Listy Biometryczne - Biometrical Letters Vol. 33(1996), No. 1, 25-31
|
ASYMPTOTICALLY NORMAL DISTRIBUTIONS IN THE MULTIVARIATE GAUSS-MARKOFF MODEL Wiktor Oktaba Agricultural University of Lublin Akademicka 13, 20-934 Lublin, Poland |
Explicit formulas for asymptotically normal distributions of three random variables involving determinants of sums of squares and products matrices for error, hypothesis and "total" and the determinant of the matrix <7252 in the multinomial Gauss-Markoff model with the covariance matrix cr2S ® V are given. By applying these results the asymptotically normal confidence intervals for 0"253 on the basis of three sums of squares and products matrices are presented.
digamma and trigamma function, multivariate gamma function, Euler's constant, standard multivariate distribution, asymptotical normality, determinant, confidence interval, Wishart distribution
