Common methodological problems in factor analytic studies.

Comrey, Andrew L.

doi:10.1037/0022-006x.46.4.648

Cited by 427 publications

(259 citation statements)

References 10 publications

Supporting

Mentioning

240

Contrasting

Unclassified

Order By: Relevance

“…On the contrary, both the "less severe" and "more severe" aggressive behaviors occurred far more frequently in the clinic sample (see Tables 1 and II). It is suggested that the failure of items 16 and 17 to load on the Physical Aggression factor in the nonclinic sample may be due to the infrequency with which they are endorsed (see Table III) (Comrey, 1978). In situations (e.g., such as a sample seeking marital therapy) where there are sufficient endorsements of these two behaviors, and hence adequate variability, these two factors do load on the Physical Aggression factor.…”

Section: Discussionmentioning

confidence: 99%

“…First, as noted previously, items 16 and 17 exhibited very little variance due to their infrequent occurrence. If the few subjects endorsing one of the life threatening behaviors also endorse the other two, a homogeneous factor would emerge (see Comrey, 1978). Given the amount of information relevant to the factor analysis not contained in the Hornung et al (1981) report, the possibility that this accounts for their Life Threatening Behavior factor cannot be excluded.…”

Section: Discussionmentioning

confidence: 99%

“…As a result, it is important to factor analyze data from the CTS for individuals with higher base rates of marital aggression. Third, neither Straus (1979), Schumm et al (1982), nor Hornung et al (1981) provide data [e.g., eigenvalues, communalities; and in some case, also item loadings (e.g., Hornung et al, 1981;Jorgensen, 1978;Schumm et aL, 1982)] normally required to facilitate conclusions from factor analytic data (Comrey, 1978;Maher, 1978). To enhance the generalizability of any findings, the present two studies are conducted on diverse samples.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Factor similarity of the Conflict Tactics Scales across samples, spouses, and sites: Issues and implications

et al. 1987

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Factor similarity of the Conflict Tactics Scales across samples, spouses, and sites: Issues and implications

et al. 1987

View full text Add to dashboard Cite

“…The method of squared multiple correlations was used for computing prior communality estimates. 23 Orthogonal (varimax) as well as oblique (promax) rotations were explored in the analyses. The scree test was used to determine the number of factors to be retained.…”

Section: Psychometric Analysis Proceduresmentioning

confidence: 99%

Psychometric properties and factor structure of the Three-Factor Eating Questionnaire (TFEQ) in obese men and women. Results from the Swedish Obese Subjects (SOS) study

et al. 2000

View full text Add to dashboard Cite

OBJECTIVE: To evaluate the construct validity of the Three-Factor Eating Questionnaire (TFEQ) in obese men and women. SUBJECTS: A total of 4377 middle-aged, obese subjects in the Swedish Obese Subjects (SOS) study. METHODS: The total sample was randomly split into two data subsets and psychometric testing was performed separately in each sample. Multitraitamulti-item analysis was conducted to test scaling assumptions and factor analysis was used to test the factor structure. Measures of mental well-being (MACL, HAD) were used for testing criterion-based validity. RESULTS: The Cognitive Restraint factor was consistently reproduced and scaling analysis demonstrated strong itemscale discriminant validity, while the item-scale convergent validity was unsatisfactory. The internal structure of the Disinhibition scale was weak. Most Disinhibition and Hunger items grouped in one global factor labeled Uncontrolled Eating. A third cluster containing items on Emotional Eating was also identi®ed. The obtained three-factor structure was cross-validated and replicated across subgroups by gender, age and BMI. CONCLUSION: The original TFEQ factor structure was not replicated. A short, revised 18-item instrument was constructed, representing the derived factors of Cognitive Restraint, Uncontrolled Eating and Emotional Eating. The most ef®cient items were used to boost both the convergent and discriminant validity of the scales.

show abstract

“…The most widely used rule uses the ratio of the number of subjects (N) to the number of items (p), and this varies from three to 10 depending on authors (Cattell, 1978;Everitt, 1975;Gorsuch, 1983;Nunnaly, 1978). Other authors have suggested an absolute minimum sample size of 50 to 500 to enable factor analysis (Aleamoni, 1973;Comrey, 1978;Comrey et al, 1992;Loo, 1983). Given these various recommendations and their lack of documented explanation, some researchers have put them to the test by studying the consequences of using factor analysis on insufficient sample sizes.…”

Section: Introductionmentioning

confidence: 99%

Sample size requirements for the internal validation of psychiatric scales

Rouquette

Falissard

2011

Int J Methods Psych Res

201

121

View full text Add to dashboard Cite

To cite this version:Alexandra Rouquette, Bruno Falissard. Sample size requirements for the internal validation of psychiatric scales.. International Journal of Methods in Psychiatric Research, Wiley, 2011, 20 (4) Abstract:The ratio of subjects to variables (N/p), as a rule to calculate the sample size required in internal validity studies on measurement scales, has been recommended without any strict theoretical or empirical basis being provided. The purpose of the present study was to develop a tool to determine sample size for these studies in the field of psychiatry. First, a literature review was carried out to identify the distinctive features of psychiatric scales. Then, two simulation methods were developed to generate data according to: 1/ the model for factor structure derived from the literature review and 2/ a real dataset. This enabled the study of the quality of solutions obtained from principal component analysis or Exploratory Factor Analysis (EFA) on various sample sizes. Lastly, the influence of sample size on the precision of Cronbach"s alpha coefficient was examined. The N/p ratio rule is not upheld by this study: short scales do not allow smaller sample size. As a rule of thumb, if one"s aim is to reveal the factor structure, a minimum of 300 subjects is generally acceptable but should be increased when the number of factors within the scale is large, when EFA is used and when the number of items is small.

show abstract

Common methodological problems in factor analytic studies.

Cited by 427 publications

References 10 publications

Factor similarity of the Conflict Tactics Scales across samples, spouses, and sites: Issues and implications

Factor similarity of the Conflict Tactics Scales across samples, spouses, and sites: Issues and implications

Psychometric properties and factor structure of the Three-Factor Eating Questionnaire (TFEQ) in obese men and women. Results from the Swedish Obese Subjects (SOS) study

Sample size requirements for the internal validation of psychiatric scales

Contact Info

Product

Resources

About