Linear regression - where is the error term in Stata?

[Silvia Haertl]

Dear all,

My work consists on the Paper of Jordà, Schularick and Taylor (2016) - Sovereigns vs. Banks: Credit Crisis and Consequences which is available under
https://academic.oup.com/jeea/articl...4/1/45/2319810


At the moment, I am trying to retrace the above mentioned paper with Stata. I need to retrace the following sequence of fixed-effects panel regressions:

I already have the following command (within a loop) which works perfectly and computes identical results as in the paper:

reg `v'`i' pk_norm pk_fin c_excess_norm_prv c_excess_fin_prv `c_rhs8a' c_d1-c_d16  ///
        if `c`j'' & core==1 & (pk_fin==1|pk_norm==1) , noconstant vce(cluster iso)

The thing which I don´t understand is, where the error term in Stata is?
Because in equation (5), u is the error term, but I don´t have the error term in my reg - command?

Could maybe someone explain to me what happens with the error term in Stata? Why it seems that I don´t need him here?

[Maarten Buis]

you can see the residual by typing predict resid, resid after your regression, followed by list resid. That is, each observation in your data has its own residual, so it does not make sense to put that in your regression output. The output does contain the standard deviation of the residual in the top right block labeled root mse.

[Silvia Haertl]

Dear Maarten, thank you very much for the quick response. That helped a lot! Thank you