Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

行銷硏究 : Marketing research

This is an important contribution to a modern area of applied probability that deals with nonstationary Markov chains in continuous time. This area is becoming increasingly useful in engineering, economics, communication theory, active networking, and so forth, where the Markov-chain system is subject to frequent  uctuations with clusters of states such that the chain  uctuates very rapidly among different states of a cluster but changes less rapidly from one cluster to another. The authors use the setting of singular perturbations, which allows them to study both weak and strong interactions among the states of the chain. This leads to simpli cations through the averaging principle, aggregation, and decomposition. The main results include asymptotic expansions of the corresponding probability distributions, occupations measures, limiting normality, and exponential rates. These results give the asymptotic behavior of many controlled stochastic dynamic systems when the perturbation parameter tends to 0. The classical analytical method employs the asymptotic expansions of onedimensional distributions of the Markov chain as solutions to a system of singularly perturbed ordinary differential equations. Indeed, the asymptotic behavior of solutions of such equations is well studied and understood. A more probabilistic approach also used by the authors is based on the tightness of the family of probability measures generated by the singularly perturbed Markov chain with the corresponding weak convergence properties. Both of these methods are illustrated by practical dynamic optimization problems, in particular by hierarchical production planning in a manufacturing system. An important contribution is the last chapter, Chapter 10, which describes numerical methods to solve various control and optimization problems involving Markov chains. Altogether the monograph consists of three parts, with Part I containing necessary, technically rather demanding facts about Markov processes (which in the nonstationary case are de ned through martingales.) Part II derives the mentioned asymptotic expansions, and Part III deals with several applications, including Markov decision processes and optimal control of stochastic dynamic systems. This technically demanding book may be out of reach of many readers of Technometrics. However, the use of Markov processes has become common for numerous real-life complex stochastic systems. To understand the behavior of these systems, the sophisticated mathematical methods described in this book may be indispensable.

Monte Carlo Methods in Bayesian Computation

Mixture regression models are an important method for uncovering unobserved heterogeneity. A fundamental challenge in their application relates to the identification of the appropriate number of segments to retain from the data. Prior research has provided several simulation studies that compare the performance of different segment retention criteria. Although collinearity between the predictor variables is a common phenomenon in regression models, its effect on the performance of these criteria has not been analyzed thus far. We address this gap in research by examining the performance of segment retention criteria in mixture regression models characterized by systematically increased collinearity levels. The results have fundamental implications and provide guidance for using mixture regression models in empirical (marketing) studies.

How collinearity affects mixture regression results

Cluster analysis finds groups in data automatically. Most methods have been heuristic and leave open such central questions as: how many clusters are there? Which method should I use? How should I handle outliers? Classification assigns new observations to groups given previously classified observations, and also has open questions about parameter tuning, robustness and uncertainty assessment. This book frames cluster analysis and classification in terms of statistical models, thus yielding principled estimation, testing and prediction methods, and sound answers to the central questions. It builds the basic ideas in an accessible but rigorous way, with extensive data examples and R code; describes modern approaches to high-dimensional data and networks; and explains such recent advances as Bayesian regularization, non-Gaussian model-based clustering, cluster merging, variable selection, semi-supervised and robust classification, clustering of functional data, text and images, and co-clustering. Written for advanced undergraduates in data science, as well as researchers and practitioners, it assumes basic knowledge of multivariate calculus, linear algebra, probability and statistics.

Model-Based Clustering and Classification for Data Science

The authors propose a new Bayesian latent structure regression model with variable selection to solve various commonly encountered marketing problems related to market segmentation and heterogeneity. The proposed procedure simultaneously performs segmentation and regression analysis within the derived segments, in addition to determining the optimal subset of independent variables per derived segment. The authors present comparative analyses contrasting the performance of the proposed methodology against standard latent class regression and traditional Bayesian finite mixture regression. They demonstrate that their proposed Bayesian model compares favorably with these traditional benchmark models. They then present an actual commercial customer satisfaction study performed for an electric utility company in the southeastern United States, in which they examine the heterogeneous drivers of perceived quality. Finally, they discuss limitations of the research and provide several directions for furth...

Model-Based segmentation featuring simultaneous segment-level variable selection

Researchers have recently introduced a finite mixture Bayesian regression model to simultaneously identify consumer market segments (heterogeneity) and determine how such segments differ with respect to active regression coefficients (variable selection). This article introduces three extensions of this model to incorporate managerial restrictions (constraints). The authors demonstrate with synthetic data that the new constrained finite mixture Bayesian regression models can be used to identify and represent several constrained heterogeneous response patterns commonly encountered in practice. In addition, they show that the proposed models are more robust against multicollinearity than traditional methods. Finally, to illustrate the proposed models' usefulness, the authors apply the proposed constrained models in the context of a service quality (SERVPERF) survey of National Insurance Company's customers.

Implementing Managerial Constraints in Model-Based Segmentation: Extensions of Kim, Fong, and DeSarbo (2012) with an Application to Heterogeneous Perceptions of Service Quality

A new Bayesian multinomial probit model is proposed for the analysis of panel choice data. Using a parameter expansion technique, we are able to devise a Markov Chain Monte Carlo algorithm to compute our Bayesian estimates efficiently. We also show that the proposed procedure enables the estimation of individual level coefficients for the single-period multinomial probit model even when the available prior information is vague. We apply our new procedure to consumer purchase data and reanalyze a well-known scanner panel dataset that reveals new substantive insights. In addition, we delineate a number of advantageous features of our proposed procedure over several benchmark models. Finally, through a simulation analysis employing a fractional factorial design, we demonstrate that the results from our proposed model are quite robust with respect to differing factors across various conditions.

A bayesian multinomial probit model for the analysis of panel choice data

Strategies for improving self-control among naïve, sophisticated, and time-consistent consumers

We investigate spatial heterogeneity of country-of-origin effects (COEs) within a country and its determinants. Drawing on the literature of COEs and information economics, we maintain that COEs are heterogeneous across regions within a country, which bears important implications to better understand subnational heterogeneity of consumer preferences. We employ a geographically weighted regression model, a spatial analysis to estimate varying COEs across regions in the USA, and analyze online review ratings of US and foreign car bands in the US market during the 2008–2014 period. The results show that (1) COEs of car brands from Germany, Japan, Korea, and the UK are heterogeneous across regions in the USA; (2) geographic distance from the country-of-origin exerts negative influences on COEs; and (3) the proportion of population born in the country-of-origin positively influences COEs.

Sunghoon Kim

Papers

Model-Based segmentation featuring simultaneous segment-level variable selection

Implementing Managerial Constraints in Model-Based Segmentation: Extensions of Kim, Fong, and DeSarbo (2012) with an Application to Heterogeneous Perceptions of Service Quality

A bayesian multinomial probit model for the analysis of panel choice data

Strategies for improving self-control among naïve, sophisticated, and time-consistent consumers

Spatial heterogeneity of country-of-origin effects within a country: analysis of online review ratings in the US car market