Testing for weak instruments

[Disha Gupta]

I have 3 endogenous variables in my model and I have identified 3 (or max 4) instruments. I wanted to know appropriate test for identifying whether the instruments are weak or not given that I have heteroskedaticity (cluster option is being used) in my data. I read that one should employ the Kleibergen-Paap F statistic in this case and compare with Stock and Yogo Critical values but in the case of 3 endogenous variables the table in their paper starts with a min of 5 instruments. I am confused as to which test to employ in this case. Any suggestions would be useful in this regard.

[Phil Bromiley]

You'll increase your chances of a helpful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

ivreg2 and xtivreg2 provide a wide variety of diagnostic tests. Having extra instruments makes many of the tests possible (since with one instrument per endog var you're just identified).

The author of Mostly Harmless Econometrics raises concerns about having more than one endogenous variables - see http://www.mostlyharmlesseconometric...bles-what-now/

I'm not sure I agree with him, but I'm not an econometrician.