On Thu, 27 Jan 2000, boonlert wrote:
> The result of paired sample t-test analysis from SPSS shows
> both a significance (sig.) of paired sample correlation and a
> significance of paired sample test but they are opposite interpretation
> (one is <.05, one >.05).
> Could any one tell me why they are different and how should I
> interpret this result?
To Rich Ulrich's good advice I would only add: PLOT YOUR DATA !!!
Produce a scatterplot of one member of each pair vs. the other member of
the pair, for the variable in question. This will display the
correlation visually, and you can see whether the reported correlation
_coefficient_ is a reasonable summary of the relationship.
When you have a plot in hand, superimpose on it, by hand, a line
representing (ordinate = abscissa) (a 45-degree line through the origin,
given equal units on both axes; but the origin would be well off the
graph for most real data, and the scaling may not be the same on both
axes); and the point (marked with a cross) plotting (mean on ordinate)
vs. (mean on abscissa). How far that point is from the line visually
represents the question, "How unequal are the means?".
-- DFB.
------------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
348 Hyde Hall, Plymouth State College, [EMAIL PROTECTED]
MSC #29, Plymouth, NH 03264 603-535-2597
184 Nashua Road, Bedford, NH 03110 603-471-7128
===========================================================================
This list is open to everyone. Occasionally, people lacking respect
for other members of the list send messages that are inappropriate
or unrelated to the list's discussion topics. Please just delete the
offensive email.
For information concerning the list, please see the following web page:
http://jse.stat.ncsu.edu/
===========================================================================
