No abstract

This article provides a large-scale investigation into several of the properties of mixture-model clustering techniques (also referred to as latent class cluster analysis, latent profile analysis, model-based clustering, probabilistic clustering, Bayesian classification, unsupervised learning, and finite mixture models; see Vermunt & Magdison, 2002). Focus is given to the multivariate normal distribution, and 9 separate decompositions (i.e., class structures) of the covariance matrix are investigated. To provide a link to the current literature, comparisons are made with K-means clustering in 3 detailed Monte Carlo studies. The findings have implications for applied researchers in that mixture-model clustering techniques performed best when the covariance structure and number of clusters were known. However, as the information about the shape and number of clusters became unknown, degraded performance was observed for both K-means clustering and mixture-model clustering.

This research is the first to examine service sweethearting, an illicit behavior that costs firms billions of dollars annually in lost revenues. Sweethearting occurs when frontline workers give unauthorized free or discounted goods and services to customer conspirators. The authors gather dyadic data from 171 service employees and 610 of their customers. The results from the employee data reveal that a variety of job, social, and remuneration factors motivate sweethearting behavior and several measurable employee traits suppress its frequency. The results from the customer data indicate that although sweethearting inflates a firm's satisfaction, loyalty, and positive word-ofmouth scores by as much as 9%, satisfaction with the confederate employee fully mediates these effects. Thus, any benefits for customer satisfaction or loyalty initiatives are tied to a frontline worker that the firm would rather not employ. Marketing managers can use this study to recognize job applicants or company settings that are particularly prone to sweethearting and as the basis for mitigating a positive bias in key customer metrics.

cluster analysis, K-means partitioning, variable selection, heuristics,

cluster analysis, variable selection,

Steinley (2007) provided a lower bound for the sum-of-squares error criterion function used in K-means clustering. In this article, on the basis of the lower bound, the authors propose a method to distinguish between 1 cluster (i.e., a single distribution) versus more than 1 cluster. Additionally, conditional on indicating there are multiple clusters, the procedure is extended to determine the number of clusters. Through a series of simulations, the proposed methodology is shown to outperform several other commonly used procedures for determining both the presence of clusters and their number.

Service operations that utilize cross-trained employees face complex workforce staffing decisions that have important implications for both cost and productivity. These decisions are further complicated when cross-trained employees have different productivity levels in multiple work activity categories. A method for policy analysis in such environments can be beneficial in determining low-cost staffing plans with appropriate Cross-training configurations.In this paper, we present an integer linear programming model for evaluating cross-training configurations at the policy level. The objective of the model is to minimize workforce staffing costs subject to the satisfaction of minimum labor requirements across a planning horizon of a single work shift. The model was used to evaluate eight cross-training structures (consisting of 36 unique cross-training configurations) across 512 labor requirement patterns. These structures, as well as the labor requirement patterns, were established based on data collected from maintenance operations at a large paper mill in the United States. The results indicate that asymmetric cross-training structures that permit chaining of employee skill classes across work activity categories are particularly useful. Subject Areas: Emplbyee Cross-training, Labor and Staff Planning, Mathematical Programming, and Operations Management.

A variance-to-range ratio variable weighting procedure is proposed. We show how this weighting method is theoretically grounded in the inherent variability found in data exhibiting cluster structure. In addition, a variable selection procedure is proposed to operate in conjunction with the variable weighting technique. The performances of these procedures are demonstrated in a simulation study, showing favorable results when compared with existing standardization methods. A detailed demonstration of the weighting and selection procedure is provided for the well-known Fisher Iris data and several synthetic data sets.