Search

Osteoporotic hip fractures in the elderly are associated with a high mortality in the first year following fracture and a high incidence of disability among survivors. We study first and second fractures of elderly women using data from the Study of Osteoporotic Fractures. We present a new conceptual framework, stochastic model, and statistical methodology for time to fracture. Our approach gives additional insights into the patterns for first and second fractures and the concomitant risk factors. Our modeling perspective involves a novel time-to-event methodology called threshold regression, which is based on the plausible idea that many events occur when an underlying process describing the health or condition of a person or system encounters a critical boundary or threshold for the first time. In the parlance of stochastic processes, this time to event is a first hitting time of the threshold. The underlying process in our model is a composite of a chronic degradation process for skeletal health combined with a random stream of shocks from external traumas, which taken together trigger fracture events. Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Time-to-event data with time-varying covariates pose an interesting challenge for statistical modeling and inference, especially where the data require a regression structure but are not consistent with the proportional hazard assumption. Threshold regression (TR) is a relatively new methodology based on the concept that degradation or deterioration of a subject's health follows a stochastic process and failure occurs when the process first reaches a failure state or threshold (a first-hitting-time). Survival data with time-varying covariates consist of sequential observations on the level of degradation and/or on covariates of the subject, prior to the occurrence of the failure event. Encounters with this type of data structure abound in practical settings for survival analysis and there is a pressing need for simple regression methods to handle the longitudinal aspect of the data. Using a Markov property to decompose a longitudinal record into a series of single records is one strategy for dealing with this type of data. This study looks at the theoretical conditions for which this Markov approach is valid. The approach is called threshold regression with Markov decomposition or Markov TR for short. A number of important special cases, such as data with unevenly spaced time points and competing risks as stopping modes, are discussed. We show that a proportional hazards regression model with time-varying covariates is consistent with the Markov TR model. The Markov TR procedure is illustrated by a case application to a study of lung cancer risk. The procedure is also shown to be consistent with the use of an alternative time scale. Finally, we present the connection of the procedure to the concept of a collapsible survival model. Copyright © 2010 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Le test d'Ames pour la salmonelle est une méthode de bioessai utilisée couramment pour évaluer le pouvoir mutagène d'un agent cancérigène potentiel. Le test est relativement rapide et fiable, et exploite la corrélation existant entre potentiel mutagène et potentiel cancérigène. Les données pour cette étude de cas proviennent d'une étude internationale impliquant vingt laboratoires dans neuf pays. Les laboratoires ont participé à une expérience planifiée pour laquelle le pouvoir mutagène de certaines substances (préparations chimiques complexes du type rencontré dans l'environnement) fut évalué à l'aide du test d'Ames. Un protocole rigoureux fut suivi. Le but principal de l'étude était d'examiner les variations intra- et inter-laboratoire dans les résultats du test. Les données consistent des comptes de colonies de salmonelle ayant subit une mutation inverse, à six doses différentes d'une substance. Chaque laboratoire participant fournit des données pour chacune des cinq substances à tester. Les bioessais furent effectués d'après un plan d'expérience factoriel prescrit. Trois groupes d'analystes participèrent à cette étude. Il leur fut demandé de modéliser la relation dose-réponse pour deux substances, de développer un indice pour la force de cette relation et d'évaluer les variations intra- et inter-laboratoire dans les résultats des bioessais. [ABSTRACT FROM AUTHOR]

The article presents comments on the relationship between the mean preference rating of a beer and the chemical and other variables for each beer and 90% prediction intervals for the sample of 37 beers with withheld preference ratings. The CDR and LP teams reportedly used a linear regression model for the mean preference rating in the form Yij = Ai + xijB + Eij. It is shown that in the two models that include the variables COLOUR, BU and 2-METHYL-1-BUTANOL only as main effects, the regression coefficients agree in sign but differ in magnitude.

Les brasseurs aiment connaǐtre la relation entre les caractéristiques chimiques de leurs bières et les préférences exprimées par les consommateurs. Deux ensembles de données furent fournis aux analystes. Le premier comprenait une série de caractéristiques chimiques mesurées sur 91 bières ainsi que des mesures de préférence, pour les měmes bières, recueillies lors de tests où les types de bières ne sont pas connus des dégustateurs. On demanda aux analystes d'utiliser ces données afin d'élaborer un modèle statistique permettant de relier les caractéristiques chimiques d'une bière aux préférences des consommateurs. Le deuxième ensemble de données était constitué de mesures sur 37 bières non incluses dans le premier ensemble. Les analystes devaient utiliser le modèle proposé afin de prédire la cote de préférence des consommateurs pour ces bières. On compare les performances des différents modèles proposés. [ABSTRACT FROM AUTHOR]

L'estimation des vents extrêcmes est essentielle aux travaux de génie mais pour obtenir de telles estimations, on doit tenir compte de considérations d'ordre statistique majeures. Dans I'étude de cas que nous présentons, on a fourni aux analystes des lectures à toutes les heures de la vitesse du vent, de sa direction et de la pression barométrique, mesures qui furent prélevées à cinq stations canadiennes durant des périodes d'observation couvrant plusieurs décennies. Leur tâche était de construire des estimations ponctuelles et par intervalle des vitesses de vent extrêmes déjà rencontrées à ces stations sur des périodes de 10, 20, 50 et 100 ans (il s'agit de quantiles). [ABSTRACT FROM AUTHOR]

Statistique Canada compile des données détaillées sur tous les homicides rapportés à la police à travers le pays. Dans cette étude, trois équipes d'analystes cherchent indépendamment à déceler une saisonnalité ou toute autre tendance temporelle dans le taux et la fréquence des homicides commis au Canada entre 1961 et 1980. [ABSTRACT FROM AUTHOR]

The article presents a study that deals with iceberg movements, weather, and ocean conditions in the vicinity of an oil-drilling platform in the South Labrador Sea. The study constructs a probabilistic forecasting model of iceberg motion. It aims to provide a platform operator with an estimate of the collision risk posed to the platform by a nearby iceberg.

