[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
"Shehzad Ali" <sia500@york.ac.uk> |

To |
<statalist@hsphsun2.harvard.edu> |

Subject |
st: RE: RE: prediction after y-logged regression |

Date |
Mon, 2 Jun 2008 14:49:34 +0100 |

Thanks, Nick and Richard. This is very helpful. I wonder if I could use link(log) after treatreg or heckman. Any thoughts on how to do it? Cheers, Shehzad -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Nick Cox Sent: 02 June 2008 13:29 To: statalist@hsphsun2.harvard.edu Subject: st: RE: prediction after y-logged regression There is a large literature on this problem, especially it seems in health economics. If you use -glm, link(log)- the predictions are in essence adjusted automatically. What you describe is a special case of smearing, which is very easy too in the case of log transformation. In my experience the results of using -glm, link(log)- and of smearing are very similar. I prefer -glm-. Nick n.j.cox@durham.ac.uk Shehzad Ali I am running a regression in which y variable is logged (semi-logarithmic). The literature suggests that in order to get an anti-logged prediction of yhat, one should proceed like this: 1. Run the regression and predict yhat, 2. Then exponentiate the predicted yhat, and finally 3. Mutiply the exponentiated predicted yhat by the mean value of residuals from the regression (otherwise known as smearing). I was wondering if there is a direct way to do it in stata or if there is any other method that experts would suggest to get anti-logged prediction. Thank you, Shehzad -- Shehzad I Ali Department of Social Policy & Social Work University of York YO10 5NG +44 (0) 773-813-0094 * * 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/ * * 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/ * * 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/

**Follow-Ups**:**Re: st: RE: RE: prediction after y-logged regression***From:*Maarten buis <maartenbuis@yahoo.co.uk>

**References**:**st: prediction after y-logged regression***From:*Shehzad Ali <sia500@york.ac.uk>

**st: RE: prediction after y-logged regression***From:*"Nick Cox" <n.j.cox@durham.ac.uk>

- Prev by Date:
**RE: st: RE: predict residual after treatreg** - Next by Date:
**Re: st: RE: RE: prediction after y-logged regression** - Previous by thread:
**st: RE: prediction after y-logged regression** - Next by thread:
**Re: st: RE: RE: prediction after y-logged regression** - Index(es):

© Copyright 1996–2015 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |