Dear STATALIST forum,
I'm looking for ways of visually depicting the association between a dichotomous explanatory variable (parod1) and an ordinal dependent variable (sis).
In the adjusted model, certain confounders are included ("ageatvisitone", diabetes (diab1) and smoking, as you can see in the example below).
The data is overdispersed and negative binomial regression (nbreg) was used for the analysis.
The mean and median dependent varible "sis" is 0. And the percentiles of the dependent variable is as follows:
percentiles: 10% 25% 50% 75% 90%
0 0 0 2 4
Do you think a box plot of parod1==1 and parod1==0 would be meaningful? And what would be the code to provide one?
I have also considered quantlie regression box plots for several quantiles since the percentiles are mainly 0. Is this a good idea and what would be the code to provide it?
Regards,
Niko
I'm looking for ways of visually depicting the association between a dichotomous explanatory variable (parod1) and an ordinal dependent variable (sis).
In the adjusted model, certain confounders are included ("ageatvisitone", diabetes (diab1) and smoking, as you can see in the example below).
The data is overdispersed and negative binomial regression (nbreg) was used for the analysis.
The mean and median dependent varible "sis" is 0. And the percentiles of the dependent variable is as follows:
percentiles: 10% 25% 50% 75% 90%
0 0 0 2 4
Code:
* Example generated by -dataex-. To install: ssc install dataex clear input byte sis float(parod1 ageatvisitone diab1 smoking) 0 0 63.6 0 2 1 0 57 0 1 0 0 62.2 0 2 0 0 53.3 0 1 0 0 50.7 0 1 end
Do you think a box plot of parod1==1 and parod1==0 would be meaningful? And what would be the code to provide one?
I have also considered quantlie regression box plots for several quantiles since the percentiles are mainly 0. Is this a good idea and what would be the code to provide it?
Regards,
Niko
