What does MD stand for?

He covers stream of variation (SoV) modeling by reviewing matrix theory and multivariate statistics, including multivariate distribution and properties and statistical inferences on mean vectors and linear models, describing variation propagation modeling with applications in assembling and machining processes, including model validation and a factor analysis method for variability modeling, diagnosing the source of variation, including diagnosis through variation pattern matching and estimation, using design methods to reduce variability, including optimized fixture layout design and process-oriented tolerance synthesis, and building in quality and reliability.

Kotz, Kummer-Gamma and Kummer-Beta univariate and multivariate distributions.

To address this point more general measures of association, such as the use of "copulas" which can join univariate distribution functions to form multivariate distribution functions are sometimes proposed.

Topics include special matrices, non-negative matrices, special products and operators, Jacobians, partitioned and patterned matrices, matrix approximation, matrix optimization, multiple integrals and multivariate distributions, linear and quadratic forms, etc.