This analysis compares modality tests on size and power in data for bimodality, indicating the Silverman test performs best.
In this paper, the Robertson’s and Fryer’s (1969) conditions are applied for the existence of bimodality in the mixture of normals. Best modality test is the pre-requisite to evaluate whether the existing data is a unimodal or bimodal. On the same data the researchers also assessed the bimodality through modality tests. For this purpose the modality tests are compared on size and power properties designed by Monte Carlo simulation. After using the simulated critical values, the results showed that the entire modality tests have stable sizes. In power assesment, mostly the Silverman Bandwidth test was found the best test.
No takes yet. Share an insight, caveat, or question.
Shah et al. (2023) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: