Ne. Turner, THE EFFECT OF COMMON VARIANCE AND STRUCTURE PATTERN ON RANDOM DATA EIGENVALUES - IMPLICATIONS FOR THE ACCURACY OF PARALLEL ANALYSIS, Educational and psychological measurement, 58(4), 1998, pp. 541-568
Selecting the correct number of factors to retain in a factor analysis
is a crucial step in developing psychometric tools or developing theo
ries. The present study assessed the accuracy of parallel analysis, a
technique in which the observed eigenvalues are compared to eigenvalue
s from simulated data in which no real factors are present. Study 1 in
vestigated the effect of the presence of one real factor on the size o
f subsequent noise eigenvalues. The size of real factors and the sampl
e size were manipulated. Study 2 examined the effect that the pattern
of structure coefficients and continuousness of the variables have on
the size of real and noise eigenvalues. Study 3 compared the results o
f Studies 1 and 2 to actual psychometric data. These examples illustra
te the importance of modeling the data more closely when parallel anal
ysis is used to determine the number of real factors.