Statalist The Stata Listserver

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

st: -mfx-

From   Nishant Dass <>
To   STATA Help <>
Subject   st: -mfx-
Date   Sat, 23 Sep 2006 05:30:45 -0700 (PDT)

Dear list-members,

I am using -mfx- after an -ivreg- estimation of the
following kind:
    ivreg y (lnx = z1) z2

and I would like to be able to make a statement like "a 1%
change in lnx results in so many % change in y", so which
of the following would be correct?

    mfx c, var(lnx) dyex
    mfx c, var(lnx) dydx

The cause of confusion is whether Stata takes the logarithm
of a variable or uses an already-"logged" variable in
calculating the marginal effects.  (If it simply uses
already-"logged" variables, then what is the use of options
other than "dydx"?)

A clarification would be very helpful.  Thank you in



Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
*   For searches and help try:

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