st: Re: user-specified predicted values

[Kit Baum <baum@bc.edu>]

capt program drop jan
program jan, eclass
syntax , adjb(numlist)
tempname b adjbeta VV
mat `b' = e(b)
local nc = colsof(b)
local nca : word count(`adjb')
if `nca' ~= `nc' {
	di as err "Must have `nc' elements in adjb'"
	error 198
	}
local cn: colnames `b'
mat `VV' = e(V)
mat input `adjbeta' = (`adjb')
mat colnames `adjbeta' = `cn'
local dv `e(depvar)'
local cmd `e(cmd)'
local pred `e(predict)'
local model `e(model)'
ereturn post `adjbeta' `VV'
ereturn local depvar `dv'
ereturn local cmd `cmd'
ereturn local pred `pred'
ereturn local model `model'
end



. reg price mpg headroom

      Source |       SS       df       MS              Number of obs =   
    74
-------------+------------------------------           F(  2,    71) =   
 10.44
       Model |   144280501     2  72140250.4           Prob > F      =   
0.0001
    Residual |   490784895    71  6912463.32           R-squared     =   
0.2272
-------------+------------------------------           Adj R-squared =   
0.2054
       Total |   635065396    73  8699525.97           Root MSE      =   
2629.2

------------------------------------------------------------------------ 
------
       price |      Coef.   Std. Err.      t    P>|t|     [95% Conf.  
Interval]
------------- 
+----------------------------------------------------------------
         mpg |  -259.1057   58.42485    -4.43   0.000    -375.6015    
-142.6098
    headroom |  -334.0215   399.5499    -0.84   0.406    -1130.701     
462.6585
       _cons |   12683.31   2074.497     6.11   0.000     8546.885     
16819.74
------------------------------------------------------------------------ 
------

. jan, adjb(-250 -300 12000)

. predict phat,xb

. g checkjan=-250*mpg-300*headroom+12000

. su phat checkjan

    Variable |       Obs        Mean    Std. Dev.       Min        Max
-------------+--------------------------------------------------------
        phat |        74    5777.703    1361.107        850       8250
    checkjan |        74    5777.703    1361.107        850       8250


Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html

On Dec 5, 2004, at 2:33 AM, statalist-digest wrote:


> I am looking for a way to compute my own version of the predicted
> values (following a regression estimation), x*b-star, where x is the
> matrix of data on the x-variables and b-star is a transformed vector
> of regression coefficients. However, I find no way of computing this
> particular cross-product using, e.g.,  matrix accum, and my data
> set is too big to allow matrix mkmat. Any clues?
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/