Bookmark and Share

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

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

Re: st: RE: mfx 2 command

From   Richard Williams <>
Subject   Re: st: RE: mfx 2 command
Date   Tue, 10 Aug 2010 18:58:19 -0500

Thanks to Dr. Martin for filling in for me! I'll just add that (1) -margeff-, also available from SSC, is often faster than -mfx2- (but -margeff- does not support as many programs), and (2), as noted in the help file for -mfx2-, "only the standard errors of the marginal effects are correct, hence use of commands like test may produce incorrect results." Of course, there is also the new -margins- command, but I am not sure if it provides the same convenience with multiple-outcome commands like -ologit- that -mfx2- and -margeff- provide.

At 01:25 PM 8/10/2010, Martin Weiss wrote:


u, clear
ologit warm yr89 male white age ed prst
eret li
mat l e(mfx_b_dydx)
mat l e(mfx_se_dydx)


-----Original Message-----
From: [] On Behalf Of Laura Cyron
Sent: Dienstag, 10. August 2010 20:20
Subject: st: mfx 2 command

Hello everyone,

I was wondering whether anyone could tell me how the -mfx2- command saves its
marginal effects and the respective standard errors.
The -mfx- command does it in e(Xmfx_dydx) and e(Xmfx_se_dydx).
I'd like to directly include the matrices in a routine but my results come from
a mprobit estimation and am using -mfx2- as mentioned above.
Reading ado-files is sadly not one of my strength and I cannot deduce from it
how the matrices storing the marginal effects and standard errors might be
called. I would greatly appreciate you input.

Thanks a lot,


*   For searches and help try:

*   For searches and help try:

Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index