Premium
A Comparison of Significance‐Testing Procedures for Parent–Child Correlations Computed from Family Data
Author(s) -
Donner Allan,
Bull Shelley
Publication year - 1984
Publication title -
journal of the royal statistical society: series c (applied statistics)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.205
H-Index - 72
eISSN - 1467-9876
pISSN - 0035-9254
DOI - 10.2307/2347704
Subject(s) - psychology , computer science , statistics , developmental psychology , mathematics
SUMMARY Procedures are studied for testing the statistical significance of a parent–child correlation coefficient, ρ ab , computed from data having a variable number of siblings per family. It is demonstrated that a simple and reasonably powerful test is obtained by comparing the pairwise estimator r p to the value of its large sample standard error and referring to tables of the standard normal distribution. This test procedure compares favourably to the likelihood ratio test in studies having as few as 25 families, especially for low values of ρ ab .