Thread: Regression analysis with dummy var.

1. Regression analysis with dummy var.

Hi everybody!

I am doing a multivar. regression analysis in stata.

I would like to know if the percentage of women in af specific position relates to the size of the wage. I have three dummy var. Gender (male=0), position (10 different, out of work = 0) and wage (y-var). How can I do a regression analysis with these variables and find out what I need to know?

I have tried to make a new dummy variable with eg. woman*leader. Is this the way to do it?

Best regards,
Lea

2. Re: Regression analysis with dummy var.

If you mean an interaction, in Stata 11 and Stata 12, you need to use

# or ##

help fvvarlist

A variable in the interaction term is assumed to be categorical unless you specify the operator c. (continuous variable). For example,

female#c.wage

female is categorical and wage is treated as a continuous variable.

If you are using Stata 10 or earlier version, you need to use

xi: i.female*wage

Originally Posted by Lea
Hi everybody!

I am doing a multivar. regression analysis in stata.

I would like to know if the percentage of women in af specific position relates to the size of the wage. I have three dummy var. Gender (male=0), position (10 different, out of work = 0) and wage (y-var). How can I do a regression analysis with these variables and find out what I need to know?

I have tried to make a new dummy variable with eg. woman*leader. Is this the way to do it?