A Tale of Two Matrix Factorizations

In statistical practice, rectangular tables of numeric data are commonplace, and are often analyzed using dimension-reduction methods like the singular value decomposition and its close cousin, principal component analysis (PCA). This analysis produces score and loading matrices representing the rows and the columns of the original table and these matrices may be used for both prediction purposes and to gain structural understanding of the data. In some tables, the data entries are necessarily nonnegative (apart, perhaps, from some small random noise), and so the matrix factors meant to represent them should arguably also contain only nonnegative elements. This thinking, and the desire for parsimony, underlies such techniques as rotating factors in a search for “simple structure.” These attempts to transform score or loading matrices of mixed sign into nonnegative, parsimonious forms are, however, indirect and at best imperfect. The recent development of nonnegative matrix factorization, or NMF, is an attractive alternative. Rather than attempt to transform a loading or score matrix of mixed signs into one with only nonnegative elements, it directly seeks matrix factors containing only nonnegative elements. The resulting factorization often leads to substantial improvements in interpretability of the factors. We illustrate this potential by synthetic examples and a real dataset. The question of exactly when NMF is effective is not fully resolved, but some indicators of its domain of success are given. It is pointed out that the NMF factors can be used in much the same way as those coming from PCA for such tasks as ordination, clustering, and prediction. Supplementary materials for this article are available online.     

A comparison of regularization methods applied to the linear discriminant function with high-dimensional microarray data

Classification of gene expression microarray data is important in the diagnosis of diseases such as cancer, but often the analysis of microarray data presents difficult challenges because the gene expression dimension is typically much larger than the sample size. Consequently, classification methods for microarray data often rely on regularization techniques to stabilize the classifier for improved classification performance. In particular, numerous regularization techniques, such as covariance-matrix regularization, are available, which, in practice, lead to a difficult choice of regularization methods. In this paper, we compare the classification performance of five covariance-matrix regularization methods applied to the linear discriminant function using two simulated high-dimensional data sets and five well-known, high-dimensional microarray data sets. In our simulation study, we found the minimum distance empirical Bayes method reported in Srivastava and Kubokawa [Comparison of discrimination methods for high dimensional data, J. Japan Statist. Soc. 37(1) (2007), pp. 123–134], and the new linear discriminant analysis reported in Thomaz, Kitani, and Gillies [A Maximum Uncertainty LDA-based approach for Limited Sample Size problems – with application to Face Recognition, J. Braz. Comput. Soc. 12(1) (2006), pp. 1–12], to perform consistently well and often outperform three other prominent regularization methods. Finally, we conclude with some recommendations for practitioners.     

Comparisons of computational methods for clustered binary data

Clustered binary data are common in medical research and can be fitted to the logistic regression model with random effects which belongs to a wider class of models called the generalized linear mixed model. The likelihood-based estimation of model parameters often has to handle intractable integration which leads to several estimation methods to overcome such difficulty. The penalized quasi-likelihood (PQL) method is the one that is very popular and computationally efficient in most cases. The expectation–maximization (EM) algorithm allows to estimate maximum-likelihood estimates, but requires to compute possibly intractable integration in the E-step. The variants of the EM algorithm to evaluate the E-step are introduced. The Monte Carlo EM (MCEM) method computes the E-step by approximating the expectation using Monte Carlo samples, while the Modified EM (MEM) method computes the E-step by approximating the expectation using the Laplace's method. All these methods involve several steps of approximation so that corresponding estimates of model parameters contain inevitable errors (large or small) induced by approximation. Understanding and quantifying discrepancy theoretically is difficult due to the complexity of approximations in each method, even though the focus is on clustered binary data. As an alternative competing computational method, we consider a non-parametric maximum-likelihood (NPML) method as well. We review and compare the PQL, MCEM, MEM and NPML methods for clustered binary data via simulation study, which will be useful for researchers when choosing an estimation method for their analysis.     

Bayesian Estimation of the Two-Parameter Gamma Distribution

In this article, we present and discuss an original price index being a special case of a general formula for price indices. We show that the discussed formula satisfies most postulates coming from the axiomatic price index theory. We compare this index to other known and popular price indices in a simulation study.     

Multivariate CUSUM and EWMA Control Charts for Skewed Populations Using Weighted Standard Deviations

This article proposes a heuristic method of constructing multivariate cumulative sum and exponentially weighted moving average control charts for skewed populations based on the weighted standard deviation method which adjusts the variance–covariance matrix of quality characteristics and approximates the probability density function using several multivariate normal distributions. These control charts, however, reduce to the conventional control charts when the underlying distribution is symmetric. In-control and out-of-control average run lengths of the proposed control charts are compared with those of the conventional control charts for multivariate lognormal and Weibull distributions. Simulation results show that considerable improvements over the standard method can be achieved when the underlying distribution is skewed.     

Regression Tolerance Intervals

In this article, we discuss the utility of tolerance intervals for various regression models. We begin with a discussion of tolerance intervals for linear and nonlinear regression models. We then introduce a novel method for constructing nonparametric regression tolerance intervals by extending the well-established procedure for univariate data. Simulation results and application to real datasets are presented to help visualize regression tolerance intervals and to demonstrate that the methods we discuss have coverage probabilities very close to the specified nominal confidence level.     

The Roles of Worker Expertise,Information Sharing Quality,and Psychological Safety in Manufacturing Process Innovation: An Intellectual Capital Perspective

This paper examines the roles of three elements of intellectual capital in implementing process innovations. Building upon prior literature, we develop a model describing how worker expertise, information sharing quality, and psychological safety work together as elements of the human, structural, and social dimensions of intellectual capital to influence the technical success of manufacturing process innovation (MPI) projects. Results of an analysis of data describing 179 MPI projects in US firms strongly support a multidimensional, process‐oriented view of intellectual capital's effects on MPI project technical performance. We also find that the incrementalness of an MPI project plays a moderating role over the relationship between worker expertise and MPI performance. Our study provides insights on how intellectual capital can be more effectively accumulated in a project environment.     

Institutions and the gender wage gap: How production and welfare regime moderates the effect of family policy

The aim of this study was to determine whether the effects of work and family reconciliation policy on the gender wage gap are moderated by institutional contexts of production and welfare regime. Using time‐series analysis for 13 countries from 1981 to 2015, the study revealed a strong association between childcare and a lower gender wage gap in the Coordinated Market Economies (CMEs)/social democratic welfare states but not in Liberal Market Economies (LMEs)/liberal welfare states. The study also found that the impact of leave generosity on the gender wage gap in CMEs/social democratic welfare states is less salient than in CMEs/continental welfare states. This study highlights the extent to which family policy affects the gender wage gap hinges on how each country organises its market coordination and welfare institutions and pushes the current literature forward to a question of ‘what kinds of’ family policy matters in ‘which’ production and welfare regimes.