Statistical Science (statistical + science)

Distribution by Scientific Domains


Selected Abstracts


Editorial: (Post-normal) statistical science

JOURNAL OF THE ROYAL STATISTICAL SOCIETY: SERIES A (STATISTICS IN SOCIETY), Issue 1 2006
James V. Zidek
First page of article [source]


Post-financial meltdown: What do the services industries need from us now?

APPLIED STOCHASTIC MODELS IN BUSINESS AND INDUSTRY, Issue 5 2009
Roger W. Hoerl
Abstract In 2008 the global economy was rocked by a crisis that began on Wall Street, but quickly spread to Main Street U.S.A., and then to side streets around the world. Statisticians working in the service sector are not immune, with many concerned about losing their jobs. Given this dramatic course of events, how should statisticians respond? What, if anything, can we do to help our struggling organizations survive this recession, in order to prosper in the future? This expository article describes some approaches that we feel can help service industries deal with aftereffects of the financial meltdown. Based on an understanding of current needs of the service industries, we emphasize three approaches in particular: a greater emphasis on statistical engineering relative to statistical science, ,embedding' statistical methods and principles into key business processes, and the reinvigoration of Lean Six Sigma to drive immediate, tangible business results. Copyright © 2009 John Wiley & Sons, Ltd. [source]


Science, engineering, and statistics

APPLIED STOCHASTIC MODELS IN BUSINESS AND INDUSTRY, Issue 5-6 2006
T. P. Davis
Abstract Symmetry and parsimony, together with unification through synthesis are important principles that govern the character of physical law. We show how these principles can be applied to engineering to develop an approach to reliability, and engineering in general, that centres on the identification, detection, and avoidance of failure modes through design. A definition of reliability, not presented in terms of probability, but rather based on physics, geometry, and the properties of materials, will be emphasized to support this approach. We will also show how the nature of the inductive,deductive learning cycle provides the framework for statistical science to be embedded into engineering practice, with particular regard to improving reliability through failure mode avoidance. Copyright © 2006 John Wiley & Sons, Ltd. [source]


Reconsideration of the physical and empirical origins of Z,R relations in radar meteorology

THE QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY, Issue 572 2001
A. R. Jameson
Abstract The rainfall rate, R, and the radar reflectivity factor, Z, are represented by a sum over a finite number of raindrops. It is shown here and in past work that these variables should be linearly related. Yet observations show that correlations between R and Z are often more appropriately described by nonlinear power laws. In the absence of measurement effects, why should this be so? In order to justify this observation, there have been many attempts to create physical ,explanations' for power laws. However, the present work argues that, because correlations do not prove causation (an accepted fact in the statistical sciences), such explanations are suspect, particularly since the parametric fits are not unique and because they exhibit fundamental physical inconsistencies. So why, then, do so many correlations fit power laws when physical arguments show that Z and R should be related linearly? It is shown in the present work that physically based, linear, relations between Z and R apply in statistically homogeneous rain. (Note that statistical homogeneity does not mean that the rain is spatially uniform.) In contrast, nonlinear power laws are empirical fits to correlated, but statistically inhomogeneous data. This conclusion is proven theoretically after developing a ,generalized' Z,R relation based upon physical consideration of R and Z as random variables. This relation explicitly incorporates details of the drop microphysics as well as the variability in measurements of Z and R. In statistically homogeneous rain, this generalized expression shows that the coefficient relating Z and R is a constant resulting in a linear Z,R relation. In statistically inhomogeneous rain, however, the coefficient varies in an unknown fashion so that one must resort to statistical fits, often power laws, in order to relate the two quantities empirically over widely varying conditions. This conclusion is independently verified using Monte Carlo simulations of rain from earlier work and is also corroborated using disdrometer observations. Thus, the justification for nonlinear power-law Z,R relations is not physical, but rather statistical, in that they provide convenient parametric fits for estimating mean R from measured mean Z in statistically inhomogeneous rain. Finally, examples based upon disdrometer data suggest that such generalized relations between two variables defined by such sums are potentially useful over a wide range of remote-sensing problems and over a wide range of scales. The examples also offer hope that data collected over disparate sampling-volumes and sampling-frequencies can still be combined to yield meaningful estimates. Although additional testing is required, this allows us to write programs which combine estimates of R using remote-sensing techniques with sparse but direct rainfall observations. [source]