6533b838fe1ef96bd12a4e80
RESEARCH PRODUCT
Statistical Techniques for Validation of Simulation and Analytic Stochastic Models
Konstantin N. NechvalNicholas A. NechvalNatalija RibakovaVadim Danovichsubject
Multivariate statisticsService (systems architecture)education.field_of_studyStochastic modellingStatistical validationPopulationApplied mathematicsMultivariate normal distributionCovarianceeducationStatistical hypothesis testingMathematicsdescription
In this paper, we consider the problem of statistical validation of multivariate stationary response simulation and analytic stochastic models of observed systems (say, transportation or service systems), which have p response variables. The problem is reduced to testing the equality of the mean vectors for two multivariate normal populations. Without assuming equality of the covariance matrices, it is referred to as the Behrens–Fisher problem. The main purpose of this paper is to bring to the attention of applied researchers the satisfactory tests that can be used for testing the equality of two normal mean vectors when the population covariance matrices are unknown and arbitrary. To illustrate the proposed statistical techniques, application examples are given.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2014-01-01 |