IV when there is an interaction term including the endogenous variable

[Hazel Gould]

Hi,

I have a regression of 'reg Y X1 X2 X1 X2 controls' and X1 is endogenous.

When I use ivreg I do 'ivregress 2sls Y X2 X1X2 controls (X1 = z1 z2)'

However, the interaction term is constructed using the endogenous X1 variable... How do I code an IV regression to control for the endogenous effect that this will be having through the interaction term?

Please help!!

Thank you so much.

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

You calculate the interaction manually and then include it in the endogenous list.
'ivregress 2sls Y X2 X1X2 controls (X1 X1X2 = z1 z2)