Factor Analysis and Principal Components Analysis

Author(s):  
Curtis Tatsuoka
2007 ◽  
Vol 100 (2) ◽  
pp. 355-364 ◽  
Author(s):  
Sook-Jeong Lee

The purpose of this study was to examine the psychometric properties of the Specific Interpersonal Trust scale of Johnson-George and Swap in Korean samples as a part of the process of providing an exemplary tool for intercultural studies of trust. A translated version of the original scale was administered to 337 university students (157 males, 180 females) in Seoul, Korea. Data were subjected to a principal components analysis and a confirmatory factor analysis. In principal components analysis for the Korean sample ( n = 167), three factors were identified and labeled: Overall Trust (Cronbach α=.89), Emotional Trust (Cronbach α = .88), and Reliableness (Cronbach α=.84). A confirmatory factor analysis ( n=170) showed that the three-factor model was valid for the sample (χ2/ df= 1.78, RMR=.06, RMSEA = .07, TLI=.92, CFI=.93). Internal consistency reliability and factorial validity were satisfactory in the case of the Korean sample. The Korean version of the Specific Interpersonal Trust Scale made good use of three factors of trust and appeared to be valid without sex differences, while the original scale distinguished the Males subscale from the Females subscale. Implications and limitations of this study were discussed.


2021 ◽  
Vol 13 (37) ◽  
pp. 4188-4219
Author(s):  
Peter D. Wentzell ◽  
Cannon Giglio ◽  
Mohsen Kompany-Zareh

Principal components analysis (PCA) is widely used in analytical chemistry, but is only one type of broader range of factor analysis tools that are described in this article.


1975 ◽  
Vol 37 (3) ◽  
pp. 849-850 ◽  
Author(s):  
David W. Stewart ◽  
G. Mac Griffith

A principal components analysis of Sensation-seeking Scale IV ( n = 156 undergraduates) followed by a varimax rotation provided some support to the factorial validity of some of Zuckerman's subscales. It is suggested that the dimensions of sensation seeking were arbitrarily limited in earlier work on the problem.


2013 ◽  
Vol 34 (3) ◽  
pp. 138-142 ◽  
Author(s):  
Lee Di Milia

The literature suggests limitations to Dickman’s dysfunctional impulsivity (DI) scale. These concerns are centered on the measurement properties of this scale and on its reliance on student samples. To address these criticisms, the DI was administered to a random adult sample (n = 649, mean age 43.83 ± 13.46 years), 13% of whom were university educated. Confirmatory factor analysis (CFA) did not support the fit of the posited 12-item DI scale. The full sample was randomly divided. Principal components analysis was applied to one sample (n = 328), resulting in a 9-item model. This new model was then replicated using CFA in the second sample (n = 321). Cronbach’s α for the 9-item model was 0.84 and item-total correlations were > 0.39. The 30th and 70th percentile scores from the DI distribution of scores were used to categorize participants with low and high DI. The high-DI group was associated with significantly more driving distractions and lane crossings.


Sign in / Sign up

Export Citation Format

Share Document