Conditional Likelihood Estimators for Hidden Markov Models and Stochastic Volatility Models

ABSTRACT.  This paper develops a new contrast process for parametric inference of general hidden Markov models, when the hidden chain has a non-compact state space. This contrast is based on the conditional likelihood approach, often used for ARCH-type models. We prove the strong consistency of the conditional likelihood estimators under appropriate conditions. The method is applied to the Kalman filter (for which this contrast and the exact likelihood lead to asymptotically equivalent estimators) and to the discretely observed stochastic volatility models.     

A Bayesian Hierarchical Model for the Evaluation of a Website

Consider a website and the surfers visiting its pages. A typical issue of interest, for example while monitoring an advertising campaign, concerns whether a specific page has been designed successfully, i.e. is able to attract surfers or address them to other pages within the site. We assume that the surfing behaviour is fully described by the transition probabilities from one page to another, so that a clickstream (sequence of consecutively visited pages) can be viewed as a finite-state-space Markov chain. We then implement a variety of hierarchical prior distributions on the multivariate logits of the transition probabilities and define, for each page, a content effect and a link effect. The former measures the attractiveness of the page due to its contents, while the latter signals its ability to suggest further interesting links within the site. Moreover, we define an additional effect, representing overall page success, which incorporates both effects previously described. Using WinBUGS, we provide estimates and credible intervals for each of the above effects and rank pages accordingly.     

Poverty and social trends in Russia

The article describes the socioeconomic situation of the Russian population and its dynamics in 1992. The analysis is based on series of regional sociological surveys led by the All-Russian Living Standards Research Center and on official Russian statistical data. The basic unit of analysis is the family, and hence family typology approbated both in research and in practical social work is introduced. Besides describing and discussing the growing poverty tendencies in contemporary Russia, the article also contains methodological recommendations for social policy bodies and social workers on the strategy of work in social maintenance and social support of the least secure population strata.     

Employment and filial relations: Is there a conflict?

Since children, particularly daughters, are among the most important sources of help and support for older Americans, it has been suggested that women's increasing employment will affect filial relations. Empirical evidence on this issue is inconsistent, in part due to the use of nonprobability samples. Few studies have measured effects for men. We attempt to broaden the scope of this question beyond help to the frail elderly by asking whether employment affects filial relations in general. We examine effects of hours employed on telephone contact, visiting, feelings of closeness, filial attitudes, and assistance to biological parents, for an area probability sample of men and women over 40. There are no effects of employment for men or women on contact, closeness, or assistance. For the vast majority of this population sample, contact and assistance involve few hours per week, and thus do not seem to conflict with employment.     

Work/Care Regimes: Institutions,Culture and Behaviour and the Australian Case

Increasingly around the industrialized world, labour markets rely upon the paid work of women, many of whom have dependents. Such changing patterns of paid work by women — and by men — are located within work/care regimes that are more or less hostile to the needs of paid workers who care for others. This article sets out a model of work/care regimes and locates the Australian case within international and historical contexts. In Australia, the unchanging normative male worker archetype dominates institutions of work and care, while the cultures of motherhood and fatherhood remain stoically resistant to renovation. In the meantime, the behaviour of working women runs ahead of these unchanging cultures and institutions, creating a policy interest in ‘reconciling’ work and care, but a failure to provide it. The reasons for this failure are outlined.     

Who Gets What From Government? Distributional Consequences of Child‐Care Assistance Policies

Given the fragmented structure of child‐care assistance in the United States, it has been difficult to obtain accurate estimates of which families are assisted, through which mechanisms, and at what level. Making use of survey data from New York City, we analyze the distribution of several forms of public child‐care assistance. Results suggest that about 40% of all families with young children receive some form of child‐care assistance. Considering all forms of assistance, the distribution of child‐care help is targeted in both expected and some unexpected ways. Implications of these results are discussed in the context of U.S. child‐care policies governing access and benefit levels.     

