Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: Re: plotting fitted lines of percentiles of two variables


From   "Michael Blasnik" <[email protected]>
To   <[email protected]>
Subject   st: Re: Re: plotting fitted lines of percentiles of two variables
Date   Wed, 02 Aug 2006 10:09:23 -0400

Actually, it appears that grqreg does something a little different then what you ask for. It plots the coefficients over a range of quantiles. It seems that you want a plot of fitted values for three different quantiles. It may be better for you to take a direct approach using -predict- to generate the fitted values for each quantile and then use a graph command to plot the three fitted lines. Something like:

sqreg infant gdpe, quant(.25 .5 .75)
predict q25hat, equation(q25)
predict q5hat, equation(q50)
predict q75hat, equation(q75)
graph twoway line q25hat q50hat q75hat gdpe

You may want to tweak the graph , especially the legend.

Michael Blasnik

----- Original Message ----- From: "Michael Blasnik" <[email protected]>
To: <[email protected]>
Sent: Wednesday, August 02, 2006 9:55 AM
Subject: st: Re: plotting fitted lines of percentiles of two variables



search graph quantile regression, all

will lead you to grqreg, which I think does what you want. You should try using the search command prior to posting to the list..

Michael Blasnik

----- Original Message ----- From: "Sam Rawlings, Social Sciences and Law 03" <[email protected]>
To: <[email protected]>
Sent: Wednesday, August 02, 2006 9:09 AM
Subject: st: plotting fitted lines of percentiles of two variables



I have two variables - Log Infant Mortality Rate (infant) and Log GDP (gdpe). I want to plot the relationship between infant and gdpe as three separate fitted lines, one each for the 25th, 50th and 75th percentiles.
I tried using qqplot but I get a single line.
I believe what I want is a graphical represention of the results of
sqreg infant gdpe, quant(.25 .5 .75).

Any help would be much appreciated. Thanks,

Samantha
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index