Monday, 5 September 2011

Factor analysis and 16PF

Raymond Cattell’s goal in creating the 16PF Questionnaire was to provide a thorough, research-based map of normal personality. Cattell believed in examining the broadest possible range of personality phenomena, including roles and states, thoughts and actions, verbal and nonverbal behavior, normal and abnormal personality, and ability and interest variables.

Allport and Odbert had worked through two of the most comprehensive dictionaries of the English language available at the time, and extracted 18,000 personality-describing words. From this gigantic list they extracted 4500 personality-describing adjectives which they considered to describe observable and relatively permanent traits.

In 1946, Cattell used the computers to analyse the Allport-Odbert list. He organized the list into 181 clusters and asked subjects to rate people whom they knew by the adjectives on the list. Using factor analysis, Cattell generated twelve factors, and then included four factors which he thought ought to appear. The result was the hypothesis that individuals describe themselves and each other according to sixteen different, independent factors. With these sixteen factors as a basis, Cattell went on to construct the 16PF Personality Questionnaire. These 16 traits were called “Primary Traits”. These were warmth, reasoning, emotional stability, dominance, lieliness, rule- consciousness, social boldness, sensitivity, vigilance, abstractedness, privateness, apprehension, openness to change, self- reliance, perfectionism, tension.

Cattel then factored these primary traits (i.e., performed a second-order factor analysis) and discovered a smaller number of over-arching personality factors or domains that provided the overall structure and meaning for the primary traits. He labelled these Second-Order or Global Factors. For example, Extraversion was found to be a Global Factor that contained primary factors Warmth/Reserve(A), Social Boldness/Shyness (H), Liveliness/Seriousness (F), Group-Orientation/Self-Sufficiency (Q2), and Forthrightness/Privatness (N)

In the original Fourth and Fifth Editions of the 16PF, there were five global factors that correspond fairly closely to the later "Big Factor" (BF): BF Openness => 16PF Openness/Tough-mindedness; BF Conscientiousness => 16PF Self-Control; BF Extraversion => 16PF Extraversion; BF Agreeableness/Dis-Agreeablenss => 16PF Independence/Accommodation; and BF Neuroticism => 16PF Anxiety (Conn & Rieke, 1994). In fact, the development of the Big-Five factors began by factor-analyzing the original items of the 16PF.

However, one big technical difference between Cattell's five Global Factors and popular Five-Factor models was Cattell's insistence on using scientific, oblique rotations, whereas Goldberg and Costa & McCrae used orthogonal rotations. Oblique rotation allows the factors to locate and define themselves, whereas orthogonal rotation forces the factors to arbitrarily be unrelated to each other (at 90 degrees to each other)--a quality which is true of very few known personality traits. However, this makes the factors easier to agree upon and to work on statistically in research. This forced the Big-Five traits into somewhat skewed definitions compared to the 16PF Global factors. For example, in Cattell's model, the basic personality trait of Dominance (Factor E) is strongly located in the Independence/Accommodation Factor (i.e., Big-Five Agreeableness) which represents a quality of fearless, original thinking and forceful, independent actions. However, other popular big five models consider Dominance as a facet of several Big-Five traits, including Extraversion, Dis-Agreeableness, and Conscientiousness. Thus Dominance is spread very thinly across a range of Big-Five factors with little influence on any one.


Group- HR1

Author- Harshada Thakurdesai

No comments:

Post a Comment