The determination of the sample size necessary to meet specified significance level and power considerations for multivariate data can be quite difficult. In this paper we propose a quick simple method of approximation. Also included is simulations that indicate the approximation is quite appropriate for bivariate normal data test of the mean vector. © 1989.
Schwertman, N. C., & Owens, M. A. (1989). Simple approximation of sample size for the bivariate normal. Computational Statistics and Data Analysis, 8(2), 201–207. https://doi.org/10.1016/0167-9473(89)90007-8