I will be doing ryff's psychological well-being scale for psychometric properties. What would be the minimum sample size for factor analysis using spss? I read Slovin's formula is not reliable?
Bruce Thompson's Exploratory and Confirmatory Factor Analysis (APA, 2004) says that it depends on the factor loadings. If factors are defined by four or more measured variables with structure coefficients < .60, then the sample size if not important (N = 60 is adequate). If factors are defined with 10 or more structure coefficients each around .40, then the sample size should be at least 150. Any sample size over 300 is considered adequate.
Comrey and Lee (1992) provided the following advise regarding sample size: 50 cases is very poor, 100 is poor, 200 is fair, 300 is good, 500 is very good, and 1,000 or more is excellent. As a rule of thumb, a minimum of 10 observations per variable is necessary to avoid computational difficulties.
It depends on the number of variables number of factors and the loadings. I'm less convinced that there is a level of n one could consider always adequate, If there is a complex factor structure and noisy data then I imagine that 300 might be far too low.
For Confirmatory Factor Analysis it is atleast 10 times the number of measure items. However for Exploratory Factor analysis it is subjected to the number of variables, factor structure and loading
From my experience, should be at least 10 times the number of variables.
10 observations per variable is necessary to avoid computational difficulties. https://stats.idre.ucla.edu/spss/output/factor-analysis/
- Badges
- Science topic
- Similar topics
- Psychology
- Psychometrics