Multivariate Reducedrank Regression Theory Methods And Applications 2nd Edition Gregory C Reinsel by Gregory C Reinsel, Raja P Velu, Kun Chen 9781071627914, 1071627910 instant download after payment.

The first version of the book was published in 1998. It covered the developments in the field as of that period. The pioneering work of Ted Anderson has provided a framework for rich extensions of the reduced-rank model not only in methodology but also in applications. Since the publication of the book, the interest in big data has grown exponentially and thus there is a need for models that are relevant for the analysis of large dimensional data. The basic reduced-rank models described in the book provide a natural way to handle large dimensional data without using any a priori theory. These models have been mainly extended via various forms of regularization techniques that found their way in applications varying from natural science areas such as genetics to social science fields including economics and finance. These techniques lead to further dimension-reduction via variable selection beyond what is implied by the reduced-rank models. They also add a great value in terms of elegant, simplified interpretations of the model coefficients and in the context of time series data, provide more accurate forecasts. Many of the developments have come not only from the field of statistics but also from machine learning, economics, etc., and thus, the interest in these extended topics comes from various areas of orientation. With emphasis on computational aspects, many of the research papers are also usually supplemented with coded algorithms for ready implementation. Because of the specialized nature of the topics, the first edition of the book was in the form of a research monograph. But the book has been received very well; the latest Google search indicates that there are more than 560 citations of the book with most of the citations in articles published in top journals in statistics, econometrics, and machine learning. Several doctoral theses have followed as well, extending the models discussed in the book. Given the significance of the big data methodology and