Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: regress


From   Richard Williams <[email protected]>
To   [email protected], [email protected]
Subject   Re: st: regress
Date   Tue, 27 Aug 2013 12:23:22 -0500

This seems to be more of a substantive question for economics than it does a statistics or Stata question. But if I thought the sign for a coefficient seemed odd, I would (a) make sure all my coding is ok, and (b) check the bivariate correlations. If the bivariate correlation was positive and the regression coefficient was negative, I would start thinking about some sort of suppressor effect. Maybe greater amounts of labor indicate lower levels of efficiency, at least once other variables are taken into account. But do some reading in economics or get the opinion of someone in the field.

At 10:32 AM 8/27/2013, Rezgar Mohammed wrote:
Hello,
I am a beginner in Econ. I would like to test the effect of some
factors on the production of specific output using the Cobb-Douglass
production function. I would like to know if you have any concerns
about the results.
Y represents output, x1 labor, x2 fertilizer, x3 land, x4 seed and x5
is capital. I wonder why the x1 coefficient is negative for example.


reg lny lnx1 lnx2 lnx3 lnx4 lnx5

Source | SS df MS Number of obs = 160
-------------+------------------------------           F(  5,   154) =22942.46
Model | 1.13880167 5 .227760334 Prob > F = 0.0000 Residual | .001528829 154 9.9275e-06 R-squared = 0.9987
-------------+------------------------------           Adj R-squared =  0.9986
Total | 1.1403305 159 .00717189 Root MSE = .00315

------------------------------------------------------------------------------
lny | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
lnx1 | -.0398971 .0008289 -48.13 0.000 -.0415346 -.0382596 lnx2 | 1.063405 .0033848 314.17 0.000 1.056719 1.070092 lnx3 | -.0008994 .0005395 -1.67 0.098 -.0019652 .0001664 lnx4 | .0023421 .0024396 0.96 0.339 -.0024772 .0071615 lnx5 | .0025708 .000884 2.91 0.004 .0008245 .0043171 _cons | -.3304083 .0228141 -14.48 0.000 -.3754774 -.2853393
------------------------------------------------------------------------------

I tested for heteroskedasticity and auto-correlation but nothing changes.


Thank you.


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/

-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  [email protected]
WWW:    http://www.nd.edu/~rwilliam

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index