文章基本信息

标题：Calculating non-centrality parameter for power analysis under structural equation modelling: An alternative
本地全文：下载
作者：David Adedia ; Atinuke O. Adebanji ; Simon K. Appiah 等
期刊名称：Pakistan Journal of Statistics and Operation Research
印刷版ISSN：2220-5810
出版年度：2021
卷号：17
期号：1
页码：273-289
DOI：10.18187/pjsor.v17i1.3148
语种：English
出版社：College of Statistical and Actuarial Sciences
摘要：Identifying the most parsimonious model in structural equation modelling is of utmost importance and the appropriate power estimation methods minimize the probabilities of Type I and Type II errors. The power of a test depends on the sample size, Type I error, degrees of freedom and effect size. In this study, a modified approach of using effect size in calculating the non-centrality parameter for power is proposed. This is compared to the approach in Maccallum et al. (1996) at different degrees of freedom and sample size specifications --- taken from 50 to 2000. As the sample size increased the difference between the power of a test for both methods reduced to zero. The results showed that the values for power of a test are the same for the modified and original approaches for large sample sizes and degrees of freedom. The findings also revealed that the sample discrepancy function ($\hat{F}$) is asymptotically unbiased.
关键词：Structural equation modelling; Effect size; Root mean square error approximation; Non-centrality parameter; Power analysis