The Annals of Statistics

Unbiasedness of Invariant Tests for Manova and Other Multivariate Problems

Michael D. Perlman and Ingram Olkin

Full-text: Open access


Let $Y:p \times r$ and $Z:p \times n$ be normally distributed random matrices whose $r + n$ columns are mutually independent with common covariance matrix, and $EZ = 0$. It is desired to test $\mu = 0$ vs. $\mu \neq 0$, where $\mu = EY$. Let $d_1, \cdots, d_p$ denote the characteristic roots of $YY'(YY' + ZZ')^{-1}$. It is shown that any test with monotone acceptance region in $d_1, \cdots, d_p$, i.e., a region of the form $\{g(d_1, \cdots, d_p)\leq c\}$ where $g$ is nondecreasing in each argument, is unbiased. Similar results hold for the problems of testing independence of two sets of variates, for the generalized MANOVA (growth curves) model, and for analogous problems involving the complex multivariate normal distribution. A partial monotonicity property of the power functions of such tests is also given.

Article information

Ann. Statist., Volume 8, Number 6 (1980), 1326-1341.

First available in Project Euclid: 12 April 2007

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier


Primary: 62H10: Distribution of statistics
Secondary: 62H15: Hypothesis testing 62H20: Measures of association (correlation, canonical correlation, etc.) 62J05: Linear regression 62J10: Analysis of variance and covariance

Unbiasedness of invariant multivariate tests monotonicity of power functions noncentral Wishart matrix characteristic roots maximal invariants noncentral distributions hypergeometric function of matrix arguments stochastically increasing MANOVA growth curves model testing for independence canonical correlations complex multivariate normal distribution FKG inequality HPKE inequality positively associated random variables pairwise total positivity of order two rectangular coordinates


Perlman, Michael D.; Olkin, Ingram. Unbiasedness of Invariant Tests for Manova and Other Multivariate Problems. Ann. Statist. 8 (1980), no. 6, 1326--1341. doi:10.1214/aos/1176345204.

Export citation