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

From |
"Aparna Mathur" <AMathur@AEI.org> |

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

Subject |
st: Elasticity after xtprobit |

Date |
Thu, 30 Aug 2007 17:46:37 -0400 |

Hi, I need to calculate the elasticity after using xtprobit (RE probit). If I use "mfx compute, eyex", it yields an error. So I tried "mfx compute, predict (pu0) eyex" and it yielded some output. Is this the correct way of computing the elasticity? Also, can I get that elasticity from the marginal effects table by multiplying the marginal effect for each variable by the mean of the variable and dividing by the overall probability that y=1? In other words, is the elasticity=(d(Pr(y=1))/dx)*(xbar/avgPr(y=1))? I've tried doing it, and while the numbers are close, they're not exactly identical, so just wanted to be certain that that is how it would be computed. Aparna * * 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/

- Prev by Date:
**Re: Re: st: Problems using predict in xtfrontier** - Next by Date:
**st: about the return list of -codebook-** - Previous by thread:
**st: Survey statistics, sampling methods** - Next by thread:
**st: about the return list of -codebook-** - Index(es):

© Copyright 1996–2016 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |