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

st: -swilk- , or thought for the day

From   "Nick Cox" <>
To   <>
Subject   st: -swilk- , or thought for the day
Date   Thu, 13 Nov 2008 19:10:30 -0000

The Shapiro-Wilk test for normality implemented in Stata's -swilk- is
quite often used. 

The journal _Statistical Science_ has on its page of future papers 


the paper "A conversation with Martin Bradbury Wilk" by Christian Genest
and Gordon Brackstone. Dr Wilk was born in 1922 and looks back on a
productive statistical and scientific life. 

I thought I would share this exchange with you: 
Christian: The 1965 Biometrika paper introducing the Shapiro-Wilk test
statistic is certainly a classic. 

Martin: I am obviously pleased with that, but to be truthful I don't
regard this work as such a great accomplishment. I am fond of saying,
significance tests are things to do while one is trying to think of
something sensible to do. 


*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index