Answers are grounded in this paper and cite their sources.
Welch's test for the Behrens-Fisher problem, which tests the equality of means of two normal populations with unknown (possibly unequal) variances, is considered in this paper. The tables of critical regions for Welch's test are of an approximate nature. The errors of the first and second kinds are calculated on computer for this test, using the Gauss-Laguerre quadrature formula. The effects of the discretization and round-off errors in the computation have been eliminated- The values of α and β, the two kinds of errors for Welch's test are tabulated. These tables give a broad picture of the behaviour of Welch's test for different values of the parameters involved.
No takes yet. Share an insight, caveat, or question.
M. B. Golhar (1972) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: