Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: NLS per individual
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: NLS per individual
Date
Sun, 21 Oct 2012 15:47:08 +0100
. help statsby
Nick
On Sun, Oct 21, 2012 at 3:30 PM, Anton Goeree <[email protected]> wrote:
> Currently, I'm doing the following NLS on my dataset:
> nl (p = 1 / (1 + exp( - {sigma} * (x - y ^ {beta} )))), nolog
>
> The dataset contains 500 observations: 50 id's and 10 p/x/y per id.
> The variable p is either zero or one, and x,y are values between 50 and 200.
>
> I'd like to get individual estimates (for each id) for "sigma" and
> "beta". I could do - bysort id: nl (p = 1 / (1 + exp( - {sigma} * (x -
> y ^ {beta} )))), nolog - of course, but that would give me a messy
> list of 50 outputs. Does any of you know if it is possible to put the
> regression estimates into two new variables?
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/