Summary
Assuming that the covariance matrices are circular, we make an appropriate transformation which reduces the circular matrices to canonical forms. The discriminant function is given when the populations are multivariate normal with different circular matrices and its distribution is derived. An asymptotic expansion for the distribution is obtained when all the parameters are unknown.
Similar content being viewed by others
References
Han, C. P. (1969). Distribution of discriminant function when covariance matrices are proportional,Ann. Math. Statist.,40, 979–985.
Hartley, H. O. (1938). Studentization and large-sample theory,J. Roy. Statist. Soc., Suppl.,5, 80–88.
Ito, Koichi (1956). Asymptotic formulae for the distribution of Hotelling's generalizedT 0 2 statistic I,Ann. Math. Statist.,27, 1091–1105; (1960), II,Ann. Math. Statist.,31, 1148–1153.
Okamoto, M. (1963). An asymptotic expansion for the distribution of the linear discriminant function,Ann. Math. Statist.,34, 1286–1301.
Patnaik, D. B. (1949). The non-central χ3 andF-distributions and their applications,Biometrika,36, 202–232.
Siotani, M. (1957). On the distribution of the Hotelling'sT 2-statistics,Ann. Inst. Statist. Math.,8, 1–14.
Wallace, D. L. (1958). Asymptotic approximations to distributions,Ann. Math. Statist.,29, 635–654.
Welch, B. L. (1947). The generalization of ‘Student's’ problem when several different population variances are involved,Biometrika,34, 28–35.
Whittle, P. (1951).Hypothesis Testing in Time Series Analysis, Uppsala, Sweden: Almquist and Wiksells.
Wise, J. (1955). The autocorrelation function and the spectral density function,Biometrika,42, 151–159.
Author information
Authors and Affiliations
Additional information
This research is partially supported by National Institutes of Health Grant No. GM 00034-12.
About this article
Cite this article
Han, CP. Distribution of discriminant function in circular models. Ann Inst Stat Math 22, 117–125 (1970). https://doi.org/10.1007/BF02506327
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02506327