Data-driven Kriging models based on FANOVA-decomposition

Kriging models have been widely used in computer experiments for the analysis of time-consuming computer codes. Based on kernels, they are flexible and can be tuned to many situations. In this paper, we construct kernels that reproduce the computer code complexity by mimicking its interaction structure. While the standard tensor-product kernel implicitly assumes that all interactions are active, the new kernels are suited for a general interaction structure, and will take advantage of the absence of interaction between some inputs. The methodology is twofold. First, the interaction structure is estimated from the data, using a first initial standard Kriging model, and represented by a so-called FANOVA graph. New FANOVA-based sensitivity indices are introduced to detect active interactions. Then this graph is used to derive the form of the kernel, and the corresponding Kriging model is estimated by maximum likelihood. The performance of the overall procedure is illustrated by several 3-dimensional and 6-dimensional simulated and real examples. A substantial improvement is observed when the computer code has a relatively high level of complexity.     

Dublin’s Seventeenth Century Parishes and the Quality of Life

Social Indicators Research - The registers of Dublin’s parishes in the seventeenth century provide access to aspects of civic and religious life. In the registers are records of burials,...     

ARE WORKERS WILLING TO PAY TO JOIN A BETTER TEAM?

Using data from the Major League Baseball free‐agent market, this study is the first to show that the productivity expected of the team a worker will join produces a significant, negative compensating wage differential. The younger workers in the sample drive this result, trading 25% of their wages to join teams with an expected productivity one standard deviation higher. This investment can be recouped if a reasonable increase in human capital occurs. These results are robust to contract length‐wage simultaneity and indicate that investment in human capital motivates the observed tradeoff, suggesting a new pathway through which human capital accumulation can affect wages. Reliable measures of workers' own past productivity and the productivity expected of a worker's future team provide key advantages to identifying these effects. (JEL J31, J24, M54)     

Demographic change and shifting views about marine resources and the coastal environment in Downeast Maine

Connections to the sea often define the character of coastal towns. However, as migrants arrive and economic diversification occurs, views about the use of marine resources and the ocean environment can change. Using survey data from Maine, we examined whether shifting demographics affect public perceptions of marine resource uses and coastal environmental concerns. We tested resource use and environmental items against a common set of demographic, background, and place-related variables. Results indicate that the level of education and the county of residence predict Mainers?? views about different marine resource uses and ocean-related environmental issues. Political party affiliation strongly influences environmental concern but not views about the use of marine resources. Migration history, on the other hand, has little effect. Understanding community contexts as well as individual background and ideological orientations will be critical as managers attempt to balance alternative uses of marine resources and resolve coastal environmental problems.     

Bayesian adaptive dose‐escalation designs for simultaneously estimating the optimal and maximum safe dose based on safety and efficacy

The main purpose of dose‐escalation trials is to identify the dose(s) that is/are safe and efficacious for further investigations in later studies. In this paper, we introduce dose‐escalation designs that incorporate both the dose‐limiting events and dose‐limiting toxicities (DLTs) and indicative responses of efficacy into the procedure. A flexible nonparametric model is used for modelling the continuous efficacy responses while a logistic model is used for the binary DLTs. Escalation decisions are based on the combination of the probabilities of DLTs and expected efficacy through a gain function. On the basis of this setup, we then introduce 2 types of Bayesian adaptive dose‐escalation strategies. The first type of procedures, called “single objective,” aims to identify and recommend a single dose, either the maximum tolerated dose, the highest dose that is considered as safe, or the optimal dose, a safe dose that gives optimum benefit risk. The second type, called “dual objective,” aims to jointly estimate both the maximum tolerated dose and the optimal dose accurately. The recommended doses obtained under these dose‐escalation procedures provide information about the safety and efficacy profile of the novel drug to facilitate later studies. We evaluate different strategies via simulations based on an example constructed from a real trial on patients with type 2 diabetes, and the use of stopping rules is assessed. We find that the nonparametric model estimates the efficacy responses well for different underlying true shapes. The dual‐objective designs give better results in terms of identifying the 2 real target doses compared to the single‐objective designs.     

The Role of Sexual Communication in Couples’ Sexual Outcomes: A Dyadic Path Analysis

In a study of 142 couples, we gathered survey data to show how sexual communication influences sexual and relationship satisfaction as well as sexual and orgasm frequency. In two dyadic data path analyses, we observed the significant paths of influence that sexual communication has on sexual and relationship satisfaction, as well as sexual and orgasm frequency. Our findings revealed greater amounts of sexual communication were associated with increased orgasm frequency in women and greater relationship and sexual satisfaction in both sexes. We also observed important differences in the associations of sexual communication and general communication on satisfaction levels. With these analyses, we expand the current literature to broaden our understanding of the role that sexual communication plays in committed relationships.     

The next forty years in public health

In this article an attempt is made to assess the major health problems of the second half of the twentieth century in developed countries, the methods appropriate to these problems, and the pattern of medical services necessary to deal with them. From an examination of mortality and morbidity trends it is suggested that the most important problems are likely to be the mortality, malformation and disability established before birth, mental illness, and the disease and disability associated with ageing. Reasons are given for doubting whether control of breeding, the method which has contributed greatly to the improvement of plants and other animals, can be expected to be effective in the case of man, and hence reliance must continue to be placed on modifications of the environment to which achievement hitherto has been entirely due. The methods likely to be significant are: an extension of measures already in use for control ofthe physical environment; discovery and application of knowledge concerning the social environment; and elaboration of more effective methods of preventing and treating disease in the individual. Profound changes will be needed in the pattern of services through which medical knowledge is applied, the most important being unification ofthe major classes ofhospitals - acute, mental and chronic; association ofthe preventive personal health services with curative services (rather than with environmental services); and the strengthening of domiciliary medical care, particularly through a new and more intimate relationship between general practitioner and hospital services.