In addition to Roger's excellent suggestions I'd underline the value of
graphical comparison too, for example using -qqplot- and the ideas
covered in
SJ-7-2 gr0027 . . Stata tip 47: Quantile-quantile plots without
programming
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . N.
J. Cox
Q2/07 SJ 7(2):275--279 (no
commands)
tip on producing various quantile-quantile (Q-Q) plots
In essence, comparing the distribution functions graphically -- or
equivalently the quantile functions -- should complement, and may tell
you more than, any omnibus measure or test.
Nick
[email protected]
Newson, Roger B
I don't know what you mean by "2nd order stochastic dominance". However,
stochastic dominance is usually measured using either Somers' D and
Harrell's c. Confidence intervals for both of those can be calculated
using the -somersd- package, downloadable from SSC using the -ssc-
command. The -somersd- package is distributed with 3 .pdf manuals, which
can be downloaded as ancillary files. The on-line help for -somersd-
refers to some Stata Journal articles on the subject, which may be
downloadable from the Stata Journal website at
http://www.stata-journal.com/
Rao, James
I would like to do some stochastic dominance analysis to compae two
distributions and I was just wondering if anyone knows how to conduct
1st and
2nd order stochastic dominance analysis in stata!
*
* 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/
