Suchergebnisse

For the most part, random roadside traffic surveys represent complex rather than simple random samples. It is known that the design effects due to clustering, for example, often inflate the standard errors of various point estimates calculated from such surveys. This study examines the design effects in random roadside surveys conducted in three Canadian provinces in 1981. Calculating the standard errors of ratio meansforfour BA C categories, four age categories and gender in those surveys, two major conclusions were drawn. First, the calculated design effects (DEFF) were all greater than 1.0, rangingfrom 1.90 to 32.26. This implies that the standard errors of the estimates are from 1.38 to 5.68 times larger than would be obtained from simple random samples of the same size. Clustering and unequal weighting both had a major impact on increasing the overall DEFF, while countervailing stratification procedures did not reduce the effect. Second, the design effects varied considerably across the surveys even though the same basic sampling strategy was employed in all three. Further, the design effects also varied across subcategories of the same variable.

Abstract: The two decades from 1830 to 1850 saw major growth in the collection and analysis of official crime statistics in England and Wales. Much of that data was collected in an attempt to understand the growing social problems engendered by a burgeoning industrial society. Unfortunately, many of the theoretical problems and policy issues the early Victorians attempted to address could not be answered due to the lack of appropriate statistical tools. This study reexamines a major data set first published by Fletcher in the late 1840s on factors influencing regional variations in crime rates throughout England. Using standard regression analysis, it is evident that the conclusions to be drawn from the data are quite different from those proposed by Fletcher in his own analysis. It is also concluded that these and similar data of the period offer a wealth of information which might be valuable to contemporary criminologists.

Cette communication traite des rapports entre l'âge, le sexe et les quatre principales causes de décès violent, soit l'homicide, le suicide, les accidents de la route et les 'autres' accidents. D'aucuns ont soutenu que ces quatre causes de décès violents sont l'expression d'une prédilection pour les comportements excessivement risqués. Par ailleurs, les partisans de la théorie de la convergence postulent que les écarts entre hommes et femmes en ce qui concerne les comportements à risque diminueront au fur et à mesure que la proportion des femmes au sein de la population active augmentera et que l'égalitarisme se répandra même si, traditionnellement, ce sont surtout les hommes qui sont portés à prendre des risques. L'analyse de données pour le Canada révèle que les taux de mortalité pour cause violente chez les hommes et les femmes ne se sont pas rapprochés ce qui ne tend guère à confirmer la théorie de la convergence. L'auteur note, par contre, que des changements importants se sont produits sur le plan des taux de mortalité par classe d'âge au cours de la période étudiée.This research examines the relationship between gender, age, and four principal causes of violent death ‐ homicide, suicide, motor vehicle accidents, and 'other' accidents. It has been argued that these four causes of violent death result from a predilection to excessive risk‐taking behaviour. It has also been suggested by convergence theorists that although risk‐taking is traditionally a male dominated activity, with the increase in the proportion of women in the labour force, and increasing egalitarianism, the gap between male and female risk‐taking should narrow. Using Canadian data to test this assumption, our findings reveal continuing differences between male and female rates of violent death, and little support for convergence theory. Significant changes are also noted in the pattern of age‐specific mortality rates over the period of investigation.

Selon Richard Easterlin, le taux de fertilite d'une cohorte est inversement proportionnel a sa taille relative. C'est principalement aux Etats‐Unis qu'on a trouve des donneespeut‐itre pas a ce pays. En general, il semble qu'au Canada les taux de fertilite relatifs de grosses cohortes sont plus Pleves que ceux de cohortes plus petites, et ceci malgre le fait que les taux de fertilite ont diminue pour toutes les cohortes au cours des dernieres annees. Lorsque I'on examine la taille relative des cohortes en contrdant les effets d'ige et de periode, la relation entre la taille de la cohorte et son taux de fertilitP disparait completernent ce qui reduit plus encore la validite de I'hypothPse de EasterlinRichard Easterlin has argued that the fertility rate of a cohort is inversely related to the relative size of that cohort. Evidence to support this proposition has been derived primarily from studies in the United States. A breakdown of Canadian fertility trends to decompose age, period and cohort effects suggests that Easterlin's hypothesis may not hold for the Canadian situation. Overall, larger Canadian cohorts appear to have higher relative fertility rates than do smaller cohorts, despite the fact that fertility rates have declined across all cohorts in recent years. Focusing on relative cohort size, and controlling for age and period effects, the relationship between cohort size and fertility disappears completely further minimizing the validity of the Easterlin Hypothesis. supportant cette these. Une analyse de la fertilite au Canada, qui distingue entre les effets d'ige, de periode et de cohorte indique que I'hypothese de Easterlin ne s'applique

Cet article pose trois questions: 1) Pourquoi étudier les inégalités entre les autochtones? 2) Quel est l'écart entre les salaires et les revenus de la population canadienne en général et ceux des différents peuples autochtones? et 3) Jusqu'à quel point existe‐t‐il des inégalités entre les peuples autochtones ainsi qu'entre la population autochtone et la population non autochtone? Cet article montre une tendance générale de l'augmentation des disparités mesurées ainsi que de la polarisation des revenus chez tous les groupes autochtones compara‐tivement à la population non autochtone. Pour ce qui est de l'inégalité entre les groupes autochtones, les Inuits se classent au sommet de la pyramide, suivis des Indiens inscrits, des Indiens non inscrits et, finalement, des Métis.This article addresses three questions: 1) Why study intra‐Aboriginal inequality? 2) What is the gap in wages and income between the general Canadian population and the different Aboriginal peoples? and 3) How much inequality exists within the Aboriginal groups and between Aboriginal groups and the non‐Aboriginal population? The article points to a general pattern of increase in measured disparity and polarization in income for all Aboriginal groups in comparison to the non‐Aboriginal population. In terms of intra‐Aboriginal inequality, Aboriginal groups rank from Inuit at the high end, through Status Indians, to non‐status Indians and, finally, to Métis.