# st: from scientific to real numbers...

 From "Christer Thrane" To Subject st: from scientific to real numbers... Date Fri, 14 Oct 2005 16:31:19 +0200

Hi,

I want to get the precise price prediction for a house with certain attributes, given the follwing regression, in real numbers. That is, 1.5e+06 (see bottom) does not tell me enough. Does anyone know how to "force" Stata to come up with the exact figure?

Christer

reg pris bta antsov leil garasje

Source | SS df MS Number of obs = 313
-------------+------------------------------ F( 4, 308) = 103.23
Model | 6.0351e+13 4 1.5088e+13 Prob > F = 0.0000
Residual | 4.5015e+13 308 1.4615e+11 R-squared = 0.5728
Total | 1.0537e+14 312 3.3771e+11 Root MSE = 3.8e+05

------------------------------------------------------------------------------
pris | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
bta | 5877.52 528.658 11.12 0.000 4837.282 6917.759
antsov | 96936.37 29516.44 3.28 0.001 38856.98 155015.8
leil | 168382.4 57136.84 2.95 0.003 55954.5 280810.4
garasje | 127576.9 47204.03 2.70 0.007 34693.7 220460.1
_cons | 277688.5 82658.97 3.36 0.001 115040.8 440336.3
------------------------------------------------------------------------------

. adjust bta = 130 antsov = 3 leil = 0 gar = 1

--------------------------------------------------------------------------------
Dependent variable: pris Command: regress
Covariates set to value: bta = 130, antsov = 3, leil = 0, garasje = 1
--------------------------------------------------------------------------------

---------------------- All | xb
----------+----------- | 1.5e+06
---------------------- Key: xb = Linear Prediction

*
* 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/