Positive-definite modification of a covariance matrix by minimizing the matrix $$\ell_{\infty}$$ ℓ ∞ norm with applications to portfolio optimization

AStA Advances in Statistical Analysis - The covariance matrix, which should be estimated from the data, plays an important role in many multivariate procedures, and its positive definiteness...     

Grocery Perishables Management

In this article, we study the joint pricing and inventory control problem for perishables when a retailer does not sell new and old inventory at the same time. At the beginning of a period, the retailer makes replenishment and pricing decisions, and at the end of a period, the retailer decides whether to dispose of ending inventory or carry it forward to the next period. The objective of the retailer is to maximize the long‐run average profit. Assuming zero lead time, we propose an efficient solution approach to the problem, which is also generalized to solve three extensions to the basic model. A feature of the present study is that we consider explicitly the influence of perishability on the demand. Among the insights gathered from the numerical analysis, we find that dynamic pricing aids extending shelf life and when disposal incurs a lower cost, or even a positive salvage value, the retailer is induced to dispose earlier since the benefit of selling new inventory offsets the loss due to disposal. We also observe that the faster the perceived rate of deterioration, the lower the threshold of the ending inventory for disposal. Perhaps a bit counter‐intuitive, maximizing profits does not mean eliminating disposals or expirations.     

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.     

Institutional rules for framing healthcare policy issues in national,financial, and specialized newspapers

By considering the role of institutional rules for news making, this study examines news frames embedded in 1162 stories from national, financial, and specialized newspapers with respect to four healthcare policy issues: “the decrease in pharmaceutical prices,” “the comprehensive medical payment system,” “swine flu,” and “humidifier-related lung disease.” Conflict, economy, crisis, and policy execution are dominant frames in stories about the policy issues, and these four frames are also major frames used by the newspapers. This phenomenon is understood as “concentration of healthcare frames.” We conducted in-depth interviews with 19 news reporters to identify institutional rules that might influence the formation of news frames. In-depth interviews revealed that similar types of frames resulted from institutional rules (e.g., journalist’s autonomy, news value, newspaper’s mission statement, and characteristics of readers). The findings suggest that health journalists follow institutional rules that govern the creation of news frames. To provide diverse perspectives on healthcare policy issues, newspapers need to reconsider their institutional rules.     

The decomposition of regional wage differentials in Korea

This research note explains the wage differentials between the capital region and the non-capital region in Korea. It analyzes what proportions of the wage differential are due to differences in productivity-related labor characteristics and due to differences in how markets value the endowments of their workers. In a decomposition analysis, we find that approximately 26.9% of the wage differential is due to differences in productivity-related labor characteristics in the capital region. With respect to the endowments of the wage-determining characteristics, a substantial portion of the overall wage advantage of workers in the capital region can be explained by the higher average level of education. It is also found that the more detailed the occupational breakdown, the more of the wage differential that can be explained. These results suggest that the use of more detailed occupation classifications alleviates aggregation bias that may be a significant factor in coarser classification schemes.     

Kernel Density Estimator From Ranked Set Samples

We study kernel density estimator from the ranked set samples (RSS). In the kernel density estimator, the selection of the bandwidth gives strong influence on the resulting estimate. In this article, we consider several different choices of the bandwidth and compare their asymptotic mean integrated square errors (MISE). We also propose a plug-in estimator of the bandwidth to minimize the asymptotic MISE. We numerically compare the MISE of the proposed kernel estimator (having the plug-in bandwidth estimator) to its simple random sampling counterpart. We further propose two estimators for a symmetric distribution, and show that they outperform in MISE all other estimators not considering symmetry. We finally apply the methods in this article to analyzing the tree height data from Platt et al. (1988 Platt, W.J., Evans, G.M., Rathbun, S.L. (1988). The population dynamics of long-lived conifer (Pinus plaustris) (1988). Amer. Natrualist 131:491–525.[Crossref], [Web of Science ®] , [Google Scholar]) and Chen et al. (2003 Chen, Z., Bai, Z., Sinha, B.K. (2003). Ranked Set Sampling: Theory and Applications. New York: Springer. [Google Scholar]).     

A Numerical Study of PQL Estimation Biases in Generalized Linear Mixed Models Under Heterogeneity of Random Effects

The penalized quasi-likelihood (PQL) approach is the most common estimation procedure for the generalized linear mixed model (GLMM). However, it has been noticed that the PQL tends to underestimate variance components as well as regression coefficients in the previous literature. In this article, we numerically show that the biases of variance component estimates by PQL are systematically related to the biases of regression coefficient estimates by PQL, and also show that the biases of variance component estimates by PQL increase as random effects become more heterogeneous.     

Extending Financial Portfolio Theory for Product Management*

This paper attempts to modify financial portfolio theory for application in product portfolio decisions. The proposed multiperiod portfolio framework should help marketers in allocating scarce corporate resources to various competing products as well as contribute to developing a body of theory to solve an important problem in marketing management. Managerial and theoretical implications are discussed.