some books call the SEMI partial r ... the part correlation (or vice versa)
... i avoid it because ... part and partial sound too much alike
when would you use the semi partial?
1. i use it sometimes to provide an alternative way to obtain the multiple
R ... say predictors are x1 and x2 ... and y is the criterion ... use r
square x1 y ... then, take the first order SEMI partial ... between
residuals on x2 ... with x1 removed ... and y ... and square it ... add the
two r squares together to get R squared ...
2. psychologically speaking .. there could be times when logically .. it
makes sense to remove some noise variable from one of the xy pair ... but
not both ... that is, there is some rationale for taking it from say x ...
but not y
however, i would not agree with the instructor's comment:
">
>The instructor claims that the part correlation is usually better (more
>interpretable?) but that SPSS and other software will not compute such a
>correlation."
if you can handle one residual variable ... why not two?
==============================================================
dennis roberts, penn state university
educational psychology, 8148632401
http://roberts.ed.psu.edu/users/droberts/droberts.htm
===========================================================================
This list is open to everyone. Occasionally, less thoughtful
people send inappropriate messages. Please DO NOT COMPLAIN TO
THE POSTMASTER about these messages because the postmaster has no
way of controlling them, and excessive complaints will result in
termination of the list.
For information about this list, including information about the
problem of inappropriate messages and information about how to
unsubscribe, please see the web page at
http://jse.stat.ncsu.edu/
===========================================================================
