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: does the
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: does the
Date
Thu, 7 Mar 2013 10:47:08 +0000
I don't understand your guess, nor the comment that -sum- does not work here.
But there is no need to guess: use
set trace on
set traced 1
so see where your program fails.
This is illegal:
forvalues i=1(1)n {
Stata won't evaluate your scalar -n- is that context. This should work
forval i = 1/`=n' {
There may be other problems too.
Nick
On Thu, Mar 7, 2013 at 5:16 AM, Wu Zhang <[email protected]> wrote:
> Hi folks,
>
> I encounter this error message : invalid syntax r(198);
> My guess is that 'tabstat' with option 'save' does not work since the matrix xstat is null, but I cannot fix it; any thoughts? thanks!
>
>
> My code is as follows:
>
> program ape_total, rclass
> version 8
> syntax varlist(numeric)
> gettoken y x : varlist /*nice way to split y and x! from Maarten*/
>
>
>
> tabstat `x', statistics( mean p25 p50 p75 p95 ) save /*'sum' does not work here!*/
>
> mat xstat=r(StatTotal)
> scalar n=rowsof(xstat)
> scalar m=colsof(xstat)
> regress `varlist'
> predict ehat, residual
> mat paraest=e(b)
>
>
>
> forvalues i=1(1)n {
> mat meanvalue=(xstat[i, 1...],1)*paraest'
> scalar meanvalues=meanvalue[1,1]
> forvalues j=1(1)m{
> scalar alpha`j'=paraest[1,j]
> gen apet`i'`j'=alpha`j'*exp(meanvalues+ehat)/(1+exp(meanvalues+ehat))^2
> sum apet`i'`j'
> return scalar ape`i'`j'=r(mean)
>
>
> }
> }
>
> drop apet* ehat
>
> end
*
* 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/