The Role of Measurement, Some Statistics, and Some Factor Analysis in Family Psychology Research

Family psychologists primarily use descriptive research methods. Important measurement principles involved include the Spearman-Brown formula and the following principles: measurements do not combine simply, reliabilities and restrictions in the range of variables set limits on correlations, regression toward the mean is inherent, and correlations must be corrected for attenuation to be compared. The author notes that all predictions should be made using regression equations; gain scores and quotients of variables pose problems. Covariances (i.e., partial and multiple correlations to "control" variables) usually are underadjustments. Statistical tests of significance are flawed, and the use of factor analyses of test items is generally not a good practice. Sample size and the ratio of the number of participants to the number of variables are important.