S. Takayanagi et N. Cliff, An examination of graduate students' statistical judgments: Statistical and fuzzy set approaches, PSYCHOL REP, 86(1), 2000, pp. 243-259
The present study examined how statistical significance levels are treated
and interpreted by graduate students who use hypothesis-testing in their sc
ientific investigation. To rest underlying psychological aspects of hypothe
sis-testing, the idea of fuzzy set theory was employed to identify the unce
rtain points in judgments. 34 graduate students in a psychology department
made judgments about hypothetical statistical decisions. The results indica
ted that (1) the majority of these students treated significance levels on
a continuum and rated them according to the magnitude of statistical signif
icance; (2) the subjects shifted their decisions based on the types of hypo
thetical scenarios but not by the sample sizes; instead, they interpreted a
smaller sample size as being less reliable. (3) The subjects frequently ch
ose formally used statistical terms, e.g., Significant and Not Significant,
more than graduated verbal expressions, e.g., Marginally Significant and B
orderline Significant; and (4) the Fuzziness (degree of confidence in decis
ion-making) was dependent on individuals and existed more in the critical p
oints of transition where judgments are most difficult. The Fuzziness Index
illustrated the subtle shifts of human decision-making patterns in statist
ical judgments. Underlying decision uncertainties and difficulties can be i
llustrated by functions generated from fuzzy set theory, which may more clo
sely resemble human psychological mechanism. This integrative study of fuzz
y set theory and behavioral measurements appears to provide a technique tha
t is more natural for examining and understanding imprecise boundaries of h
uman decisions.