THE IMPACT OF PRELIMINARY MODEL SELECTION ON LATENT GROWTH MODEL PARAMETER ESTIMATES
Hancock, Gregory R
MetadataShow full item record
In latent growth modeling (LGM), model selection and inference are treated as separate stages of data analysis, but they are generally conducted on the assumption that the model is known a priori and thus model selection and inference are performed on the same data set. This two-step process ignores the effects of model uncertainty on parameter estimation and statistical inference, and thus may result in problems which ultimately lead to misleading or invalid inferences. This present study was thus designed to investigate the possible problems arising from the use of the two-step process in LGM. The goals of this study were: (1) To examine the subsequent impact of preliminary model selection using information criteria on LGM parameter estimates; (2) To assess the data splitting method as a possible way to mitigate the effects of model uncertainty. To achieve these goals, two Monte Carlo simulation studies were conducted. Study1 conducted both model selection and parameter estimation using the same data set, to investigate the possible impact of preliminary model selection in terms of relative parameter biases, and coverage rate. Study 2 conducted model selection and parameter estimation using different split-data sets, in order to assess the data splitting method as a possible way to mitigate the effects of model uncertainty. The major finding of this study was that inference based on the AIC or the BIC model selection leads to additional bias in the estimates and overestimates the sampling variability of the parameters estimates. The results of the simulation study showed that the post-model-selection parameter estimator has larger relative parameter biases, larger relative variance biases, and smaller coverage rate of confidence interval than those of the pre-model-selection estimator. These post-model-selection problems due to model uncertainty, unfortunately, still existed when the data splitting method was applied.