Re: st: Precision issues with Mata. Where's my error?

[Marta García-Granero <mgarciagranero@gmail.com>]

Thanks a lot! Time to adjust my glasses again.

Marta

El 05/06/2013 13:49, Scott Merryman escribió:
> On Wed, Jun 5, 2013 at 6:23 AM, Marta García-Granero
> <mgarciagranero@gmail.com> wrote:
> > The problem is that I expected x42 and x43 to be 9.95 and 36.34 (checked
> > with other software, like Winpepi, or SPSS 21 NPTESTS command), and I get
> > 10.36 and 36.55.
> >
> > I can't find my error.
> In the Excel code for x40 and x41 you have:
>
> x40 = x16 * x16 - 2 * x39 * x16 * x27 + x27 * x27
> x41 = x17 * x17 - 2 * x39 * x17 * x26 + x26 * x26
>
> while the Mata code is:
>
> x40=x16^2-2*x39*x16*(x27^3)
> x41=x17^2-2*x39*x17*(x26^3)
>
>
> x27 + x27 * x27 != x27^3
>
> Scott
>
> *
> *   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/
*
*   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/