cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Check out the JMP® Marketplace featured Capability Explorer add-in
Choose Language Hide Translation Bar
GregPeq
Level II

JMP Odds Ratio Calculations Don't Match Mine

I'm new to JMP (version 16.1). I'm running a binomial logisitic regression model. I have the model output set to include parameter estimates and odds ratios. When I take the logodds from the parameter estimates and exponentiate them in Excel in order to obtain the odds ratios, they don't match the odds ratio output in JMP.

 

My parameter estimates shows that confidence limits are Wald based, and under Odds Ratios it says that tests and confidence intervals are Wald based as well. 

 

Does anyone have any insight as to why my calculations differ from JMPs? How does JMP calculate the odds ratios?

 

Example:

JMP Output:

TermEstimateStd ErrorChiSquareProb>ChiSqLower 95%Upper 95%
Intercept2.4606561.5708632.450.1172-0.618185.539491
Age-0.032870.0215372.330.127-0.075080.009342
Sex[Female]-0.052660.2346920.050.8225-0.512650.407328
BMI-0.06740.0420162.570.1087-0.149750.014951
Speed-0.018830.0176971.130.2874-0.053510.015859
Restraint All[None]-0.436130.2694352.620.1055-0.964220.09195

 

My Odds Ratio Calculations: 

TermEstimateOdds Ratio
Intercept2.46065611.71249
Age-0.032870.967665
Sex[Female]-0.052660.948703
BMI-0.06740.934823
Speed-0.018830.98135
Restraint All[None]-0.436130.646532

 

JMP's Odds Ratios

Unit Odds Ratios    
TermOdds RatioLower 95%Upper 95%Reciprocal
Age0.9676650.9276691.0093861.033415
BMI0.9348230.8609251.0150631.069722
Speed0.981350.9478961.0159851.019004

 

Range Odds Ratios    
TermOdds RatioLower 95%Upper 95%Reciprocal
Age0.2354520.0367521.5084094.247151
BMI0.0736580.0030421.78354113.57625
Speed0.1837220.0080994.1674365.443015

 

Odds Ratios for Sex     
Level1/Level2Odds RatioProb>ChisqLower 95%Upper 95%
MaleFemale1.1110640.82250.4427912.787911
FemaleMale0.9000380.82250.3586922.2584

 

Odds Ratios for Restraint All     
Level1/Level2Odds RatioProb>ChisqLower 95%Upper 95%
SeatbeltNone2.3923250.10550.8320196.878711
NoneSeatbelt0.4180040.10550.1453761.201896

 

 

Thanks in advance!

1 ACCEPTED SOLUTION

Accepted Solutions
ron_horne
Super User (Alumni)

Re: JMP Odds Ratio Calculations Don't Match Mine

Hi @GregPeq ,

the odds ratio table is the easiest and guaranteed way to get the correct contrasts between the categories.

the reason your calculation looks incorrect is that you have been using the "Nominal" scale for the categorical. if you use "Ordinal" you would get the exact same value as in the contrasts table. this is due to the fact that when nominal values are used JMP estimates the coefficients as difference from a non weighted average category. this makes much more sense when there are many categories. when a variable is ordinal, coefficients are estimated as the difference from the previous category.

for further information about categorical variables definitions you can follow this discussion from the past:

 

 

Let us know if it works for you,

Ron

 

View solution in original post

4 REPLIES 4
ron_horne
Super User (Alumni)

Re: JMP Odds Ratio Calculations Don't Match Mine

Hi @GregPeq ,

the odds ratio table is the easiest and guaranteed way to get the correct contrasts between the categories.

the reason your calculation looks incorrect is that you have been using the "Nominal" scale for the categorical. if you use "Ordinal" you would get the exact same value as in the contrasts table. this is due to the fact that when nominal values are used JMP estimates the coefficients as difference from a non weighted average category. this makes much more sense when there are many categories. when a variable is ordinal, coefficients are estimated as the difference from the previous category.

for further information about categorical variables definitions you can follow this discussion from the past:

 

 

Let us know if it works for you,

Ron

 

GregPeq
Level II

Re: JMP Odds Ratio Calculations Don't Match Mine

Thanks for your reply, @ron_horne . 

My response variable is binomial. Are you saying that I should assign an ordinal modeling type to this variable in JMP, and reserve the nominal modeling type for multinomial (non-ordinal) variables? Wouldn't this cause JMP to run an ordinal logistic regression rather than a binomial logistic regression?

 

Thanks,

Greg

ron_horne
Super User (Alumni)

Re: JMP Odds Ratio Calculations Don't Match Mine

Hi @GregPeq ,

no, just define Sex and Restraint All as ordinal and perform the same calculation (including your own odd ratios) this should bring you to the same as JMP odds ratios.

ron

 

GregPeq
Level II

Re: JMP Odds Ratio Calculations Don't Match Mine

@ron_horne, you are a gentleman and a scholar. This worked like a charm!

 

Thanks for your help,

Greg