Informed decision making: the new paradigm

Health care cannot survive in its present form. It is becoming unaffordable for a large share of the country's population. Its quality and effectiveness inexplicably vary between communities and across time. With all these problems, the process of health care can be understood. All that are needed are good, basic data; its access, management, and analysis; and then presentation of facts and observations. Together, these functions describe the translation of data into information--the field of medical informatics. Information about such management concerns as clinical efficiency (which largely is related to appropriateness and cost-effectiveness) and about the realities of day-to-day medical practice can be used to improve the value of health care. Informed decision making is based solely on confidence that, given the right information and understanding, we can all make the right decisions. The right decisions mean better patient acceptance and satisfaction, a sense of value enhancement by payers, and support of the Hippocratic tradition.     

Task partitioning in new product development teams: A knowledge and learning perspective

R&D alliances and outsourcing elements of the new product development process are now commonplace practices among many firms. However, little previous work has examined how these organizational choices influence project knowledge and learning. Based on a comparison of three new product development projects in the software industry, this paper examines how task partitioning in the project influences learning and knowledge development within the firm. The paper suggests that internal development projects encourage synthetic learning and development of architectural and tacit knowledge; in contrast, outsourcing and joint ventures encourage analytic learning and development of component and explicit knowledge.     

Compliance Versus Risk in Assessing Occupational Exposures

Assessments of occupational exposures to chemicals are generally based upon the practice of compliance testing in which the probability of compliance is related to the exceedance [γ, the likelihood that any measurement would exceed an occupational exposure limit (OEL)] and the number of measurements obtained. On the other hand, workers’ chronic health risks generally depend upon cumulative lifetime exposures which are not directly related to the probability of compliance. In this paper we define the probability of “overexposure” (θ) as the likelihood that individual risk (a function of cumulative exposure) exceeds the risk inherent in the OEL (a function of the OEL and duration of exposure). We regard θ as a relevant measure of individual risk for chemicals, such as carcinogens, which produce chronic effects after long-term exposures but not necessarily for acutely-toxic substances which can produce effects relatively quickly. We apply a random-effects model to data from 179 groups of workers, exposed to a variety of chemical agents, and obtain parameter estimates for the group mean exposure and the within- and between-worker components of variance. These estimates are then combined with OELs to generate estimates of γ and θ. We show that compliance testing can significantly underestimate the health risk when sample sizes are small. That is, there can be large probabilities of compliance with typical sample sizes, despite the fact that large proportions of the working population have individual risks greater than the risk inherent in the OEL. We demonstrate further that, because the relationship between θ and γ depends upon the within- and between-worker components of variance, it cannot be assumed a priori that exceedance is a conservative surrogate for overexposure. Thus, we conclude that assessment practices which focus upon either compliance or exceedance are problematic and recommend that employers evaluate exposures relative to the probabilities of overexposure.     

Fitting Hierarchical Holographic Modeling into the Theory of Scenario Structuring and a Resulting Refinement to the Quantitative Definition of Risk

A point of view is suggested from which the Hierarchical Holographic Modeling (HHM) method can be seen as one more method within the Theory of Scenario Structuring (TSS), which is that part of Quantitative Risk Assessment having to do with the task of identifying the set of risk scenarios. Seen in this way, HHM brings strongly to our attention the fact that different methods within TSS can result in different sets of risk scenarios for the same underlying problem. Although this is not a problem practically, it is a bit awkward conceptually from the standpoint of the "set of triplets" definition of risk, in which the scenario set is part of the definition. Accordingly, the present article suggests a refinement to the set of triplets definition, which removes the specific set of scenarios, found by any of the TSS methods, from the definition of risk and casts it, instead, as an approximation to the "true" set of scenarios that is native to the problem at hand and not affected by the TSS method used.     

Importance of interpolation when constructing double-bootstrap confidence intervals

We show that, in the context of double-bootstrap confidence intervals, linear interpolation at the second level of the double bootstrap can reduce the simulation error component of coverage error by an order of magnitude. Intervals that are indistinguishable in terms of coverage error with theoretical, infinite simulation, double-bootstrap confidence intervals may be obtained at substantially less computational expense than by using the standard Monte Carlo approximation method. The intervals retain the simplicity of uniform bootstrap sampling and require no special analysis or computational techniques. Interpolation at the first level of the double bootstrap is shown to have a relatively minor effect on the simulation error.     

GMM Estimation with persistent panel data: an application to production functions

This paper considers the estimation of Cobb-Douglas production functions using panel data covering a large sample of companies observed for a small number of time periods. GMM estimatorshave been found to produce large finite-sample biases when using the standard first-differenced estimator. These biases can be dramatically reduced by exploiting reasonable stationarity restrictions on the initial conditions process. Using data for a panel of R&Dperforming US manufacturing companies we find that the additional instruments used in our extended GMM estimator yield much more reasonable parameter estimates.