Thanks to Kit Baum, a new package called -kdens-
is available from SSC.
-kdens- provides high-end univariate kernel density
estimation tools. -kdens- supplements official Stata's
-kdensity- and also incorporates and extends the
capabilities of various pervious user add-ons such
as -adgakern-, -bandw-, -varwiker-, -akdensity-, or
-asciker-.
Important features of -kdens- are:
* adaptive (variable bandwidth) estimation is
supported
* several automatic bandwidth selectors including the
Sheather-Jones plug-in estimate are available
* pointwise variance and confidence interval estimation
is supported
* boundary correction for variables with bounded domain
is supported
* fast binned approximation estimation is available
To install -kdens-, type
. ssc install kdens
and then type
. help kdens
to view the helpfile. Furthermore, an overview of the
formulas used by -kdens- is available from
http://fmwww.bc.edu/RePEc/bocode/k/kdens.pdf
Note that -kdens- requires the -moremata- package. To
install -moremata-, type
. ssc install moremata
Comments and suggestions are highly welcome!
ben
*
* 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/