An empirical comparison of alternative methods for principal component extraction

Hubbard, Raymond; Allen, Stuart J.

doi:10.1016/0148-2963(84)90047-x

Cited by 107 publications

(68 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Parallel Analysis also indicated a two-factor solution. Parallel Analysis has shown to be the most accurate in choosing the number of components to retain, with both Kaiser's criterion and Catell's Scree Test tending to overestimate the number of components (Zwick and Velicer, 1986;Hubbard and Allen, 1987). Therefore the original scoring structure as suggested by the Y-BOCS authors provides the optimal fit in the present sample.…”

Section: Discussionmentioning

confidence: 90%

Factor structure of the Yale–Brown Obsessive–Compulsive Scale (Y-BOCS) in a large sample of patients with schizophrenia or related disorders and comorbid obsessive–compulsive symptoms

Boyette

Swets

Meijer

et al. 2011

Psychiatry Research

View full text Add to dashboard Cite

a b s t r a c t a r t i c l e i n f oIn the past decade there has been an increasing interest in the levels of obsessive-compulsive symptoms (OCS) found in patients with schizophrenia or related disorders. The widely acknowledged gold standard measure of the severity of OCS is the content-free version of the Yale-Brown Obsessive-Compulsive Scale (Y-BOCS) (Goodman et al., 1989a,b). However, factor analytic research in patients with obsessive-compulsive disorder (OCD) provided varied results. So far no study has been conducted on the factor structure of the Y-BOCS in patients with schizophrenia. The present study addresses this issue. We administered the Y-BOCS in a sample of 217 patients with schizophrenia or related disorders and comorbid OCS who participated in a multicentre cohort study. We used principal component analysis (PCA) to explore the underlying factor structure. A two-factor solution consistent with the originally proposed scoring structure of the Y-BOCS provided the optimal fit. We also found some support for a three-factor solution consistent with earlier findings by Kim et al. and Moritz et al. (Kim et al., 1994;Moritz et al., 2002). The produced factors showed good reliability and strong correlations with the Y-BOCS Total score. However, the resistance to compulsion item failed to demonstrate adequate correlation to the Total score, a finding consistent with earlier findings in several studies with patients with OCD.

show abstract

Section: Discussionmentioning

confidence: 90%

Factor structure of the Yale–Brown Obsessive–Compulsive Scale (Y-BOCS) in a large sample of patients with schizophrenia or related disorders and comorbid obsessive–compulsive symptoms

Boyette

Swets

Meijer

et al. 2011

Psychiatry Research

View full text Add to dashboard Cite

show abstract

“…Retention of factors was determined according to three criteria: Kaiser's (1958) criterion (eigenvalues >1), inspection of the scree plot, and Horn's parallel analysis (1965), using the software developed by Watkins (2000). Hubbard and Allen (1987) suggest that parallel analysis is one of the most accurate methods, comparing the size of eigenvalues from principal components analysis to ones randomly generated from a data set of the same size, and retaining factors with eigenvalues exceeding those from the random data set.…”

Section: Factor Analysis Of the Testicular Selfexamination Questionnairementioning

confidence: 99%

Testicular Self-Examination in an Adult Community Sample

2010

View full text Add to dashboard Cite

The study investigated the impact of relationship status on participants' knowledge of testicular cancer and their current and planned testicular self-examination (TSE) behavior. Adult male civil servants (N = 188) were recruited in the northwest of the United Kingdom (mean age = 33.37 years, SD = 10.77). The survey instrument asked about current and intended TSE practice, knowledge of testicular cancer, as well as attitudes and beliefs toward testicular cancer and self-examination. Factor analysis identified five factors equating to the benefits of TSE, fear, perceived risk, knowledge, and fatality. In logistic regression models, the benefits of TSE, fear, and knowledge significantly predict current TSE behaviors, whereas the benefits of TSE and perceived risk predicted future TSE intentions. Models predicting TSE practice differed according to relationship status. The findings suggest that strategies designed to promote TSE should be sensitive to individual differences in the influences on a person's motivation to engage in TSE.

show abstract

“…The number of factors to be retained was guided by three decision rules: Kaiser's criterion (eigenvalues >1), inspection of the scree plot, and use of Horn's (1965) parallel analysis. Parallel analysis is among the most accurate approaches to estimating the number of components (Hubbard & Allen, 1987;Zwick & Velicer, 1986). The eigenvalues obtained from PCA are compared with those obtained from a randomly generated data set of the same size (Watkins, 2000).…”

Section: Discussionmentioning

confidence: 99%

Initial Development of the Health Promoting Activities Scale to Measure the Leisure Participation of Mothers of Children With Disabilities

Bourke-Taylor

Law

Howie

et al. 2012

The American Journal of Occupational Therapy

View full text Add to dashboard Cite

OBJECTIVE. The Health Promoting Activities Scale (HPAS) measures the frequency with which mothers participate in self-selected leisure activities that promote health and well-being. We undertook an initial evaluation of the scale with mothers of school-age children with developmental disabilities (N = 152). METHOD. We used a mixed methodology in the instrument design: a qualitative study to generate items and a quantitative study to evaluate the instrument. Our statistical analysis assessed the internal consistency, factor structure, and construct validity of the HPAS. RESULTS. The HPAS showed good internal consistency (Cronbach’s α = .78). Construct validity was supported by moderate correlations with subjective maternal mental and general health (Short Form 36, Version 2) and by differentiation in leisure participation among groups of mothers reporting differences in mental health status. CONCLUSION. Initial evaluation of the HPAS indicates that this brief tool is psychometrically sound. The HPAS allows professionals to evaluate clients’ participation in leisure occupations that promote health and well-being. Further development of the HPAS is warranted.

show abstract

An empirical comparison of alternative methods for principal component extraction

Cited by 107 publications

References 36 publications

Factor structure of the Yale–Brown Obsessive–Compulsive Scale (Y-BOCS) in a large sample of patients with schizophrenia or related disorders and comorbid obsessive–compulsive symptoms

Factor structure of the Yale–Brown Obsessive–Compulsive Scale (Y-BOCS) in a large sample of patients with schizophrenia or related disorders and comorbid obsessive–compulsive symptoms

Testicular Self-Examination in an Adult Community Sample

Initial Development of the Health Promoting Activities Scale to Measure the Leisure Participation of Mothers of Children With Disabilities

Contact Info

Product

Resources

About