Premium
Parent attitude research instrument (PARI): Clinical vs. statistical inferences in understanding abusive mothers
Author(s) -
Paulson Morris J.,
Schwemer Gregory T.,
Afifi A. A.,
Bendel R. B.
Publication year - 1977
Publication title -
journal of clinical psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.124
H-Index - 119
eISSN - 1097-4679
pISSN - 0021-9762
DOI - 10.1002/1097-4679(197707)33:3<848::aid-jclp2270330351>3.0.co;2-o
Subject(s) - univariate , psychology , discriminant function analysis , statistical significance , socioeconomic status , multivariate analysis , psychodynamics , developmental psychology , clinical psychology , multivariate statistics , statistics , medicine , psychotherapist , population , mathematics , environmental health
Attitudes toward child rearing and early experiences in childhood traditionally have been regarded as psychodynamic factors that influence adult behavior. The present study assessed the capacity of the Parent Attitude Research Instrument (PARI) to differentiate between court‐identified abusive mothers and a control sample of nonabusive, well‐baby clinic mothers of comparable socioeconomic status. While univariate t ‐tests showed statistical significance for 3 of the 23 PARI scales, more sophisticated and appropriate multivariate tests (Discriminant Function Analysis) demonstrated that the PARI correctly classified the experimental and control S s only 65% of the time. It appears that the PARI alone should not be used to identify potentially abusive mothers. Even more important, the results caution and alert non‐statistically informed clinicians and researchers to the pitfall of over‐interpreting clinical data that are based on the more simple univariate tests of statistical significance.