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

within-subject comparisons in psychoacoustics


I would like to pose a question to the readers of this group on the pros
and cons of doing within-subject analyses. Those of us who researching
psychoacoustics are well aware of the tradition in which individuals are
tested extensively and individual trends in the data are reported rather
than groups effects.

Sometimes ANOVAs and t-tests are conducted on individual subjects to see
if the treatment effect signficantly influenced performance for *that*
subject. However, often, particularly for instance for research on
psychophysical tuning curves, such statistics are not reported. From
consulting with statisticians, I have learned that one problem with
determining statistical significance of within-subject comparisons is
that ANOVA and t-tests require that data-points within each condition
are statistically independent. If all the data in a particular analysis
are provided by one subject then it can be argued that individual data
points within each treatment are no longer independent, and hence not
amenable to ANOVA.

I would be very interested in hearing from other researchers who have
encountered this problem in their experiments and the various approaches
you may have taken to deal with it. I would especially like to hear the
views of those who have conducted significance tests on within-subject
comparisons and the justifications you have for doing so in light of
this apparent violation of the assumptions of ANOVA.

Chris Chambers
Department of Psychology
Monash University
Clayton, Victoria 3168

Tel. +61 3 9905 3978
Fax. +61 3 9905 3948

EMAIL: chris.chambers@sci.monash.edu.au