The Effect of Sample Size on Latent Growth Models.

A Monte Carlo simulation approach was taken to investigate the effect of sample size on a variety of latent growth models. A fully balanced experimental design was implemented, with samples drawn from multivariate normal populations specified to represent 12 unique growth models. The models varied factorially by crossing number of time points, variance of intercept factor, and variance of slope factor. Simulation results show that sample size was found to influence the convergence rates of the models, with larger samples resulting in fewer improper estimates and failures. However, this effect is lessened if the variances of the slope and intercept factors are low. It is also lessened when more timepoints are added to the model. This research reinforces previous findings on the importance of sample size used in latent models. The paper also makes recommendations about sample size for researchers hoping to use latent growth models. (Contains 7 tables, 6 figures, and 15 references.) (SLD)