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

From |
Bert Jung <bjung59@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: Multiplying coefficients and standard errors in -estout- |

Date |
Mon, 1 Feb 2010 13:00:53 -0500 |

Thanks Maarten and Kit. Scaling the regressor will do the trick and solves my problem. My general preference is to change reported estimates rather than the underlying data. Multiplying by 100 seems like an easy task, especially since -estout- can transform coefficients (and presumably se. if I could figure out how). Of course I am willing to compromise that principle to get my problem fixed -- thanks for your suggestions! Maarten, in my context the linear probability model fits quite well. Your point is well taken and in fact my logit marginal effects are very similar. For better or worse economists tend to like LPM, see e.g. page 107 in Angrist and Pischke* for a common view. Cheers, Bert PS Apologies for not specifying: as you guessed my -estout- is from SSC. I use Stata/SE 10.1 * Angrist and Pischke (2009) "Mostly Harmless Econometrics", http://books.google.com/books?id=bUZzyXeV1JUC On Mon, Feb 1, 2010 at 7:52 AM, Kit Baum <baum@bc.edu> wrote: > <> > > As you're using a LPM, why don't you just scale the regressors /100? > > On Feb 1, 2010, at 2:33 AM, Bert wrote: > >> I am reporting coefficients from a linear probability model using >> - -estout- and -esttab-. I would like to multiply the coefficients with >> 100 so that readers can interpret them as percentage point change. I >> tried the -transform(@*100)- option in estout which works for the >> coefficients but struggle with the standard errors. Any suggestions >> greatly appreciated. > > > Kit Baum | Boston College Economics & DIW Berlin | http://ideas.repec.org/e/pba1.html > An Introduction to Stata Programming | http://www.stata-press.com/books/isp.html > An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html > > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/ > * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**Re: st: Multiplying coefficients and standard errors in -estout-***From:*Kit Baum <baum@bc.edu>

- Prev by Date:
**st: R: AW: R: Fw: Calculating a confidence interval for population variance based upon sample.** - Next by Date:
**Re: st: marginal effects in biprobit and average treatment effect in switching probit** - Previous by thread:
**Re: st: Multiplying coefficients and standard errors in -estout-** - Next by thread:
**Re: st: Multiplying coefficients and standard errors in -estout-** - Index(es):

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