The article describes a case study that illustrated the diversity of statistical analyses of the same empirical evidence. Two sets of analysts examine health data gathered from firefighters who were exposed to fumes and explosions from the Mississauga, Ontario train derailment in November 1979 to determine whether exposure to hazardous chemicals had lasting effects on the lung function of the Mississauga firefighters. Analysts were suggested to look for predictive values for some lung tests on healthy people.

Cet article étudie les méthodes de régression multiple applicables aux données progressivement censurées à droite et provenant d'une distribution gaussienne inverse. On utilise l'algorithme EM qui permet d'obtenir des estimateurs à maximum de vraisemblance et on présente ensuite les propriétés inhérentes à leur distribution asymptotique. La méthodologie est illustrée à l'aide de deux études de cas, dont une a trait à la caractéristique défectueuse de la distribution gaussienne inverse. Finalement, on tente d'établir un paralléle entre la methodologie utilisée dans les méthodes de régression pour échantillons complets à distribution gaussienne inverse et celle utilistée dans les autres méthodes de régression pour données de survie censurées. [ABSTRACT FROM AUTHOR]

The search for radiation sensitzers for use in radiotherapy is based on the assumption that proper use of these compounds will provide a differential sensitization of tumor and normal tissue. Based on the evidence that hypoxic cells exist within human tumors but not within normal cell populations, there is reason to believe that specific sensitizers of hypoxic cells might provide useful therapeutic benefit. This paper discusses the possible advantages of such sensitizers, over reliance on the phenomenon of reoxygenation, and describes very briefly the current status of hypoxic cell sensitizers. Finally a proposal is made concerning the way in which such sensitizers might be tested for their efficacy in human radiotherapy. [ABSTRACT FROM AUTHOR]

The Finsch Deep is an asymmetric rhomboidal basin, with a maximum depth of 5400 m, situated to the north of the Solomon Sea Triple Junction, Papua New Guinea. Anomalous slip vector azimuths, regional plate velocities, earthquake hypocenters, and bathymetric depth relative to surrounding terranes all indicate that the Finsch Deep is not a passive feature developed behind the subduction front. Our interpretation of all available data, including seismological studies, detailed bathymetry, side-scan character, and seismic sections, suggests that the Finsch Deep has developed due to N-S extension in the transition zone from continental collision west of the Solomon Sea Triple Junction to oceanic subduction to the east. The key mechanisms thought to drive 'convergent margin extension' within the New Guinea Collision are slab pull and oblique subduction. Researchers studying other convergent margins have recognized underplating and tectonic erosion as driving mechanisms for extension; though we have no evidence to either support or discount their presence within the New Guinea Collision. [ABSTRACT FROM AUTHOR]

This paper considers two independent risk situations for each of which the outcome may be either no loss or a specified loss. It investigates the relationships between independent, sequential, and joint decision approaches to determining whether insurance should be purchased against either type of loss. All three approaches lead to identical decisions when the disutility function is linear or exponential, whether of a convex or concave type. With other functions such as a quadratic, the approaches may lead to different acts. The differences in the acts selected can be explained by the "risk premium" implicit in the disutility function. [ABSTRACT FROM AUTHOR]

The author comments on a case study that analyzed extreme wind speed in five Canadian locations. According to the author, although different estimation methods were used by the investigators, the fact that both arrived on the same estimates on the same data is reassuring. The author adds that the task in this case is the estimation of extreme fractile such as extreme winds associated with tornadoes which was omitted, and a valid prediction interval would require that this source be taken into account by some means.

The article presents a case study that deals with the potential of statistical modelling and ARIMA methodology to describe and forecast iceberg paths. The models were applied using virtual real-time implementation for platform operator to use them on site and without processing delays. It questions the accuracy of the forecasts and risk assessments provided by the models to win the confidence of platform operators. It calls for settling other issues before determining the usefulness of such models.

Comments on an article by Duane G. Harris and Richard F. Nehring on a theoretical model of the maximum bid price for agricultural land and the application of the model to cash-grain farms in Iowa. Formulation of a revised model; Implications of the model; Application of the model to data provided by Harris and Nehring.

This article examines the application of a first hitting time (FHT) model, using an operational time scale, to assess mortality risk differentials of the work environment. A major case application is presented that applies the model to three job categories of railroad workers. The data set involves a study of more than 50 000 workers with mortality assessed from 1959 to 1996. Lung cancer mortality was assessed because of a suspected link to diesel exhaust exposure. Based on a model that stipulates that death occurs when the disease state of a subject first hits a threshold value, the FHT model provides insights into factors influencing disease progression. In this application, in particular, the findings suggest that a job category in 1959 alters the risk of death from lung cancer.