Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: re: P-value using centiles


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: re: P-value using centiles
Date   Mon, 16 Nov 2009 07:57:06 -0500

<>

Martin replied 

[R], p. 259, explains the formulas used to calculate the ci, so you want to
take a cue from it...


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Paul K.
Musingila
Gesendet: Sonntag, 15. November 2009 01:06
An: statalist@hsphsun2.harvard.edu
Betreff: st: P-value using centiles

Att.
I have a an output from centile and I want to get a p-value i do i go about
this using stata commands.


Note well the statement in help centile and [R] centile that the CI presented "makes no specific assumptions about the distribution". It is hard to imagine computing a P-value from the ratio of the centile to its s.e. if you do not have some assumption on the distribution of that object. On the other hand, if you use centile's  meansd option, normality is assumed. The last part of [R] centile gives the very simple formula for the s.e. in that instance, and it could be evaluated against the Normal cdf to derive a p-value.

Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                              An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
   An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html


*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index