Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

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

st: Re: query regarding restricted cubic splines

From   Maarten Buis <>
Subject   st: Re: query regarding restricted cubic splines
Date   Fri, 22 Mar 2013 10:54:42 +0100

--- Ridhima Gupta wrote me privately:
> I  am sorry for not posting this on state help. But I wasn't too sure if my query makes sense.

If your question makes no sense, then asking it to me in person would
not solve that problem. So the rule remains: "questions about Stata
should be sent to the Statalist, not to me privately". For that reason
I have forward your question, with answer, to the Statalist.

> I read your power point presentation on restricted cubic splines. Am I correct in assuming that right now I can only transform one independent variable using a restricted cubic spline while I have to control for the others by suing polynomials if I want to model non-linearity? Is there no way to apply restricted cubic splines to more than one independent variable in Stata?

No, you can add as many splines to your model as you want.  These
spline can be anything you like: linear, quadratic, cubic, ...,
restricted or not, B-spline or not. You can, if you want, interact
those splines. Roger Newson has recently published a nice paper on
splines in the Stata Journal, in which he also discusses adding
multiple splines (and their interaction) to a model:

Roger B. Newson (2012) "Sensible parameters for univariate and
multivariate splines". The Stata Journal, 12(3):479--504.

-- Maarten

Maarten L. Buis
Reichpietschufer 50
10785 Berlin

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index