zbMATH — the first resource for mathematics

Estimation of \(\Pr (a'x>b'y)\) in the multivariate normal case. (English) Zbl 0699.62053
Summary: We consider two non-independent random vectors \(x_{p\times 1}\) and \(y_{q\times 1}\) having multivariate normal distribution and obtain the maximum likelihood and the minimum variance unbiased estimates of \(R=\Pr (a'x>b'y)\) where a and b are two known vectors.
The problem arises, for example, in a system where the energy is supplied to the system by p sources and is consumed through q sources. Some interesting special cases are deduced. A simulation study was carried out to compare the MVUE and MLE of R. An application is provided to determine the effect of a certain drug on the level of biochemical compounds found in the brain.

62H12 Estimation in multivariate analysis
62P10 Applications of statistics to biology and medical sciences; meta analysis
Full Text: DOI
[1] Bajlton D. E, Biometrika 48 pp 227– (1961)
[2] DOI: 10.2307/1267350 · Zbl 0195.20001
[3] DOI: 10.2307/1266860 · Zbl 0262.62016
[4] Govindabajulu Z., Sankhya 29 pp 35– (1967)
[5] Morrison D.F., Muitivariate Statistical Methods (1976)
[6] DOI: 10.2307/2283110 · Zbl 0127.10504
[7] DOI: 10.2307/1268261 · Zbl 0352.62036
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.