New test for equal variances more robust than traditional methods.
The article presents new tests for checking if variances are equal in different groups of data. These tests are compared to the commonly used Bartlett test, which is known to have limitations. The new tests are shown to be more robust when assumptions about the data distribution are not met, and they have good power in large samples. The researchers suggest using the new tests as an alternative to the Bartlett test for more reliable results.
