On the Convergence of the Monte Carlo Maximum Likelihood Method for Latent Variable Models

While much used in practice, latent variable models raise challenging estimation problems due to the intractability of their likelihood. Monte Carlo maximum likelihood (MCML), as proposed by Geyer & Thompson (1992 ), is a simulation-based approach to maximum likelihood approximation applicable to general latent variable models. MCML can be described as an importance sampling method in which the likelihood ratio is approximated by Monte Carlo averages of importance ratios simulated from the complete data model corresponding to an arbitrary value of the unknown parameter. This paper studies the asymptotic (in the number of observations) performance of the MCML method in the case of latent variable models with independent observations. This is in contrast with previous works on the same topic which only considered conditional convergence to the maximum likelihood estimator, for a fixed set of observations. A first important result is that when is fixed, the MCML method can only be consistent if the number of simulations grows exponentially fast with the number of observations. If on the other hand, is obtained from a consistent sequence of estimates of the unknown parameter, then the requirements on the number of simulations are shown to be much weaker.     

UNDERSTANDING THE DECISION TO PARTICIPATE IN A SURVEY

The lack of full participation in sample surveys threatens theinferential value of the survey method. We review a set of conceptualdevelopments and experimental findings that appear to be informativeabout causes of survey participation; offer an integration ofthat work with findings from the more traditional statisticaland survey methodological literature on nonresponse; and, giventhe theoretical structure, deduce potentially promising pathsof research toward the understanding of survey participation.     

Assessing Risk of Victimization through Epidemiological Concepts: An Alternative Analytic Strategy Applied to Routine Activities Theory*

Cet article fait appel aux concepts et aux techniques de l'épidémiologie pour examiner la capacité de la théorie des activités routinières à expliquer le risque de victimisation criminelle. En allant au-delà de l'identification des facteurs de risque de victimisation, les auteurs se demandent comment les changements des facteurs de causalité pourraient influer sur ce risque dans la population générale. lis trouvent que les prédicteurs établis avec des méthodes plus traditionnelles expliquent la plus grande partie du risque, mais que certains sont moins importants pour la compréhension du risque de la population dans l'ensemble en raison du petit nombre de personnes qui leur est associé, tandis que d'autres sont plus utiles parce qu'ils s'appliquent à un plus grand nombre de personnes.
This paper draws upon concepts and techniques from epidemiology to examine the ability of routine activities theory to account for the risk of criminal victimization. Moving beyond the identification of risk factors for victimization, we ask how changes to causal factors might affect the risk of victimization in the general population. We find that predictors identified with more traditional methods account for the bulk of the risk, but that some are less important for understanding overall population risk because of the small numbers of people associated with them, while others are more helpful because they apply to larger numbers.     

DO NEWLY RETIRED WORKERS IN THE UNITED STATES HAVE SUFFICIENT RESOURCES TO MAINTAIN WELL‐BEING?

A current policy issue is the extent to which savings are sufficient to sustain economic well-being in retirement. We compare annuitized wealth at retirement to three preretirement consumption estimates. About one-half of new retirees have insufficient resources to enable the full maintenance of estimated preretirement consumption in retirement, and about 40% fail to meet the "0.7 of earnings" standard that is used in many studies. Using standards reflecting social (poverty) norms we find a less serious problem. About 5% (25%) of new retirees have insufficient resources to enable an above-poverty (near-poverty) level of living during retirement. (JEL J14, J26 )     

ON THE INDEPENDENCE OF THE SAMPLE MEAN AND TRANSLATION-INVARIANT STATISTICS FOR MATRIX NORMAL DISTRIBUTIONS

We present an explicit characterization of the joint dependency structure of an n×p matrix normal random matrix such that the p-dimensional sample mean vector is independent of all translation invariant statistics.     

