Comparison of Two Methods to Identify Major Personality Factors

Abstract

Both Howarth and Comrey have developed taxon omies of personality traits and inventories to measure them. The Howarth Personality Questionnaire and Ad ditional Personality Factor inventories include 20 fac tors, whereas the Comrey Personality Scales (CPS) taxonomy includes eight factors. Howarth identified his factors through factor analysis of items, whereas Comrey identified his primary level factors through factor analysis of conceptually distinct clusters of ho mogeneous items, called Factored Homogeneous Item Dimensions (FHIDs), while avoiding the inclusion of highly redundant variables in the same analysis. Data for all three inventories were collected from the same subjects and factor analyzed. The Howarth factor scales were narrower in content and more highly over lapping than the CPS factor scales. Most of the Ho warth factor scales were good marker variables for the CPS primary factors. Five CPS factors had major loadings for more than one of the Howarth factor scales. The CPS Emotional Stability vs. Neuroticism (S) primary level factor was split into several lower level factors in the Howarth system. Factor analysis of items is recommended to identify FHIDs. Factor anal ysis of FHIDs, in which no two FHIDs are merely al ternate forms of the same conceptual variable, is rec ommended to identify the major primary factors of personality.

Why item parcels are (almost) never appropriate: Two wrongs do not make a right—Camouflaging misspecification with item parcels in CFA models.

“…However, this assessment was based on knowledge of population generating models in which some of the items representing each factor had zero cross-loadings in the population generating model and were the target items in the target rotation. Although it is common in factor analysis for several of the indicators to serve as “markers” of the factor (e.g., Cattell, 1949; Comrey, 1984; Gallucci & Perugini, 2007; Howarth, 1972; Overall, 1974), this is clearly not the case in all situations, and the target rotation would not be expected to perform as well—at least in terms of accurately estimating the true population correlation. However, we also note that this assumption is far less extreme than the ICM-CFA model that assumes that all items have zero factor loadings on all factors other than the one they are designed to measure (i.e., that the unidimensionality assumption is met).…”

Factor analysis and scale revision.

“…An overinclusive item pool with multiple items representing different aspects of a construct also achieves a second goal, which is the creation of facet scales, item parcels (Cattell & Burdsal, 1975;Kishton & Widaman, 1994), homogeneous item composites (Hogan, 1983), or factored homogeneous item dimensions (FHID; Comrey, 1984Comrey, , 1988. Many authors who have written on factor analysis and scale construction or revision emphasize the importance of creating multi-item homogeneous item clusters.…”

The Validity of Eysenck’s Neuroticism Dimension within the Minnesota Multiphasic Personality Inventory in Patients with Duodenal Ulcer

“…Factor analytic studies have shown that many of the items in MMPI are overlapping with fewer factors than the number of subscales recommended [7]. Thus, Comprey [9] found by factor analy sis that a neurotic factor was among the three most important factors in MMPI. In contrast to MMPI, the Eysenck Neuroticism Scale was developed due to its stable factor structure [10], In a Danish validity study [11] the Ey senck Neuroticism Scale correlated highly with a global assessment of character neurosis performed by an experienced psychiatrist.…”