cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Register for our Discovery Summit 2024 conference, Oct. 21-24, where you’ll learn, connect, and be inspired.
Choose Language Hide Translation Bar
CowDoc
Level I

Full parameter estimates in mixed model

I am running a mixed model for a continuous outcome using JMP Pro 17. In the output for the fixed effects parameter estimates, I have a 5-class categorical disease and the report shows the result for 4 of the 5 levels. How do I get or derive the Std Error for the parameter that is not displayed in the output report? (see the last row in the output copied and pasted below)

Fixed Effects Parameter Estimates       
        
TermEstimateStd ErrorDFDent RatioProb>|t|95% Lower95% Upper
Intercept1022.568168.9938296.66.05<.0001689.98841355.147
305MEp0.3202140.00654110510748.95<.00010.3073930.333034
PrevLgp[1]-124.38513.32405102630-9.34<.0001-150.5-98.2698
PrevLgp[2]99.008214.12753904417.01<.000171.31838126.698
PrevLgp[3]153.981415.93062948379.67<.0001122.7575185.2052
PrevLgp[4]81.0656922.153441009703.660.000337.64522124.4862
PrevLgp_5+       
1 ACCEPTED SOLUTION

Accepted Solutions
CowDoc
Level I

Re: Full parameter estimates in mixed model

OK - I figured out a work around. In order to get the missing details, I changed the ordering of the categorical variables and then reran the model. Now, I can copy in the previously missing line because the referent population has changed.

View solution in original post

3 REPLIES 3
statman
Super User

Re: Full parameter estimates in mixed model

Possibly see here:

https://www.jmp.com/support/help/en/18.0/?os=mac&source=application#page/jmp/expanded-estimates.shtm...

 

"All models are wrong, some are useful" G.E.P. Box
CowDoc
Level I

Re: Full parameter estimates in mixed model

Yes, I use the Expanded Estimates report when I run least sq means models/ANOVA but I don't think it is an option within the mixed models section. I am running a mixed model with 2 variables listed as random effects and others listed as fixed effects. However, I can't figure out how to get the std error/confidence interval for the unreported category.

CowDoc
Level I

Re: Full parameter estimates in mixed model

OK - I figured out a work around. In order to get the missing details, I changed the ordering of the categorical variables and then reran the model. Now, I can copy in the previously missing line because the referent population has changed.