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

Re: st: m stat for sign test

From   Chris Witte <>
Subject   Re: st: m stat for sign test
Date   Thu, 9 Oct 2008 11:45:02 -0700 (PDT)

The excerpt below is taken from SAS's help.  This is what I would like in addition to the p-value:

Sign Test

PROC UNIVARIATE calculates the sign test statistic as 

M=(n+ -n- )/2 

where n+ is the number of values that are greater than mu_o and n- is the number of values that are less than mu_o. Values equal to mu_o are discarded. Under the null hypothesis that the population median is equal to mu_o

----- Original Message ----
From: Christopher Baum <>
Sent: Thursday, October 9, 2008 1:22:06 PM
Subject: st: m stat for sign test

< >
Chris said

I'm running a -signtest- analysis on groups of data to see whether  
they differ from an expected value.  The data isn't normally  
distributed, which is why I'm not using -ttest-.  I know that SAS  
reports the m statistic with the p-value from the sign test.  Can  
stata give this as well?

-signtest- gives you a p-val for the null, as described in the help,  
that the median difference between varname and exp is zero. Isn't that  
what you want to test the null that the grouped values of varname  
equal their corresponding exp in an average sense?

Kit Baum, Boston College Economics and DIW Berlin
An Introduction to Modern Econometrics Using Stata:

*  For searches and help try:


*   For searches and help try:

© Copyright 1996–2023 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index