Exploratory Factor Analysis With Small Sample Sizes

TLDR

Exploratory factor analysis is conventionally considered reliable only with large samples, typically requiring at least 50 observations. This study systematically examines the sample size thresholds that allow EFA to produce reliable results when N is below 50. Through extensive simulations varying loadings, factor numbers, and variable counts, and by evaluating pattern congruence, factor score correlations, Heywood cases, and eigenvalue gaps—alongside a subsampling analysis of a Big Five Internet survey—the authors estimate the minimal N needed under different distortion scenarios. The results indicate that with well‑conditioned data (high loadings, few factors, many variables), EFA can yield trustworthy outcomes even for N far below 50, though such favorable conditions are relatively rare in behavioral research.

Abstract

Exploratory factor analysis (EFA) is generally regarded as a technique for large sample sizes (N), with N = 50 as a reasonable absolute minimum. This study offers a comprehensive overview of the conditions in which EFA can yield good quality results for N below 50. Simulations were carried out to estimate the minimum required N for different levels of loadings (λ), number of factors (f), and number of variables (p) and to examine the extent to which a small N solution can sustain the presence of small distortions such as interfactor correlations, model error, secondary loadings, unequal loadings, and unequal p/f. Factor recovery was assessed in terms of pattern congruence coefficients, factor score correlations, Heywood cases, and the gap size between eigenvalues. A subsampling study was also conducted on a psychological dataset of individuals who filled in a Big Five Inventory via the Internet. Results showed that when data are well conditioned (i.e., high λ, low f, high p), EFA can yield reliable results for N well below 50, even in the presence of small distortions. Such conditions may be uncommon but should certainly not be ruled out in behavioral research data.