st: Re: Comparison of results from Stata and Mata

[wgould@stata.com (William Gould, StataCorp LP)]

Matthew Baker <matthew.baker@hunter.cuny.edu> wrote, 

> I have noticed that there can be a (small) discrepancy between the
> results produced by Stata's predict command after running a regression
> and what I think should generate identical results in Mata. As an
> illustration, when running the following code:
>
>       sysuse auto, clear
>       reg price weight length
>       predict xb
>       gen err=price-xb
>
>     mata
>       st_view(X=.,.,"weight length")
>       X=X,J(rows(X),1,1)
>       st_view(Y=.,.,"price")
>       beta=invsym(X'X)*X'Y
>       err_mata=Y-X*beta
>     end
>
>     getmata err_mata
>     sum err err_mata
>
> I find that the results of the sum command are as follows [...]
>
>   Variable |  Obs        Mean   Std. Dev.       Min      Max
> -----------+------------------------------------------------
>        err |   74   -.0000198   2382.413  -4432.274  5771.01
>   err_mata |   74    6.20e-06   2382.413  -4432.274  5771.01