Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Heather Sun, MD" <heather.sun@stanford.edu> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: How to Graph - Exponential model |
Date | Mon, 1 Oct 2012 13:02:34 -0700 (PDT) |
Yes, I tried: twoway (function _b[b1:_cons] * _b[b2:_cons] ^ x, range(x)) (scatter y x) But it only graphed y-values for half of the x-values and in a very scattered skewed way (not a nice exponential line as expected). ----- Original Message ----- From: "Richard Goldstein" <richgold@ix.netcom.com> To: statalist@hsphsun2.harvard.edu Sent: Monday, October 1, 2012 12:50:57 PM Subject: Re: st: How to Graph - Exponential model did you try -twoway function- to get your line? Rich On 10/1/12 3:35 PM, Heather Sun, MD wrote: > Dear All: > > I have performed the non-linear least squares estimation method of regression, using the exponential model y = b1*b2^x. > > I would like to create a graph of this equation on a scatterplot of my data, along with 95% confidence interval lines. > > I am able to create the scatterplot but am having difficulty graphing the regression exponential equation line. I have tried twoway graphs, but the fit plot options of linear prediction and quadratic prediction with confidence intervals obviously does not match the exponential model. > > Thanks in advance! * * 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/