Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: st: Interpreting mfx & margeff Coefficients from GLM
From
Richard Williams <[email protected]>
To
[email protected], [email protected]
Subject
Re: st: st: Interpreting mfx & margeff Coefficients from GLM
Date
Tue, 03 Apr 2012 09:29:59 -0500
At 04:01 PM 4/2/2012, Clifton Chow wrote:
Stata listers,
I ran a glm log link (family gamma from modified park's test) on my
dataset in which the dependent variables is hours worked. To
interpret the coefficients in the model, I transformed it via mfx
and margeff. I have a couple of questions about interpreting the
coefficients after transformation;
1. Is mfx mainly appropriate for indicator explanatory variables and
margeff for continous ones?
2. Can I interpret the results of the mfx coefficients in the raw
scale (i.e. hours)?
3. What does the column in the far right X referred to in the mfx output?
Most people are going to want to use the -margins- command rather
than the older -mfx- or -margeff-. The far right column in -mfx- is
the mean of the X variable. I am not sure what is happening with this
particular combo of link and family, but an intro to -margins- is at
http://www.nd.edu/~rwilliam/stats/Margins01.pdf .
Below is my partial mfx output from GLM:
y = Predicted mean hours (predict)
= 8.7005381
------------------------------------------------------------------------------------------------
variable | dy/dx Std. Err. z P>|z| [ 95%
C.I. ] X
---------+--------------------------------------------------------------------------------------
X1*| 8.891796 1.83527 4.84 0.000 5.29474
12.4889 .237385
X2*| -5.151794 1.41499 -3.64 0.000 -7.92513
-2.37846 .519545
(*) dy/dx is for discrete change of dummy variable from 0 to 1
4. For margeff, to interpret these in hours, should I exp(margeff
coefficient)?
Average partial effects after glm
y = log(hours)
------------------------------------------------------------------------------
variable | Coef. Std. Err. z P>|z| [95%
Conf. Interval]
-------------+----------------------------------------------------------------
X1 | 16.5519 3.9611 4.18 0.000 8.788287
24.31551
X2 | -7.379914 1.553438 -4.75 0.000 -10.4246 -4.335232
Thanks
*
* 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/
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/