In a recent article, Trafimow suggested the usefulness of imagining an ideal universe where the only difference between original and replication experiments is the operation of randomness. This contrasts with replication in the real universe where systematicity, as well as randomness, creates differences between original and replication experiments. Although Trafimow showed (a) that the probability of replication in the ideal universe places an upper bound on the probability of replication in the real universe, and (b) how to calculate the probability of replication in the ideal universe, the conception is afflicted with an important practical problem. Too many participants are needed to render the approach palatable to most researchers. The present aim is to address this problem. Embracing skewness is an important part of the solution.
The inverse coefficient of variation (ICV) has gained significant attention as a preferred measure in fields such as economics, healthcare, and clinical trials. This makes it desirable for researchers to determine appropriate sample sizes when using sample-based estimators to estimate the population ICV. In this paper, we derive both the moment and Bayes estimators of the ICV under a skew-normal distribution, and use them to develop equations for sample size determination based on the A Priori Procedure (APP). The multivariate skew-normal model introduces a flexible dependence structure through its shape parameters, allowing correlation patterns that cannot be captured by the standard multivariate normal model. This dependence directly affects the behavior of the ICV estimators and plays an important role in determining the required sample sizes, highlighting the benefits of jointly modeling skewness and dependence. We further construct confidence intervals and evaluate their coverage probabilities via Monte Carlo simulations. Finally, a real-world dataset is analyzed to illustrate the practical applicability of the proposed methodology.
The a priori procedure (APP) is concerned with determining appropriate sample sizes to ensure that sample statistics to be obtained are likely to be good estimators of corresponding population parameters. Previous researchers have shown how to compute a priori confidence interval means or locations for normal and skew-normal distributions. However, two critical limitations persist in the literature: (1) While numerous skewed models have been proposed, the APP equations for location parameters have only been formally established for the basic skew-normal distributions. (2) Even within this fundamental framework, the APPs for sample size determinations in estimating locations are constructed on samples of specifically dependent observations having multivariate skew-normal distributions jointly. Our work addresses these limitations by extending a priori reasoning to the more comprehensive unified skew-normal (SUN) distribution. The SUN family not only encompasses multiple existing skew-normal models as special cases but also enables broader practical applications through its capacity to model mixed skewness patterns and diverse tail behaviors. In this paper, we establish APP equations for determining the required sample sizes and set up confidence intervals for the location parameter in the one-sample case, as well as for the difference in locations in matched pairs and two independent samples, assuming independent observations from the SUN family. This extension addresses a critical gap in the literature and offers a valuable contribution to the field. Simulation studies support the equations presented, and two applications involve real data sets for illustrations of our main results.