Jack Cohen (and others) made a distinction between a NULL hypothesis
(specification of a value for some parameter) and a NIL hypothesis (the
parameter, which may be a difference or may be an index of relationship, has
a value of zero).  I always just assumed that the two hypotheses were just
numbered with with 0 and 1.
----- Original Message -----
From: "Richard M." <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>
Sent: Thursday, March 20, 2003 12:41 PM
Subject: is the Null hypothesis always equal to zero?


I know that it is possible to reject an hypothesis that is not equal to zero
(like a difference of 0.5 standard deviation or a correlation less or equal
to .20).  But I wonder whether we still call such an hypothesis the "NULL"
hypothesis.





.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to