Quantile regression - control group

[Nicola Rossi]

Dear Stata users,

I have a question regarding the application of quantile regression with a control group. I will try to explain better my objective...


In a prior analysis, I applied a Mlogit regression model. In this case, my dependent variable was as follows:
"0" - Control Group;
"1" - first label (main group);
"2" - second label (main group).

I had first and second labels only on my main group. The stata output reports two models that show the statistical significance of independent variables on first and second labels (in comparison to control group), while stata does not disclose the model regarding the control group.

Now, instead of a multinomial dependent variable, I have a continuous variable and I want to see the influence of independent variables on the dependent variable in terms of quantiles. However, I would like to maintain the same conceptual approach, including my control group (as baseline group) in the analysis (as in the Mlogit analysis). Is it possible with quantile regression analysis?


In the past I applied this model xtqreg Y x1 x2 ....xn, , quantile(.10 .20 .30 .40 .50 .60 .70 .80 .90), but I did not need to take into account also a control group. Is there a way to integrate quantile regression to include control group too?


Any suggestions would be really appreciated,
Thank you in advance for your support.

Regards,
N

[Carlo Lazzaro]

Nicola:
you can probably plug:

i.group

in the right-hand side of your regression equation.