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]

Re: st: macro `if' in nonlinear least squares

From   Nick Cox <>
To   "" <>
Subject   Re: st: macro `if' in nonlinear least squares
Date   Thu, 2 May 2013 16:33:41 +0100

See the help and manual entry for -nl-. The short answer is that for
generality a program must have a way of working with subsets. If you
are all the data, `if' is empty and no restriction is applied.

"Function evaluator programs must accept a varlist, an if exp, and an
option named at()
    that accepts the name of a matrix.  It may optionally accept
weights as well.  Unlike
    substitutable expression programs, a function evaluator program is
not declared to be
    r-class.  The outline of a nlfunc_prog program is

        program nlfunc_prog
            version 10
            syntax varlist [aw fw iw] if, at(name)
            local lhs: word 1 of `varlist'
            local rhs: subinstr local varlist "`lhs'" "", word
            (evaluate the function at at matrix)
            replace `lhs' = <the function values> `if'

    When evaluating your function, remember to restrict the estimation
sample by using `if'."

On 2 May 2013 16:27, Francesca Colantuoni <> wrote:
> I am programming a nonlinear least square regression, and I am trying
> to find the best way to do it based on variuos examples that I found
> online.
> In the following code, I have trouble understanding what stata does
> with the macro `if' at the end of the generate command. Would anybody
> clarify that for me? I could not find an explanation for this use of
> "if" in either [P] or [U] manual (or Google).
> // Some temporary variables
>     tempvar kterm lterm
>     generate double `kterm' = `delta'*`capital'^(-1*`rho') `if'
>     generate double `lterm' = (1-`delta')*`labor'^(-1*`rho') `if'
>     // Now fill in dependent variable
>     replace `logout' = `b0' - 1/`rho'*ln(`kterm'+`lterm') `if'
> Best Regards,
> Francesca
> *
> *   For searches and help try:
> *
> *
> *
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index