Bootstrap approach to inference and power analysis based on three test statistics for covariance structure models

摘要: We study several aspects of bootstrap inference for covariance structure models based on three test statistics, including Type I error, power and sample-size determination. Specifically, we discuss conditions a statistic to achieve more accurate level both in theory practice. Details analysis determination are given. For data sets with heavy tails, propose applying methodology transformed sample by downweighting procedure. One the key safe is generally satisfied but may not be original tails. Several illustrate that, combining bootstrapping, researcher find nearly optimal procedure evaluating various models. A rule handling non-convergence problems replications proposed.