 |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: RE: broken stick (piecewise linear) regression
Raphael Fraser wrote:
-nl- offers a solution but it is NOT a good one. I have tested it with
data from the cited paper below and have been found lacking.
Here is one reason why we fit two-line models rather than a smooth curve:
In examining the relationship between two linear metabolic variables,
as a person exercise we can detect the time at which this person
changes form aerobic to anaerobic state (i.e. change in slope). That
point is what we refer to as the changepoint. Here interest lies in
estimating the changepoint.
The Statistician (2001). 50, Part 1, 51-61.
I am a bit disappointed though that Stata is still lagging behind.
I have written an ado-file that does broken-stick regression (also
referred to as hockey stick regression, which is the name I used for the
ado-file. Try
net from personalpages.manchester.ac.uk/staff/mark.lunt
then click on "loghockey" to find it.
I've tested it against the data in the paper quoted above and it
produces exactly the same results. However, it is only a function to be
used with nl.
Hope that is of some help
Mark
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/