Bayesian D-optimal supersaturated designs

We introduce a new class of supersaturated designs using Bayesian D-optimality. The designs generated using this approach can have arbitrary sample sizes, can have any number of blocks of any size, and can incorporate categorical factors with more than two levels. In side by side diagnostic comparisons based on the E(s²)$E(s^2)$ criterion for two-level experiments having even sample size, our designs either match or out-perform the best designs published to date. The generality of the method is illustrated with quality improvement experiment with 15 runs and 20 factors in 3 blocks.     

Mediated Political Communication in Australia: leading issues,new evidence

New 2007 survey data on political communication is used to study the relation between commercial and ABC/SBS television consumption and Australian political and civic culture. The first section outlines the demographic characteristics of viewers who rely, respectively, for their news and current affairs, on commercial as compared with public service television. This is followed by a profile of popular views on the concentration of media ownership in Australia. The paper then shows that levels of trust in other people are higher for those who rely on public service television. Similarly, knowledge about basic constitutional facts is shown to be positively related to a preference for public service television news consumption. The same holds for civic engagement. The conclusions imply that Australians generally favour stronger public interest regulation of commercial television broadcasting. The conclusion explains that media regulation in Australia generally lags behind public preferences for a more explicitly democratic regulatory regime.     

Allowing Family to be Family: End-of-Life Care in Veterans Affairs Medical Foster Homes

The Medical Foster Home program is a unique long-term care program coordinated by the Veterans Health Administration. The program pairs Veterans with private, 24-hour a day community-based caregivers who often care for Veterans until the end of life. This qualitative study explored the experiences of care coordination for Medical Foster Home Veterans at the end of life with eight Veterans’ family members, five Medical Foster Home caregivers, and seven Veterans Health Administration Home-Based Primary Care team members. A case study, qualitative content analysis identified these themes addressing care coordination and impact of the Medical Foster Home model on those involved: (a) Medical Foster Home program supports Veterans’ families; (b) Medical Foster Home program supports the caregiver as family; (c) Veterans’ needs are met socially and culturally at the end of life; and (d) the changing needs of Veterans, families, and caregivers at Veterans’ end of life are addressed. Insights into how to best support Medical Foster Home caregivers caring for Veterans at the end of life were gained including the need for more and better respite options and how caregivers are compensated in the month of the Veteran’s death, as well as suggestions to navigate end-of-life care coordination with multiple stakeholders involved.     

Efficiency with Endogenous Population Growth

In this paper, we generalize the notion of Pareto efficiency to make it applicable to environments with endogenous populations. Two efficiency concepts are proposed: ℘‐efficiency and 𝒜‐efficiency. The two concepts differ in how they treat potential agents that are not born. We show that these concepts are closely related to the notion of Pareto efficiency when fertility is exogenous. We prove a version of the first welfare theorem for Barro–Becker type fertility choice models and discuss how this result can be generalized. Finally, we study examples of equilibrium settings in which fertility decisions are not efficient, and we classify them into settings where inefficiencies arise inside the family and settings where they arise across families.     

Hurricane Destructive Power Predictions Based on Historical Storm and Sea Surface Temperature Data

Forecasting destructive hurricane potential is complicated by substantial, unexplained intraannual variation in storm-specific power dissipation index (PDI, or integrated third power of wind speed), and interannual variation in annual accumulated PDI (APDI). A growing controversy concerns the recent hypothesis that the clearly positive trend in North Atlantic Ocean (NAO) sea surface temperature (SST) since 1970 explains increased hurricane intensities over this period, and so implies ominous PDI and APDI growth as global warming continues. To test this "SST hypothesis" and examine its quantitative implications, a combination of statistical and probabilistic methods were applied to National Hurricane Center HURDAT best-track data on NAO hurricanes during 1880-2002, and corresponding National Oceanographic and Atmospheric Administration Extended Reconstruction SST estimates. Notably, hurricane behavior was compared to corresponding hurricane-specific (i.e., spatiotemporally linked) SST; previous similar comparisons considered only SST averaged over large NAO regions. Contrary to the SST hypothesis, SST was found to vary in a monthly pattern inconsistent with that of corresponding PDI, and to be at best weakly associated with PDI or APDI despite strong correlation with corresponding mean latitude (R(2)= 0.55) or with combined mean location and a approximately 90-year periodic trend (R(2)= 0.70). Over the last century, the lower 75% of APDIs appear randomly sampled from a nearly uniform distribution, and the upper 25% of APDIs from a nearly lognormal distribution. From the latter distribution, a baseline (SST-independent) stochastic model was derived predicting that over the next half century, APDI will not likely exceed its maximum value over the last half century by more than a factor of 1.5. This factor increased to 2 using a baseline model modified to assume SST-dependence conditioned on an upper bound of the increasing NAO SST trend observed since 1970. An additional model was developed that predicts PDI statistics conditional on APDI. These PDI and APDI models can be used to estimate upper bounds on indices of hurricane power likely to be realized over the next century, under divergent assumptions regarding SST influence.     

SMALL‐AREA ESTIMATION OF POVERTY: THE AID INDUSTRY STANDARD AND ITS ALTERNATIVES

Small‐area estimation of poverty‐related variables is an increasingly important analytical tool in targeting the delivery of food and other aid in developing countries. We compare two methods for the estimation of small‐area means and proportions, namely empirical Bayes and composite estimation, with what has become the international standard method of Elbers, Lanjouw & Lanjouw (2003) . In addition to differences among the sets of estimates and associated estimated standard errors, we discuss data requirements, design and model selection issues and computational complexity. The Elbers, Lanjouw and Lanjouw (ELL) method is found to produce broadly similar estimates but to have much smaller estimated standard errors than the other methods. The question of whether these standard error estimates are downwardly biased is discussed. Although the question cannot yet be answered in full, as a precautionary measure it is strongly recommended that the ELL model be modified to include a small‐area‐level error component in addition to the cluster‐level and household‐level errors it currently contains. This recommendation is particularly important because the allocation of billions of dollars of aid funding is being determined and monitored via ELL. Under current aid distribution mechanisms, any downward bias in estimates of standard error may lead to allocations that are suboptimal because distinctions are made between estimated poverty levels at the small‐area level that are not significantly different statistically.