The purpose of this thesis is to construct several stochastic
process models for combined statistical dynamic prediction of the
500-millibar pressure surface for the northern hemisphere. To
achieve this, a random forcing function is added to the spectral form
of the nondivergent vorticity equation. Three models, one linear and
two...
An iterative approach is suggested for the estimation
of the error covariance matrix [sigma] to find approximate BLUE
estimators in linear regression models.
It is shown through
experimental studies how the variances can be estimated in
the simple general linear regression model, in the linear
regression model sequenced over time,...
A Bayesian approach to the analysis of a two-phase linear
regression model is given. It is assumed that the regression model is
continuous at the change point. The likelihood function is expressed
in a form which explicitly contains the continuity restriction. The
natural conjugate prior distribution for the likelihood function...
In a discrete review inventory process, when the demand
forms a stochastically convergent sequence of random variables,
it seems reasonable that the optimal stationary (s, S) inventory
policy will be a function of the limiting demand and cost structure
only. The intent of this paper is to provide a rigorous...
A computationally efficient algorithm has been developed for
determining exact or approximate solutions for large scale generalized
fixed charge problems. This algorithm is based on a relaxation
of the Benders decomposition procedure, combined with a linear
mixed integer programming (MIP) algorithm specifically designed to
solve the problem associated with Benders...