Statalist


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

Re: st: slight typo in the manual for -moptimize-: initial values set for the


From   [email protected] (Jeff Pitblado, StataCorp LP)
To   [email protected]
Subject   Re: st: slight typo in the manual for -moptimize-: initial values set for the
Date   Mon, 09 Nov 2009 09:29:09 -0600

Laszlo Sandor <[email protected]> points out an inconsistency in the
documentation for -moptimize()-:

> I was surprised to find that -moptimize- does not allow initial values
> for the intercepts, at least according to my understanding the manual.
> After some experimenting and bugfixing, it is now obvious to me that
> it does, only the manual seems to be inconsistent in its notation for
> "ki" for  equation i.
> Here is a link to the ambiguous passage:
> http://www.stata.com/help.cgi?mf_moptimize#def_b0

Laszlo is correct.  The description for -moptimize_init_eq_coefs()- should be

    moptimize_init_eq_coefs(M, i, b0) sets the initial values of the
	coefficients for the ith parameter to be b0: 1 x (ki+ci).  The default
	is (0, 0, ..., 0).

Here 'ci' is 1 if equation 'i' contains an intercept, and 0 otherwise.

We will fix the online help in a future ado-file update.

--Jeff
[email protected]
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index