BAYESIAN SUBSET SELECTION AND MODEL AVERAGING USING A CENTRED AND DISPERSED PRIOR FOR THE ERROR VARIANCE

This article proposes a new data‐based prior distribution for the error variance in a Gaussian linear regression model, when the model is used for Bayesian variable selection and model averaging. For a given subset of variables in the model, this prior has a mode that is an unbiased estimator of the error variance but is suitably dispersed to make it uninformative relative to the marginal likelihood. The advantage of this empirical Bayes prior for the error variance is that it is centred and dispersed sensibly and avoids the arbitrary specification of hyperparameters. The performance of the new prior is compared to that of a prior proposed previously in the literature using several simulated examples and two loss functions. For each example our paper also reports results for the model that orthogonalizes the predictor variables before performing subset selection. A real example is also investigated. The empirical results suggest that for both the simulated and real data, the performance of the estimators based on the prior proposed in our article compares favourably with that of a prior used previously in the literature.     

Use of Sensitivity Analysis to Assess Reliability of Metabolic and Physiological Models

Because ethical considerations often preclude directly determining the human health effects of treatments or interventions by experimentation, such effects are estimated by extrapolating reactions predicted from animal experiments. Under such conditions, it must be demonstrated that the reliability of the extrapolated predictions is not excessively affected by inherent data limitations and other components of model specification. This is especially true of high-level models composed of ad hoc algebraic equations whose parameters do not correspond to specific physical properties or processes. Models based on independent experimental data restricting the numerical space of parameters that do represent actual physical properties can be represented at a more detailed level. Sensitivities of the computed trajectories to parameter variations permit more detailed attribution of uncertainties in the predictions to these low-level properties. S-systems, in which parameters are estimated empirically, and physiological models, whose parameters can be estimated accurately from independent data, are used to illustrate the applicability of trajectory sensitivity analysis to lower-level models.     

Effects of the Mechanism of Receptor-Mediated Gene Expression on the Shape of the Dose-Response Curve

A mathematical model of receptor-mediated gene expression that includes receptor binding of natural and xenobiotic ligands, protein synthesis and degradation, and metabolism of the xenobiotic ligand was created to identify the determinants of the shape of the dose-response profile. Values of the model's parameters were varied to reflect alternative mechanisms of expression of the protein. These assumptions had dramatic effects on the computed response to a bolus dose of the xenobiotic ligand. If all processes in the model exhibit hyperbolic kinetics, the dose-response curves can appear sigmoidal but actually be linear with a positive slope at low doses. The slope of the curve only approached zero at low dose, indicative of a threshold for response, if binding of the xenobiotic ligand to the receptor exhibited positive cooperativity (ligand binding at one site increases the affinity for ligand at another binding site on the receptor). Positive cooperativity in the rate-limiting step of protein synthesis produced dose-response curves which were "U-shaped" at low doses, also indicative of a threshold. Positive cooperativity in the metabolism of the xenobiotic ligand produced dose-response curves that increased more rapidly than linearly with increasing dose. The model illustrates the fact that response cannot be predicted from qualitative mechanistic arguments alone; any assessment of risk to health from xenobiotic chemicals must be based on a detailed quantitative examination of the kinetic behavior of each chemical species individually.     

Residential Mortgages and Public Policy: What to do with Fannie and Freddie?

The current debate on U.S. housing policy focuses on the role of the government in supporting the mortgage market. Existing organizations (Fannie Mae/Freddie Mac) are in conservatorship status, and Congress is considering alternative structures and guarantees including the Johnson‐Crapo bill, to provide catastrophic insurance in support of the coverage from private companies. The resolution of this issue is complicated by the various activities involved in the issue—investment securities, public policy, macroeconomics, accounting, and insurance. This article reviews the impact of these activities on U.S. housing, with a discussion of the feasibility of creating a catastrophic insurance program similar to that of the Federal Deposit Insurance Corporation. The federal government has successfully operated catastrophic insurance programs in support of private sector initiatives, and this experience—while certainly not perfect—may be a reasonable approach to the current Fannie/Freddie dilemma.     

Shorter hours wanted? A systematic review of working-time preferences and outcomes

Changes in working time have important economic, social and environmental implications. However, research on workers' preferences is highly fragmented across disciplines and journals. To overcome this, the present article provides a systematic review of the literature, analysing 173 studies. The study shows that working-time outcomes and mismatches are mostly studied in a small group of OECD countries, using survey data and statistical methods. The most clear and consistent results are about gender, care responsibilities and current working hours. Among professions, only the medical workforce receives substantial attention. Norms and preference formation are poorly understood, and more qualitative research is essential to understand how working-time reductions could spread.     

Improving the Mental Health Outcomes of LGBTQ Youth and Young Adults: A Longitudinal Study

ABSTRACT

The purpose of this groundbreaking study was to evaluate outcomes of 482 LGBTQ (lesbian, gay, bisexual, transgender, or questioning) youth and young adults who received services and supports through the Comprehensive Community Mental Health Services for Children with Serious Emotional Disturbances Program (CMHI). This study was a secondary data analysis using data from a larger study of 3208 LGBTQ and non-LGBTQ youth ages 11 through 21 who had a serious emotional disturbance (SED). This study is significant in that it evaluates functional outcomes for young people identified as LGBTQ based on a specialized service framework (i.e., system of care approach). In essence, do LGBTQ youth with SED benefit from a specific approach to intervention? In addition, a comparison at intake on suicidality, bullying and victimization was conducted between the LGBTQ and non-LGBTQ identifying youth from the larger sample. The youth and a caregiver were interviewed face-to-face separately at intake, 6-months, and 12-months. Significant improvements were found across all of the dependent variables, supporting the viability of SOC for improving outcomes for LGBTQ youth. Future research should continue to build on this study by adding to the design a control group to improve internal validity of the findings.     

A flexible particle Markov chain Monte Carlo method

Particle Markov Chain Monte Carlo methods are used to carry out inference in nonlinear and non-Gaussian state space models, where the posterior density of the states is approximated using particles. Current approaches usually perform Bayesian inference using either a particle marginal Metropolis–Hastings (PMMH) algorithm or a particle Gibbs (PG) sampler. This paper shows how the two ways of generating variables mentioned above can be combined in a flexible manner to give sampling schemes that converge to a desired target distribution. The advantage of our approach is that the sampling scheme can be tailored to obtain good results for different applications. For example, when some parameters and the states are highly correlated, such parameters can be generated using PMMH, while all other parameters are generated using PG because it is easier to obtain good proposals for the parameters within the PG framework. We derive some convergence properties of our sampling scheme and also investigate its performance empirically by applying it to univariate and multivariate stochastic volatility models and comparing it to other PMCMC methods proposed in the literature.     

The ambivalent image of jews in the minds of christian fundamentalists

This paper discusses the varied ways Christian fundamentalists think about Jews and Israel in their theology and in their daily lives. Topics include the continuing significance for fundamentalists of Jewish responsibilities for the death of Jesus, the place of the Holocaust imagery and especially the importance of the creation of the state of Israel in 1948, and the instrumental role fundamentalists believe Jews play in the end- time story leading up to the return of Jesus to Mount of Olives and the making of a new Jerusalem and the beginning of the millennium. The paper suggests that in these ambivalent images lies much social distress in the form of anti- semitism, distortion of our Middle East policy, and the erosion of efforts to create a human ecumenism.An earlier version of this paper appeared in translation as Das zweitdeutige Bild des Juden in Bewusstsein christlicher Fundamentalisten, inBrennpunkte des gegenwartigen Antisemitismus, a book published by the Center for the Study of Anti-Semitism, Free University of Berlin.