Multiple Imputation in Multivariate Problems When the Imputation and Analysis Models Differ

Bayesian multiple imputation (MI) has become a highly useful paradigm for handling missing values in many settings. In this paper, I compare Bayesian MI with other methods – maximum likelihood, in particular—and point out some of its unique features. One key aspect of MI, the separation of the imputation phase from the analysis phase, can be advantageous in settings where the models underlying the two phases do not agree.     

Developing a cost-benefit analysis process for small-to-moderate expenditure decisions

During the Reagan administration, the federal government mandated the use of cost–benefit analysis (CBA) for regulatory decisions involving $100 million or more. While the use of CBAs has increased, less attention has been given to CBA processes involving smaller expenditures (regulatory and nonregulatory). As the federal budget tightens in the years ahead, the need to make hard decisions about these policies, programs, and technologies will increase. This paper describes a CBA process developed for the Office of Strategic Planning of the Social Security Administration; it was designed to handle small-to-moderate expenditure decisions (or for preliminary estimates of larger undertakings). A sample CBA using this process is provided, along with a discussion of the lessons that were learned from an initial application.     

Redesigning hospitals around patients and technology

Hospitals must drastically redesign themselves and revise their operations to be successful. Four major redesign initiatives will enable the traditional hospital to provide effective patient care while attaining its own profitability goals.     

A longitudinal study of the cause and consequences of changes in diversification in the U.S. pharmaceutical industry 1977–1986

The paper hypothesizes that diversification by firms based in the pharmaceutical industry during the 1977-86 time period was primarily undertaken to reduce the risks associated with being dependent upon a technologically dynamic environment. Consistent with this non-efficiency motive for diversification, declining economic performance is predicted. A longitudinal empirical analysis provides support for these propositions.     

Copyright Damages and Statistics

This paper discusses the statistical issues that arise in conducting an economic damages analysis in the context of a litigation matter involving copyrights. Calculating damages in copyright cases turns out to be a natural application for econometric modelling methods. Surprisingly, elementary statistical issues can be a source of significant debate between the experts in such matters. In this paper, we present a case study and illustrate how issues such as interpretation of p -values and what "rejection of the null hypothesis" really "means" in such matters.     

Implementing reverse e-auctions: A learning process

Reverse e-auctions, which enable suppliers to compete on-line in real-time, are changing the way organizations select their suppliers. We explore how five large firms in different industries learned to use e-auctions, and how e-auctions were integrated into their purchasing processes. To successfully implement e-auctions, organizations should: (1) build e-auction competencies; (2) organize for knowledge management; (3) create a holistic sourcing process; (4) focus on the total cost of ownership; and (5) experiment with e-auction designs. Key observations are drawn from the case studies, and implications for supply managers are presented.