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: boostrapping from a log regression

Subject   Re: st: boostrapping from a log regression
Date   02 Sep 2010 11:03:17 +0100

Many thanks for your help Maarten, the reference has an excellent summary of GLM and surrounding issues which has been very helpful to a relative newcomer.

However I wonder if I haven't been clear enough with my query. Its the actual Beta Coefficient im having difficulty trying to obtain in natural units not the predicted values of the dependent variables (y).

I had understood from a colleague (who is now away and uncontactable unfortunately) that it is possible to obtain this by bootstrap. However I am uncertain as to how this can be achieved in stata or how to extract the required scalars from said bootstrap in order to use them in a later calculation.

I have actually tried a number of models including GLM models, but the AIC on the log transformed model is so much lower that i`d prefer to use it if it is at all possible.

Failing that, does anyone know if i would need to perform any similar transofrmations on beta coeficients from a GLM -Gamma- link(identity)-, or -Gamma- -link(log).

Andy Stoddart

On Aug 31 2010, Maarten buis wrote:

--- On Mon, 30/8/10, wrote:
Im trying to regress a log transformed dependent (y)
variable on a dummy variable with a number of other
explanatory variables:

Log Y = b1 + b2D + b3X1 + ... + bnXn + u

From this I am trying to extract  scalars from the
matrix for:
a) the Beta (coefficient) of the dummy in natural units,
b) the variance (Y:D), and
c) the standard error (or t-test)

The easiest solution is to use -glm- together with -link(log)-
option. See for more on this issue:

Nicholas J. Cox, Jeff Warburton, Alona Armstrong, Victoria J. Holliday
(2007) "Fitting concentration and load rating curves with generalized
linear models" Earth Surface Processes and Landforms, 33(1):25--39.

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index