Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# Re: st: Polynomial Fitting and RD Design

 From Nick Cox <[email protected]> To [email protected] Subject Re: st: Polynomial Fitting and RD Design Date Thu, 1 Sep 2011 09:31:30 +0100

```Sure, but that still leaves the non-numeric issues. I guess the main
issue is just reproducing behaviour with smooth curves, but what
arguments justify any kind of quartic here?

Nick

On Thu, Sep 1, 2011 at 9:06 AM, Maarten Buis <[email protected]> wrote:
> --- On Wed, Aug 31, 2011 at 9:54 PM, Patrick Button wrote:
>>>> I need to run a regression that fits a 4th degree polynomial separately
>>>> for points of the running variable, x, below 0.5 and above 0.5. The
>>>> regression includes a dummy variable for if x >= 0.5 or not as well. If
>>>> there is a discontinuity at 0.5, then this is picked up in the coefficient
>>>> on that dummy variable.
> <snip>
>>>> *Left Side Polynomial
>>>> gen xa = (1-D)*x
>>>> gen x2a = (1-D)*x^2
> <snip>
>
> --- On Thu, Sep 1, 2011 at 8:37 AM, Nick Cox wrote:
>> Even if you can get this to work as intended, look at the sizes of
>> those coefficients! The resultant curve may look about right, but this
>> is a dubious thing to do numerically and statistically. I
>
> The numerical problems can be alleviated by using orthogonal
> polynomials, see -help orthog-. This is just a different way of
> representing that 4th degree polynomial that makes it a lot easier for
> computers to deal with.
>
*
*   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/
```