Statalist


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

Re: st: Graphing quadratic relationship


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Graphing quadratic relationship
Date   Fri, 18 Sep 2009 23:14:01 -0400

Stephanie L Kent:
You might also try -locpr- on SSC.

On Fri, Sep 18, 2009 at 2:34 PM, Ronan Conroy <rconroy@rcsi.ie> wrote:
> On 18 MFómh 2009, at 18:35, Stephanie L Kent wrote:
>
>> Dear users,
>>
>> I would like to graph a relationship between a quadratic independent
>> variable and my dependent variable to see how y varies acccording to x and
>> x^2.  It's a logistic regression so my DV is 0-1 and I need to show how
>> both the 0's and 1's vary according to x and x^2.  Any advice on how to
>> get
>> started is much appreciated!
>
> I would be wary of quadratic terms, which tend to produce nonsense estimates
> at the extremes of the data, or to extrapolate to nonsense estimates beyond
> the observed range. Have you tried fractional polynomials?
>
> As to graphing, I have two suggestions:
>
> 1. jitter your response variable to give a better impression of the density.
> If you have a lot of data, you can end up with two 'stripes' across the
> graph at y=0 and y=1 otherwise
> 2. Add a plot of predicted probabilities as a connected line
>

*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index