The Division of Household Labor in Germany and Israel

We compare the patterns of household division of labor in Germany and Israel—two countries that share key elements of the corporatist welfare regime but differ in their gender regimes—and evaluate several hypotheses using data from the 2002 International Social Survey Program. Although time constraints and relative resources affect the division of household labor and women’s housework in both societies, we find that in Germany the gender order of household labor is more rigid, whereas in Israel the spouses’ linked labor market status exerts distinctive effects. We also find significant relationships between gender ideology and the division of household labor. We discuss the theoretical advantages of approaching the comparative study of gender inequality from the vantage point of family and gender regimes.     

African American family life in societal context: Crisis and hope

Since 1965 hundreds of articles and books have been published about African American families. Nevertheless, our understanding of these families continues to be limited. There is a tendency to gloss over important within-group differences; thus, monolithic, stereotypic and inaccurance portrayals of Black family life are common. This paper sets aside debates of Black family pathology or viability, focusing instead on these families' essential character. The paper seeks to understand Black families on their own terms, locating them in relevant social, historical, political and cultural contexts. Key empirical patterns and trends reveal dramatic changes in Black family geographic location, headship, quality of life and socioeconomic status since 1950.A complex picture is revealed. There has been gradual but steady overall improvement alongside persistent, extreme racial disparties and pronounced class disparities among Black families. The proposed Black Family Socio-Ecological Context model specifies and connects institutional, interpersonal, environmental, temporal and cultural facts that shape the essential character of Black family life in such a way as to produce characteristics simultaneously shared and idiosyncratic. The model also provides an organized, systematic accounting of research and public policy issues relevant to the study of African American families.An early version co-authored with Richard A. English was presented during the National Council on Family Relations Meetings in Portland, Oregon, October 1980.     

Exposure Reconstruction for the TCDD-Exposed NIOSH Cohort Using a Concentration- and Age-Dependent Model of Elimination

Recent studies demonstrating a concentration dependence of elimination of 2,3,7,8-tetrachlorodibenzo-p-dioxin (TCDD) suggest that previous estimates of exposure for occupationally exposed cohorts may have underestimated actual exposure, resulting in a potential overestimate of the carcinogenic potency of TCDD in humans based on the mortality data for these cohorts. Using a database on U.S. chemical manufacturing workers potentially exposed to TCDD compiled by the National Institute for Occupational Safety and Health (NIOSH), we evaluated the impact of using a concentration- and age-dependent elimination model (CADM) (Aylward et al., 2005) on estimates of serum lipid area under the curve (AUC) for the NIOSH cohort. These data were used previously by Steenland et al. (2001) in combination with a first-order elimination model with an 8.7-year half-life to estimate cumulative serum lipid concentration (equivalent to AUC) for these workers for use in cancer dose-response assessment. Serum lipid TCDD measurements taken in 1988 for a subset of the cohort were combined with the NIOSH job exposure matrix and work histories to estimate dose rates per unit of exposure score. We evaluated the effect of choices in regression model (regression on untransformed vs. ln-transformed data and inclusion of a nonzero regression intercept) as well as the impact of choices of elimination models and parameters on estimated AUCs for the cohort. Central estimates for dose rate parameters derived from the serum-sampled subcohort were applied with the elimination models to time-specific exposure scores for the entire cohort to generate AUC estimates for all cohort members. Use of the CADM resulted in improved model fits to the serum sampling data compared to the first-order models. Dose rates varied by a factor of 50 among different combinations of elimination model, parameter sets, and regression models. Use of a CADM results in increases of up to five-fold in AUC estimates for the more highly exposed members of the cohort compared to estimates obtained using the first-order model with 8.7-year half-life. This degree of variation in the AUC estimates for this cohort would affect substantially the cancer potency estimates derived from the mortality data from this cohort. Such variability and uncertainty in the reconstructed serum lipid AUC estimates for this cohort, depending on elimination model, parameter set, and regression model, have not been described previously and are critical components in evaluating the dose-response data from the occupationally exposed populations.