant%20test&f=false

http://www.stata-journal.com/sjpdf.html?articlenum=st0097

There are two ways of doing the model:

1. As a series of binary regressions (see Brant's paper)

2. The full model involves this
Say U =0,1,2 –> create dummy out of the three categories D1 D2
if you have
U on X
you will have to change the model to
U on X, XD1, XD2
If you have q X variables you will have instead 3q X variables.
Before proceeding further you should make sure that you understand the intricacies of the full model and why it doesn't guarantee P>0 as virtually all other models do.
 Salmi Md Zahid posted on Sunday, March 04, 2018 - 8:04 pm
Thank you for your response & guide. I already read the materials (2 of them) and understand on the concept of Brant test, also already run simple ordered logistic and look into the result of Brant test.

But is it means that MPLUS not able to generate the coefficients for partial proportional simultaneously? is it generate a series of binary logistic is the only option? Im not so clear on the second option given above.

because actually im planning to fit a multilevel model for ordinal response as my main model. is it possible to do this using MPLUS?

Thanks in advance.
 Tihomir Asparouhov posted on Monday, March 05, 2018 - 1:51 pm
First to clarify - there is an error in my earlier post. Method 2 above doesn't work. Here is what you can do in Mplus.

Method 1: using the binary regressions. The method works ok and would produce consistent estimates. Here is a sample code that assumes 1 covariate and a categorical variable U that has 3 categories: 0,1,2

variable: names are x u;
usevar are x u1 u2;
categorical=u1 u2;
define: if (u==0) then u1=0 else u1=1;
if (u<=1) then u2=0 else u2=1;
model: u1-u2 on x;
analysis: link=logit; estimator=ml;
data: file=1.dat;

Method 2: The full non-proportional model is possible in Mplus using the constraint command User's Guide example 5.23 features that option. The sample code for the non-proportional model would be as follows

variable: names are x u;
categorical=u;
constraint=x;
model: u on x; [u$2] (t2);
model constraints: new(a b); t2=a-b*x;
analysis: link=logit; estimator=ml;
data: file=1.dat;

Method 1 can be used for two-level models but Method 2 can not be used for two-level models because the constraint option is not available for two-level models. You can use Method 2 with type=complex to account for non-independence of the observations across clusters.
 Salmi Md Zahid posted on Sunday, March 18, 2018 - 11:56 pm
I try it based on your suggestion (Method 1):
My DV is ordinal with 5 categories, and i test it on single IV(gender). i recode my DV as 1 to 5.

Below is my input instructions:
DATA: FILE IS XXX.dat;
VARIABLE: NAMES ARE x u;
usevar are x u1 u2 u3 u4;
CATEGORICAL IS u1 u2 u3 u4;
DEFINE: if (u==1) then u1=0 else u1=1;
if (u<=2)then u2=0 else u2=1;
if (u<=3) then u3=0 else u3=1;
if (u<=4) then u4=0 else u4=1;
ANALYSIS: link=logit; ESTIMATOR = ML;
MODEL: u1-u4 ON x

I manage to get the result but i noticed that it define the u1-u4 wrongly (the proportions for each u's are totally wrong).Could you help me to identify where's the mistake with the command?

Thank you.
Salmi
 Bengt O. Muthen posted on Monday, March 19, 2018 - 3:32 pm
Send your output to Support along with your license number.
 Salmi Md Zahid posted on Tuesday, March 27, 2018 - 10:28 pm
Dear Mr. Muthen,

Sorry for late reply. I successfully solve the problem above. Im using Demo version now but already in the process to purchase the software. In the meantime, i have another two questions as follows:

1) is there any difference in the command for different type of independent variable; e.g.continuous vs categorical.

2) This is my input to get Brant Wald test for univariate ordinal logistic:

TITLE: Univariate Partial Proportional Odds - student gender;
DATA: FILE IS G:\PhD2015\TIMSS2015\Malaysia2015\UnivariatePPO-MPLUS\Gender.dat;
VARIABLE: NAMES ARE x u;
CATEGORICAL IS u;
MISSING ARE ALL (9);
ANALYSIS: link=logit; ESTIMATOR = ML;
MODEL: u ON x

Descriptive seems okay but the result on Brant Test seems wrong as follows:

BRANT WALD TEST FOR PROPORTIONAL ODDS

Degrees of
Chi-Square Freedom P-Value

U
Overall test 0.000 3 1.000
X 0.000 3 1.000

Where is the problem actually?

Thank you.
Salmi
 Bengt O. Muthen posted on Wednesday, March 28, 2018 - 11:55 am
You need a continuous x to use this test.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: