Model Averaging Using the Kullback Information Criterion in Estimating Effective Doses for Microbial Infection and Illness

Since the National Food Safety Initiative of 1997, risk assessment has been an important issue in food safety areas. Microbial risk assessment is a systematic process for describing and quantifying a potential to cause adverse health effects associated with exposure to microorganisms. Various dose-response models for estimating microbial risks have been investigated. We have considered four two-parameter models and four three-parameter models in order to evaluate variability among the models for microbial risk assessment using infectivity and illness data from studies with human volunteers exposed to a variety of microbial pathogens. Model variability is measured in terms of estimated ED01s and ED10s, with the view that these effective dose levels correspond to the lower and upper limits of the 1% to 10% risk range generally recommended for establishing benchmark doses in risk assessment. Parameters of the statistical models are estimated using the maximum likelihood method. In this article a weighted average of effective dose estimates from eight two- and three-parameter dose-response models, with weights determined by the Kullback information criterion, is proposed to address model uncertainties in microbial risk assessment. The proposed procedures for incorporating model uncertainties and making inferences are illustrated with human infection/illness dose-response data sets.     

The Boom‐Bust‐Recovery Cycle: Dynamics of Change in Community Satisfaction and Social Integration in Delta,Utah*

Abstract To better understand the long‐term effects of rapid boom growth, we reexamine four subjective indicators of community satisfaction and social integration in Delta, Utah, that were originally analyzed by Brown, Geertsen, and Krannich in 1989. With 24 years of longitudinal data, we find that within approximately a decade of the boom period three of the four indicators returned to or exceeded pre‐boom levels. We argue that we need to modify our theories and vocabulary regarding boomtowns to account for a “boom‐bust‐recovery cycle” that better takes into consideration the dynamic nature of communities and their residents and how they subjectively adjust to shifts in objective conditions.     

Homeless families today: Our challenge tomorrow

Family homelessness continues to be one of the most misunderstood and inadequately addressed public policy issues in America today. One reason is the scarcity of quantitative data available on the subject. In response, Columbia Universitys Graduate School of International and Public Affairs and the Institute for Children and Poverty designed and implemented an extensive survey on the demographics of homeless families in the New York City region. Data on more than 140 variables was collected from 743 homeless heads-of-household during the spring of 1997. The parents who were interviewed resided in fourteen emergency and transitional family shelters located throughout New York City and northern New Jersey. The following report summarizes the key elements of this research.     

Common sense: Why jobs and training alone won't end welfare for homeless families

With the advent of welfare reform, its proponents anticipate that millions of Americans chronically dependent on public assistance will be set free. In reality, far too many welfare recipients are trapped in a web of poverty from which they are incapable of escaping. Today, over a third of all welfare recipients are single, poorly-educated mothers with little or no work experience (Pavetti 1995, 3). Worse yet, extreme poverty has forced 600,000 of these families into homelessness. Common sense dictates that unless the states, in their new role as leaders in welfare innovation, immediately forge strategic policy, these women and their children–yet another generation–will sink deeper into poverty and dependence.     

Financial Health Economics

We provide a theoretical and empirical analysis of the link between financial and real health care markets. This link is important as financial returns drive investment in medical research and development (R&D), which, in turn, affects real spending growth. We document a “medical innovation premium” of 4–6% annually for equity returns of firms in the health care sector. We interpret this premium as compensating investors for government‐induced profit risk, and we provide supportive evidence for this hypothesis through company filings and abnormal return patterns surrounding threats of government intervention. We quantify the implications of the premium for the growth in real health care spending by calibrating our model to match historical trends, predicting the share of gross domestic product (GDP) devoted to health care to be 32% in the long run. Policies that had removed government risk would have led to more than a doubling of medical R&D and would have increased the current share of health care spending by more than 3% of GDP.     

The Changing Culture of Fatherhood in Comic‐Strip Families: A Six‐Decade Analysis

A content analysis of 490 Father's Day and Mother's Day comic strips published from 1940 to 1999 indicates that the culture of fatherhood has fluctuated since World War II. “Incompetent” fathers appeared frequently in the late 1940s, early 1950s, and late 1960s but were rarer in the late 1950s, early and late 1970s, early 1980s, and early 1990s. Fathers who were mocked were especially common in the early and late 1960s and early 1980s but were less common in the late 1940s, early and late 1950s, and early and late 1970s. Fathers who were nurturant and supportive toward children were most evident in the late 1940s, early 1950s, and early and late 1990s, with the longitudinal pattern resembling a U‐shaped curve. Differences between fathers and mothers also oscillated from one decade to the next.     

Missing values in replicated Latin squares

Designs based on any number of replicated Latin squares are examined for their robustness against the loss of up to three observations randomly scattered throughout the design. The information matrix for the treatment effects is used to evaluate the average variances of the treatment differences for each design in terms of the number of missing values and the size of the design. The resulting average variances are used to assess the overall robustness of the designs. In general, there are 16 different situations for the case of three missing values when there are at least three Latin square replicates in the design. Algebraic expressions may be determined for all possible configurations, but here the best and worst cases are given in detail. Numerical illustrations are provided for the average variances, relative efficiencies, minimum and maximum variances and the frequency counts, showing the effects of the missing values for a range of design sizes and levels of replication.