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: Looking for courses in non-linear modelling and imputation techniques

From   Maarten Buis <>
Subject   Re: st: Looking for courses in non-linear modelling and imputation techniques
Date   Tue, 11 Oct 2011 08:58:05 +0200

On Mon, Oct 10, 2011 at 8:46 PM, Jacobs, David wrote:
> Splines seem extremely useful, but referees (in sociology at least) often give me trouble about the theoretical justification for particular cut points when I use this specification.  And sociological theory isn't terribly informative about such issues.
> I certainly agree that quadratics or for that matter cubics (which soc. referees also don't like) are procrustean, while dummies throw away information.
> Does anyone on the list have advice about how to justify splines when theory in one's discipline (and others) is mute about cut points?

If you are using splines in a linear regression you can use -nl- to
estimate the cut-point. I posted an example of how to do that in Stata
 here: <>
I don't tend to take those estimated cut-points too seriously, but
they are an effective way of pleasing referees. (No one who is
refereeing one of my papers is listening, right?)

Otherwise, you can consider a plot of partial residuals against the
original predictor with the spline function overlaid to show that the
spline (hopefully) captures the key features in the data. That is
after all the real justification when theory does not give you one.

Hope this helps,

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

*   For searches and help try:

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