Whether "more is ever too much" for the number of indicators (p) per factor (p/f) in confirmatory factor analysis (CFA) was studied by varying sample size (N) from 50 to 1,000 and p/f from 2 to 12 items per factor in 30,000 Monte Carlo simulations. For all sample sizes, solution behavior steadily improved (more proper solutions and more…

Monte Carlo methods were used to evaluate an EM algorithm used for the correction of missing data in latent class analysis. Findings regarding bias in parameter estimates suggest practical limits for the utility of the EM algorithm in terms of sample size and nonresponse rate. (SLD)

Monte Carlo methods were used to investigate the effect of misspecification of the second level in a two-level hierarchical linear model (HLM). Sample composition, heterogeneity of the group size, level of intraclass correlation, and correlation between second-level predictors were manipulated. Each of 20 generated data sets was analyzed nine…

Effectiveness of jackknife methods in reducing bias in estimation of the log-1 autocorrelation parameter p1 was evaluated through a Monte Carlo study using sample sizes ranging from 6 to 500. These estimates appear less biased in the small sample case than many that have been investigated recently. (SLD)

The behavior of eight measures of fit used to evaluate confirmatory factor analysis models was studied through Monte Carlo simulation to determine the extent to which sample size, model size, estimation procedure, and level of nonnormality affect fit when analyzing polytomous data. Implications of results for evaluating fit are discussed. (SLD)

A Monte Carlo study was conducted to examine the performance of several strategies for estimating the squared cross-validity coefficient of a sample regression equation in the context of best subset regression. Results concerning sample size effects and the validity of estimates are discussed. (TJH)

The accuracy of four empirical techniques to estimate shrinkage in multiple regression was studied through Monte Carlo simulation. None of the techniques provided unbiased estimates of the population squared multiple correlation coefficient, but the normalized jackknife and bootstrap techniques demonstrated marginally acceptable performance with…

Two measures of association between sets of variables have been proposed for set correlation: the proportion of generalized variance, and the proportion of additionive variance. Because these measures are strongly positively biased, approximate expected values and estimators of these measures are derived and checked. (Author/BW)

Using computer simulation data, the effect of a single global outlier in two-group classification analysis was explored in terms of the outcome variables of change in classification results (PCHNG), change in misclassification rate (MISDIF), and change in precision of misclassification rate estimation. The precision of misclassification rate…

This paper empirically and systematically assessed the performance of bootstrap resampling procedure as it was applied to a regression model. Parameter estimates from Monte Carlo experiments (repeated sampling from population) and bootstrap experiments (repeated resampling from one original bootstrap sample) were generated and compared. Sample…

Using a Monte Carlo simulation, a bootstrap procedure was evaluated for setting a confidence interval on the unrestricted population correlation (rho) assuming various degrees of incomplete truncation on the predictor. Sample size was the most important factor in determining accuracy and stability. Sample size should be at least 50. (SLD)

The bias and relative efficiency of two alternative estimators of optimal weights in meta-analysis were assessed through Monte Carlo simulation, defining the standardized mean differences as the effect-size index. The estimator proposed by L. Hedges and I. Olkin (1985) was more efficient than that of J. Hunter and F. Schmidt (1990). (SLD)

A Monte Carlo simulation study investigated the effects on 10 structural equation modeling fit indexes of sample size, estimation method, and model specification. Some fit indexes did not appear to be comparable, and it was apparent that estimation method strongly influenced almost all fit indexes examined, especially for misspecified models. (SLD)

Investigated the assumption that determining an adequate sample size in structural equation modeling can be aided by considering the number of parameters to be estimated. Findings from maximum likelihood confirmatory factor analysis support previous research on the effect of sample size, measured variable reliability, and the number of measured…

A Monte Carlo simulation study was conducted to investigate the effects of sample size, estimation method, and model specification on structural equation modeling (SEM) fit indices. Based on a balanced 3x2x5 design, a total of 6,000 samples were generated from a prespecified population covariance matrix, and eight popular SEM fit indices were…