Darren T. Andrews

TL;DR: The theoretical principles and practical implementation of a new method for multivariate data analysis, maximum likelihood principal component analysis (MLPCA), are described in this article, which is an analog to PCA that incorporates information about measurement errors to develop PCA models that are optimal in a maximum likelihood sense.

TL;DR: Two new approaches to multivariate calibration are described that, for the first time, allow information on measurement uncertainties to be included in the calibration process in a statistically meaningful way, based on principles of maximum likelihood parameter estimation.

TL;DR: In this paper, a new method, called maximum likelihood principal component analysis (MLPCA), is proposed for multivariate analysis of incomplete data sets, which incorporates measurement error variance information in the decomposition of multivariate data.

TL;DR: In this paper, the percent content of saturates (61-99%), mono-aromatics (1-34), diaromsatics (0-5), and polarity of saturate values were predicted using multivariate calibration methods.

TL;DR: In this paper, the authors compared the performance of principal components analysis (PCA) and regression methods on linear, two-dimensional data sets with a zero intercept and showed that all of them can be unified under the principle of maximum likelihood estimation, embodied in the general case by multiply weighted regression.