sme.hlp.htm

--------------
help for sme
--------------

Tests of Simple Main Effects
----------------------------

sme var1 var2 [, dfe(dferror) sse(sserror) alpha(#) ]

Description
-----------

sme performs tests of simple main effects on var1 for each level of
var2.  sme is run after first using anova.

Options
-------

dfe(dferror) specifies the degrees of freedom for the error term of the
        sme if dfe is not the residual degrees of freedom.

sse(sserror) specifies the sum of squares for the error term of the
        sme if sse is not the residual sum of squares.

alpha(#) specifies the nominal alpha level.  The default value is .05.


Concerns about tests of simple main effects
-------------------------------------------

Statisticians do not universally approve of the use of tests of simple 
main effects.  In particular, there are concerns over the conceptual error 
rate.  Tests of simple main effects are one tool that can be useful in
interpreting interactions.  Caution should be exercised in interpreting 
the results produced by sme.  In general, the results of tests of simple 
main effects should be considered suggestive and not definitive.


Examples
--------

 . anova y a b a*b
 . sme b a
 . sme a b
 . anova y a s|a b a*b
 . sme a b, dfe(24) sse(18.5)
 
 
Author
------

      Philip B. Ender
      Statistical Computing and Consulting
      UCLA Department of Education
      UCLA Academic Technology Services
      enderatucla.edu  

References
----------

Kirk, R. E. 1982. Experimental Design. 2d ed. Pacific Grove, CA: Brooks/Cole
Dunn, O.J. 1974. On mutiple test and confidence intervals. Communications
     in Statistics, 3, 101-103.  (Cited in Kirk, 1982).
Marascuilo, L.A. and Levin, J.R. 1970. Appropriate post hoc comparisons for
     interactions and nested hypotheses in analysis of variance designs: The
     elimination of type IV errors.  American Educatinal Research Journal,
     7, 397-421.  (Cited in Kirk, 1982).
Marascuilo, L.A. and Levin, J.R. 1976. The simultaneous investigation of inter-
     action and nested hypotheses in two-factor analysis of variance designs.
     American Educatinal Research Journal, 13, 61-65.  (Cited in Kirk, 1982).


Also see
--------

On-line:  help for anova