Home  About us  Contact
 

Statistical Point (statistical + point)

Distribution by Scientific Domains
Mathematics and Statistics40%

Selected Abstracts

Evaluation of reduced rank semiparametric models to assess excess of risk in cluster analysis

ENVIRONMETRICS, Issue 4 2009
Marco Geraci
Abstract The existence of multiple environmental hazards is obviously a threat to human health and, from a statistical point of view, the modeling and the detection of disease clusters potentially related to those hazards offer challenging tasks. In this paper, we consider low rank thin plate spline (TPS) models within a semiparametric approach to focused clustering for small area health data. Both the distance from a putative source and a general, unspecified clustering process are modeled in the same fashion and they are entered log-additively in mixed Poisson-Normal models. Some issues related to the identification of the random effects arising from this approach are investigated. Under different simulated scenarios, we evaluate the proposed models using conditional Akaike's weights and tests for variance components, providing a comprehensive model selection methodology easy to implement. We examine observations of lung cancer deaths taken in Ohio between 1987 and 1988. These data were analyzed on several occasions to investigate the risk associated with a putative source in Hamilton county. In our analysis, we found a strong south-eastward spatial trend which is confounded with a significant radial distance effect decreasing between 0 and 150 km from the point source. Copyright © 2008 John Wiley & Sons, Ltd. [source]

INTERPRETATION OF THE RESULTS OF COMMON PRINCIPAL COMPONENTS ANALYSES

EVOLUTION, Issue 3 2002
David Houle
Abstract Common principal components (CPC) analysis is a new tool for the comparison of phenotypic and genetic variance-covariance matrices. CPC was developed as a method of data summarization, but frequently biologists would like to use the method to detect analogous patterns of trait correlation in multiple populations or species. To investigate the properties of CPC, we simulated data that reflect a set of causal factors. The CPC method performs as expected from a statistical point of view, but often gives results that are contrary to biological intuition. In general, CPC tends to underestimate the degree of structure that matrices share. Differences of trait variances and covariances due to a difference in a single causal factor in two otherwise identically structured datasets often cause CPC to declare the two datasets unrelated. Conversely, CPC could identify datasets as having the same structure when causal factors are different. Reordering of vectors before analysis can aid in the detection of patterns. We urge caution in the biological interpretation of CPC analysis results. [source]

Statistical evaluation of diffusion-weighted imaging of the human kidney

MAGNETIC RESONANCE IN MEDICINE, Issue 2 2010
Hans-Jörg Wittsack
Abstract The signal of diffusion-weighted imaging of the human kidney differs from the signal in brain examinations due to the different microscopic structure of the tissue. In the kidney, the deviation of the signal behavior of monoexponential characteristics is pronounced. The aim of the study was to analyze whether a mono- or biexponential or a distribution function model fits best to describe diffusion characteristics in the kidney. To determine the best regression, different statistical parameters were utilized: correlation coefficient (R2), Akaike's information criterion, Schwarz criterion, and F-test (Fratio). Additionally, simulations were performed to analyze the relation between the different models and their dependency on signal noise. Statistical tests showed that the biexponential model describes the signal of diffusion-weighted imaging in the kidney better than the distribution function model. The monoexponential model fits the diffusion-weighted imaging data the least but is the most robust against signal noise. From a statistical point of view, diffusion-weighted imaging of the kidney should be modeled biexponentially under the precondition of sufficient signal to noise. Magn Reson Med, 2010. © 2010 Wiley-Liss, Inc. [source]

Southern hemisphere winter ozone fluctuations

THE QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY, Issue 572 2001
P. K. Vigliarolo
Abstract In this paper the relationship between ozone and atmospheric variability is explored over the southern hemisphere during the austral winter season, with special emphasis on synoptic transient fluctuations. The analysis of ozone tracks (or high-frequency ozone variability) shows that they have a significant correspondence with storm tracks at middle and high latitudes. Moreover, ozone tracks maximize over the Indian Ocean slightly downstream of the storm-track maximum, while over the Pacific region both ozone and storm tracks show decreased amplitudes. In particular, over southern South America (a region of climatological winter ozone minima and moderate to high ozone variability) the leading winter synoptic-scale variability mode was identified through a rotated extended empirical orthogonal function analysis applied to the meridional-wind perturbation at 300 hPa. The resulting mode is characterized by a baroclinic wave travelling eastward along subpolar latitudes, which maximizes near the tropopause level. Composite ozone fields based on this mode confirm, from a statistical point of view, the classical relationship between ridges (troughs) and minimum (maximum) ozone content. Furthermore, it is shown that dynamical processes in the upper troposphere and lower stratosphere associated with subpolar waves are responsible for the observed ozone distribution. This happens due to the barotropic equivalent vertical structure of the wave, together with the fact that ozone partial pressure maximizes near the level where the waves attain maximum amplitudes. [source]

A Point Estimator for the Time Course of Drug Release

BIOMETRICAL JOURNAL, Issue 1 2009
Stephan Koehne-Voss
Abstract Procedures for deconvolution of pharmacokinetic data are routinely used in the pharmaceutical industry to determine drug release and absorption which is essential in designing optimized drug formulations. Although these procedures are described extensively in the pharmacokinetic literature, they have been studied less from a statistical point of view and variance estimation has not been addressed. We discuss the statistical properties of a numerical procedure for deconvolution. Based on a point-area deconvolution method we define an estimator for the function that describes the time course of drug release from a drug formulation. Asymptotic distributions are derived and several methods of variance and interval estimation are compared (© 2009 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim) [source]