Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "L.M.A. Mulotte" <L.Mulotte@uvt.nl> |
To | "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu> |
Subject | st: Shapes of two Inverted U curves (same model on two different samples) |
Date | Mon, 4 Jul 2011 17:12:07 +0000 |
Dear Readers I have an OLS model that includes both a linear effect and the quadratic term. I run this model on two samples, one with a treatment (sample X) and one without treatment (Sample Y). I find that the turning point of Curve Y is significantly smaller than the turning point of Curve X. Is there any means to test whether the "legs" of Curve Y are steeper than the "legs" of Curve X? Put differently, I would like to do a test to know whether Curve Y is closer to Curve Y1 or closer to Curve Y2, as described hereafter: [ [ # # [ # # [ curve Y1 # # [ + # # [ + + # # [ + + # @ @ # [ + #+ @ @ # [ + # +@ @ # [ + # @ + @ # curve X [ + # @ + curve Y2 @ # _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ Here is an example showing my problem use http://www.stata-press.com/data/r11/nlswork gen age2=age*age regress ln_wage age age2 birth_yr grade if south==0 regress ln_wage age age2 birth_yr grade if south==1 Which of the two Inverted-U curves exhibits the "steepest" legs ? And, can I do a statistical test for that? Thanks for your consideration Best, Louis * * 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/