0

My nominal GEE's, with the DV having three groups, produced the following output:

                           NominalGEE Regression Results                           
===================================================================================
Dep. Variable:                        task   No. Observations:                  112
Model:                          NominalGEE   No. clusters:                        2
Method:                        Generalized   Min. cluster size:                  44
                      Estimating Equations   Max. cluster size:                  68
Family:                       _Multinomial   Mean cluster size:                56.0
Dependence structure:         Independence   Num. iterations:                    31
Date:                     Tue, 22 Nov 2016   Scale:                           1.000
Covariance type:                    robust   Time:                         16:14:50
==============================================================================
                 coef    std err          z      P>|z|      [95.0% Conf. Int.]
------------------------------------------------------------------------------
HF[1.0]        0.9400      0.436      2.156      0.031         0.085     1.794
LFHF[1.0]     -0.6134      0.082     -7.454      0.000        -0.775    -0.452
SDNN[1.0]      0.6610      0.053     12.477      0.000         0.557     0.765
pNN50[1.0]    -1.2769      0.045    -28.094      0.000        -1.366    -1.188
HF[3.0]        1.1308      0.019     59.228      0.000         1.093     1.168
LFHF[3.0]      0.5117      0.050     10.233      0.000         0.414     0.610
SDNN[3.0]     -0.4080      0.223     -1.826      0.068        -0.846     0.030
pNN50[3.0]    -0.1943      0.386     -0.503      0.615        -0.952     0.563
==============================================================================
Skew:                          0.4459   Kurtosis:                      -1.1039
Centered skew:                 0.4320   Centered kurtosis:             -1.0652
==============================================================================

If I understood correctly, the nominal GEE uses one group as reference group, and then calculates the IVs' coefficients for the two other groups (group 1.0 and group 3.0 in this case). The coefficients depict a change in logged odds, given the value of the IVs. In other words, with the coefficients you calculate the chance of belonging to a particular group, as opposed to the reference group.

However, is it possible to infer the odds/chance to belong to group 1.0 as opposed to group 3.0 from this graph? Or do I have to perform a new GEE with a different reference group?

Robin Kramer
  • 579
  • 2
  • 5
  • 14
  • You have to do another model with a different reference group. I just noticed that you only have 2 clusters (i.e. only 2 different levels of the clustering variable used in the GEE model). If this is correct, you shouldn't use a GEE model at all. It is often recommended that you have at least 50 clusters. Perhaps you can just include the clustering variable as another independent variable instead? – JonB Nov 23 '16 at 08:49
  • Hi @JonB, thanks for the answer. I indeed only have two clusters (participants) in my pilot study. I first wanted to do a Friedman Chi-2 test, where I found main effects, but I wasn't able to perform post-hoc testing (http://stats.stackexchange.com/questions/246719/friedman-test-and-post-hoc-test-for-python). Could you suggest another test where I can compare the different levels of the DV? Nb. the Friedman question is about a different (ordinal) set of data, but the idea is the same I guess) – Robin Kramer Nov 23 '16 at 09:15
  • 1
    You can perhaps do a multinomial logistic regression? – JonB Nov 23 '16 at 09:25
  • @JonB thank you, it seems to be a lot easier. Final question, is the multinomial regression also fit for ordinal data? – Robin Kramer Nov 23 '16 at 10:08
  • Just found the answer to my own question. You lose order of the ordinal variable with a multinomial regression (http://www.theanalysisfactor.com/logistic-regression-models-for-multinomial-and-ordinal-variables/). An ordered logistic regression, however, has not yet been implemented in Python (https://github.com/statsmodels/statsmodels/issues/807). Only available Python alternative is the GEEOrdinal. – Robin Kramer Nov 23 '16 at 10:19
  • Ok, then you can try R. I learned it pretty quickly with no previous programming experience at all. – JonB Nov 23 '16 at 11:18
  • The polr() function in thr MASS package will do ordinal logistic regression. – JonB Nov 23 '16 at 11:58
  • I deliberately moved away from R for the current project, because I found data handling in Python easier (the DataFrame functions were more intuitive to me than `R`s data.frame). But I think I may be going back to R indeed. Thank you so much for all the help :) – Robin Kramer Nov 23 '16 at 12:01
  • Interesting! I'm considering learning Python for the same reason, but with the idea to still use R for analysis. – JonB Nov 23 '16 at 12:23
  • AFAIK, GEE can be used with a single cluster and independence does not assume any cluster structure for the parameter estimates. However, not all cluster robust standard errors will be available in that case. So, GEE can be used for GLM as a special case. – Josef Nov 23 '16 at 19:39

0 Answers0