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: Re: st: Polynomial Fitting and RD Design

From   Maarten Buis <[email protected]>
To   [email protected]
Subject   Re: Re: st: Polynomial Fitting and RD Design
Date   Fri, 2 Sep 2011 22:41:06 +0200

On Fri, Sep 2, 2011 at 8:50 PM, Austin Nichols wrote:
>  I agree that global
> polynomials are generically a bad idea for the RD design, but
> "considering a fractional polynomial model instead," one should be
> comparing to the standard approach, not a polynomial.  I.e. Maarten's
> example graph does not provide evidence for a fractional polynomial
> model over local linear regression.

That is as I intended my example: a comparison of a global polynomial
with a fractional polynomial. The polynomials suggested by the
original poster looked suspicious to me, and I was trying to come up
with some alternative that was easy to implement and I overlooked that
all this was already better implemented in the -rd- package. I happily
bow to suprerior wisedom.

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