The Canadian syndrome of regional polarities: an obituary

Les études dans lesquelles il est question des différences entre les régions du Canada mentionnent souvent un phénomène appelé le «syndrome des polarités»; il s'agit de la tendance à l'augmentation, d'est en ouest, des taux de plusieurs indicateurs sociaux, dont le divorce, le suicide et la criminalité. L'auteur de cette communication, estimant que ce syndrome appartient plutǒt à l'histoire, démontre que les taux de suicide et de divorce convergent dans toutes les régions canadiennes depuis 1921 et met cette tendance en relation avec les résultats d'une analyse récente des taux de criminalité régionaux. The ‘syndrome of polarities’ whereby rates for social indicators such as divorce, suicide, and crime rise from east to west is often noted in studies of Canadian regional differences. There are, however, reasons to view this polarity as an historical remnant, and the paper shows a convergence in regional suicide and divorce rates since 1921. The trend is tied in with a recent analysis of regional crime rates.     

From the Environment to the Workplace and Back Again? Occupational Health and Safety Activism in Ontario, 1970s–2000*

Cet article aborde la question des alliances entre les mouvements sociaux au moyen d'une étude sur la possibilité d'une convergence ou d'une alliance entre deux des mouvements sociaux les plus stables en Ontario au cours des trois dernières décennies: la santé et la sécurité au travail (SST) et les mouvements environnementaux. Les deux mouvements ont non seulement duré, mais ils ont été couronnés de succès. Aujourd'hui, cependant, chaque mouvement est fractionné et au repos. Les développements politiques récents poussent plusieurs activistes des mouvements ouvriers ou de la SST à réclamer une alliance avec les mouvements environnementaux. L'auteur soutient que, bien qu'il existe un bénéfice pour les deux mouvements en de telles entreprises, des différences de classes continuelles entre ces deux mouvements militent contre toute alliance durable. This article addresses the issue of alliances between social movements through an investigation into the possibility of a convergence and/or alliance between two of the most enduring social movements in Ontario over the past three decades: the occupational health and safety (OHS) and the environmental movements. Both movements have not only endured, but been successful movements. Presently, however, each movement is fragmented and becalmed. Recent political developments are leading many OHS/labour movement activists to argue for an alliance with environmental movements. I argue that while there is benefit to both movements in such undertakings, continuing class differences between these two movements militates against any enduring alliance.     

WHO GETS THE NEWS? ALTERNATIVE MEASURES OF NEWS RECEPTION AND THEIR IMPLICATIONS FOR RESEARCH

This article investigates patterns in audience reception of16 news stories that received prominent media coverage in thesummer and fall of 1989. Using a national sample of Americanadults, it compares education, self-reported rates of mediause, interpersonal communication, and prior levels of generalpolitical knowledge as predictors of individual differencesin recall of current news events. Results indicate that respondents'background level of political knowledge is the strongest andmost consistent predictor of current news story recall acrossa wide range of topics, suggesting that there is indeed a generalaudience for news and that this audience is quite sharply stratifiedby preexisting levels of background knowledge. Thus, in surveyresearch applications that require estimates of individual differencesin the reception of potentially influential political communications,a measure of general prior knowledge—not a measure ofnews media use—is likely to be the most effective indicator.The article further concludes that the tendency of individualsto acquire news and information on a domain- or topic-specificbasis fails to undermine the value of political knowledge asa general measure of propensity for news recall.     

USING DUAL FRAME DESIGNS TO REDUCE NONRESPONSE IN TELEPHONE SURVEYS

This article reports on the results of a series of experimentsdesigned to improve response rates for telephone surveys. Inthree surveys telephone households were selected using bothstandard random digit dialing (RDD) techniques and lists oftelephone numbers purchased from a commercial firm. In the RDDportions of the samples "cold contact" interviewing methodswere used; in the list frame portions advance letters were mailed,and the listed household name was used in the introduction.Experiments were designed to test the effects on response ratesof the advance letters and use of the listed household nameas a means of establishing rapport. The advance letters increasedresponse rates, but no difference could be attributed to theuse of names. The mixture of RDD and list sampling techniquesis also used to evaluate the effects of relative response rateson substantive findings. The cost consequences of these dualframe designs are assessed along a number of dimensions, andthe cost and error components of these designs are discussed.