BookmarkSubscribeRSS Feed
patriciav
Calcite | Level 5

Hello,

I'm trying to predict preterm birth (yes/no) from weight gain during pregnancy, controlling for race/ethnicity, bmi at entry to prenatal care, and parity (number of previous births). I've run a logistic regression with the following model statement:

preterm=wtgaincat ethnicity bmicat parity;

wtgaincat has 4 levels (ethnicity has 3, bmicat has 4)

In my output, the p-value for the Wald Chi-Square in Type 3 Analysis of Effects table is .0292 - so less than .05, so significant.

In the Maximum Likelihood parameter estimates table, the p-value for one of the levels of wtgaincat is .0130, so significant.

The OR is for that level of wtgaincat 0.332.

BUT the CI is   0.082 -1.345 - so not significant?

Are there some situations where the p-value for the ML estimate is better, and other situations where you'd favor the 95% CI around the OR????

I'm not sure what to think or to report. Any help would be much appreciated!

Thanks,

Patricia

8 REPLIES 8
ballardw
Super User

It would be helpful if you showed your code so we can avoid making suggestions already present in your model and the output as something else may be needed to answer the question.

Reeza
Super User

What does the rest of your code look like within proc logistic or genmod?

patriciav
Calcite | Level 5

Sorry, here is the proc, is that what you need? If more, I can paste that as well.

Thank you!

Patricia

 

proc logistic descending data=jain_ob7 ;

title1 'Assoc between wtgaincat and preterm';

title2 'Controlling for bmicat, ethnicity, parity';

class wtgaincat bmicat ethnicity;

model preterm=wtgaincat ethnicity bmicat parity;

format wtgaincat wtgaincatrevf.;

where bmicat>=3 and gaentry28=1;

run;

Reeza
Super User

Does that give you the odds ratio and CI by default?

patriciav
Calcite | Level 5

Yep.

Don't know if this will come through, but there is the relevant output.

"wtgaincat 0 above recommended" is the level that I'm talking about, that has conflicting p-value and OR CI.

Patricia

 


                                    Type 3 Analysis of Effects


                                                      Wald

                           Effect         DF    Chi-Square    Pr > ChiSq

                           wtgaincat       3        9.0083        0.0292

                           Ethnicity       2       12.8604        0.0016

                           bmicat          3        2.3003        0.5125

                           Parity          1        1.7427        0.1868



 

                             Analysis of Maximum Likelihood Estimates


                                                          Standard          Wald

     Parameter                          DF    Estimate       Error    Chi-Square    Pr > ChiSq

     Intercept                           1     -1.4628      0.3557       16.9141        <.0001

     wtgaincat 0 above recommended       1     -0.9070      0.3652        6.1689        0.0130

     wtgaincat 1 2 recommended           1      0.6497      0.3272        3.9432        0.0471

     wtgaincat 2 1 below recommended     1      0.0617      0.3884        0.0253        0.8737

     Ethnicity AA                        1      0.9401      0.3552        7.0041        0.0081

     Ethnicity H                         1     -0.9584      0.2920       10.7740        0.0010

     bmicat    30-35                     1     -0.0366      0.3246        0.0127        0.9102

     bmicat    35-40                     1     -0.4800      0.3837        1.5646        0.2110

     bmicat    40-45                     1      0.4624      0.3772        1.5025        0.2203

     Parity                              1     -0.2109      0.1598        1.7427        0.1868



 


                                        Odds Ratio Estimates

                                                              Point          95% Wald

         Effect                                            Estimate      Confidence Limits


         wtgaincat 0 above recommended   vs 3 0 wt loss       0.332       0.082       1.345

         wtgaincat 1 2 recommended       vs 3 0 wt loss       1.575       0.417       5.942

         wtgaincat 2 1 below recommended vs 3 0 wt loss       0.875       0.208       3.685

         Ethnicity AA vs White                                2.514       0.703       8.988

         Ethnicity H  vs White                                0.377       0.129       1.101

         bmicat    30-35 vs 45+                               0.913       0.266       3.140

         bmicat    35-40 vs 45+                               0.586       0.153       2.251

         bmicat    40-45 vs 45+                               1.504       0.396       5.717

         Parity                                               0.810       0.592       1.108

 

 


 


 


 


 


 


Reeza
Super User

patriciav wrote:

Sorry, here is the proc, is that what you need? If more, I can paste that as well.

Thank you!

Patricia

proc logistic descending data=jain_ob7 ;

title1 'Assoc between wtgaincat and preterm';

title2 'Controlling for bmicat, ethnicity, parity';

class wtgaincat bmicat ethnicity/param=ref;

model preterm=wtgaincat ethnicity bmicat parity;

format wtgaincat wtgaincatrevf.;

where bmicat>=3 and gaentry28=1;

run;

try adding the param=ref option (see above) as specified in this note:

36478 - The odds ratio for a confidence interval disagrees with the parameter p-value or confidence ...

patriciav
Calcite | Level 5

That is perfect, thank you so much!!!!

patriciav
Calcite | Level 5

Reeza, I can't figure out how to mark your response as correct, if this is important pls let me know and I'll do it.

Patricia

sas-innovate-2024.png

Today is the last day to save with the early bird rate! Register today for just $695 - $100 off the standard rate.

 

Plus, pre-conference courses and tutorials are filling up fast and are always a sellout. Register today to reserve your seat.

 

Register now!

What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 8 replies
  • 1614 views
  • 0 likes
  • 3 in conversation