摘要:

Various compromises that have occurred between Bayesian and non-Bayesian methods are reviewed. (A citation is provided that discusses the inevitability of compromiseswithinthe Bayesian approach.) One example deals with the masses of elementary particles, but no knowledge of physics will be assumed.

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475256

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

We discuss and comment on the use of statistics in a number of topical issues in forensics and medicine. The forensic issues are scientific misconduct, DNA pattern matching, and causal analysis. In the biomedical area, particular statistical approaches are suggested for problems of mass screening, interim analysis, and the regulation of chronic diseases.

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475257

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

Taking the absolute number of CD4 T-cells as a marker of disease progression for persons infected with the human immunodeficiency virus (HIV), we model longitudinal series of such counts for a sample of 327 subjects in the San Francisco Men's Health Study (Waves 1–8, excluding zidovudine cases). We conduct a fully Bayesian analysis of these data. We employ individual level nonlinear models incorporating such critical features as incomplete and unbalanced data, population covariates (age at study entry and an indicator of self-reported herpes simplex virus infection), unobserved random change points, heterogeneous variances, and errors in variables. We construct prior distributions using results of previously published work from several different sources and data from HIV-negative men in this study. We also develop an approach to Bayesian model choice and individual prediction. Our analysis provides marginal posterior distributions for all population parameters in our model for this cohort. Using an inverse prediction approach, we also develop the posterior distributions of time for CD4 T-cell number to reach a specified level.

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475258

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475259

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475260

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475261

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

Maternal-to-infant transmission of the human immunodeficiency virus (HI V) accounts for most cases of acquired immune deficiency syndrome (AIDS) in children. In New York City more than 500 cases of AIDS attributed to such transmission were reported before the end of 1989; this accounts for 80% of the cases of pediatric AIDS in the United States. In addition to surveillance of AIDS cases, the New York State Health Department instituted a program to screen the blood of newborns for presence of HIV antibodies in December 1987. Such antibodies imply that the mother, although not necessarily the child, is infected with HIV. The new methods we propose in this article allow us to combine the two types of information to estimate the risk of AIDS for the first 10 years of life. They also make it possible to estimate the number of children born to infected mothers since the start of the epidemic and to project the future number of cases of pediatric AIDS. From these projections it appears that the case load and the average age at diagnosis will increase steadily throughout the early 1990s. The statistical problem that we address concerns making inferences about processes of infection, disease, and reporting for which realizations are right- (and perhaps left-) truncated. Further complication arises from the fact that the reporting delay distribution appears to be changing over chronologic time.

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475262

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

We propose time-dependent association measures for application to bivariate survival analysis. Such association measures provide informative summaries for data on twins, ophthalmic and auditory studies, and for other matched-pair designs. We develop several desirable properties of time-dependent association measures and study three measures motivated by these properties. We examine the measures from a general bivariate survival perspective and for the proportional hazards frailty model. We use monozygotic (MZ) and dizygotic (DZ) twin data from the Danish Twin Registry to illustrate how these measures depend on the specification of the proportional hazards frailty model. This model consists of two components: a baseline hazard function and a frailty distribution. We produce gamma and nonparametric maximum likelihood estimates of the frailty distribution and estimate a Gompertz baseline hazard function. For two of the measures, a nonparametric estimate provides a comparison to the model-based estimates. As expected, the MZ twins display greater association at all ages, but the association measures give different insights into the association structure.

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475263

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

We use the concept of a latent variable to derive the joint distribution of a continuous and a discrete outcome, and then extend the model to allow for clustered data. The model can be parameterized in a way that allows one to write the joint distribution as a product of a standard random effects model for the continuous variable and a correlated probit model for the discrete variable. This factorization suggests a convenient approach to parameter estimation using quasi-likelihood techniques. Our approach is motivated by the analysis of developmental toxicity experiments for which a number of discrete and continuous outcomes are measured on offspring clustered within litters. Fetal weight and malformation data illustrate the results.

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475264

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor

摘要:

Time series methods are used to make long-run forecasts, with confidence intervals, of age-specific mortality in the United States from 1990 to 2065. First, the logs of the age-specific death rates are modeled as a linear function of an unobserved period-specific intensity index, with parameters depending on age. This model is fit to the matrix of U.S. death rates, 1933 to 1987, using the singular value decomposition (SVD) method; it accounts for almost all the variance over time in age-specific death rates as a group. Wherease0has risen at a decreasing rate over the century and has decreasing variability,k(t) declines at a roughly constant rate and has roughly constant variability, facilitating forecasting.k(t), which indexes the intensity of mortality, is next modeled as a time series (specifically, a random walk with drift) and forecast. The method performs very well on within-sample forecasts, and the forecasts are insensitive to reductions in the length of the base period from 90 to 30 years; some instability appears for base periods of 10 or 20 years, however. Forecasts of age-specific rates are derived from the forecasts ofk, and other life table variables are derived and presented. These imply an increase of 10.5 years in life expectancy to 86.05 in 2065 (sexes combined), with a confidence band of plus 3.9 or minus 5.6 years, including uncertainty concerning the estimated trend. Whereas 46% now survive to age 80, by 2065 46% will survive to age 90. Of the gains forecast for person-years lived over the life cycle from now until 2065, 74% will occur at age 65 and over. These life expectancy forecasts are substantially lower than direct time series forecasts ofe0, and have far narrower confidence bands; however, they are substantially higher than the forecasts of the Social Security Administration's Office of the Actuary.

ISSN:0162-1459    

DOI:10.1080/01621459.1992.10475265

出版商:Taylor & Francis Group    

年代:1992

数据来源: Taylor