Scaling limits for the transient phase of local Metropolis–Hastings algorithms

Summary.  The paper considers high dimensional Metropolis and Langevin algorithms in their initial transient phase. In stationarity, these algorithms are well understood and it is now well known how to scale their proposal distribution variances. For the random-walk Metropolis algorithm, convergence during the transient phase is extremely regular—to the extent that the algo-rithm's sample path actually resembles a deterministic trajectory. In contrast, the Langevin algorithm with variance scaled to be optimal for stationarity performs rather erratically. We give weak convergence results which explain both of these types of behaviour and practical guidance on implementation based on our theory.     

Mapping the regional transition to cyclicity inClethrionomys rufocanus: Spectral densities and functional data analysis

We study the regional transitions in dynamics of the gray-sided vole,Clethrionomys rufocanus, within Hokkaido, Japan. The data-set consists of 225 time series of varying length (most from 23 to 31 years long) collected between 1962 and 1992 by the Forestry Agency of the Japanese Government. To see clearly how the periodic behavior changes geographically, we estimate the spectral density functions of the growth rates of all populations using a log-spline method. We subsequently apply functional data analysis to the estimated densities. The functional data analysis is, in this context, analogous to a principal component analysis applied to curves. We plot the results of the analysis on the map of Hokkaido, to reveal a clear transition from relatively stable populations in the southwest and west to populations undergoing 3–4 year cycles in the northeast and east. The degree of seasonality in the vegetation and the rodent demography appear to be strongest in the cyclic area. We briefly speculate that the destabilization of the rodent dynamics is linked to increased seasonalforcing on the trophic interactions in which the gray-sided voles are involved.     

Partial least squares Cox regression for genome-wide data

Most methods for survival prediction from high-dimensional genomic data combine the Cox proportional hazards model with some technique of dimension reduction, such as partial least squares regression (PLS). Applying PLS to the Cox model is not entirely straightforward, and multiple approaches have been proposed. The method of Park et al. (Bioinformatics 18(Suppl. 1):S120–S127, 2002) uses a reformulation of the Cox likelihood to a Poisson type likelihood, thereby enabling estimation by iteratively reweighted partial least squares for generalized linear models. We propose a modification of the method of park et al. (2002) such that estimates of the baseline hazard and the gene effects are obtained in separate steps. The resulting method has several advantages over the method of park et al. (2002) and other existing Cox PLS approaches, as it allows for estimation of survival probabilities for new patients, enables a less memory-demanding estimation procedure, and allows for incorporation of lower-dimensional non-genomic variables like disease grade and tumor thickness. We also propose to combine our Cox PLS method with an initial gene selection step in which genes are ordered by their Cox score and only the highest-ranking k% of the genes are retained, obtaining a so-called supervised partial least squares regression method. In simulations, both the unsupervised and the supervised version outperform other Cox PLS methods.     

Organizational factors and child participation in decision‐making: differences between two child welfare organizations

Children in residential care tend to be less content with the quality of care arrangements and participation opportunities compared to children in foster care. This study explored possible differences in social workers' views about child participation and service quality. Hierarchical regression analyses were used to test if any differences may be explained by collaboration between professionals' and social workers' work engagement. We found that social workers from residential care services seem more prudent in letting children participate in case planning compared to social workers planning for foster care. Social workers' judgements of service quality were also highly affected by their organizational affiliation, but personal factors such as work engagement may also play a part. The differences we found regarding social workers' attitudes towards participation and their rating of service quality are associated with organizational culture. Understanding how organizations shape social workers' decisions to include or exclude children in care planning may help gain a more comprehensive understanding of what is needed to take the participation agenda forward.     

Designing Realized Kernels to Measure the ex post Variation of Equity Prices in the Presence of Noise

This paper shows how to use realized kernels to carry out efficient feasible inference on the ex post variation of underlying equity prices in the presence of simple models of market frictions. The weights can be chosen to achieve the best possible rate of convergence and to have an asymptotic variance which equals that of the maximum likelihood estimator in the parametric version of this problem. Realized kernels can also be selected to (i) be analyzed using endogenously spaced data such as that in data bases on transactions, (ii) allow for market frictions which are endogenous, and (iii) allow for temporally dependent noise. The finite sample performance of our estimators is studied using simulation, while empirical work illustrates their use in practice.     

Reaching universal coverage by means of social health insurance in Lesotho? Results and implications from a financial feasibility assessment

This article discusses the process, results and implications of a financial feasibility assessment of social health insurance (SHI), as one part of Lesotho's exploration of how to move towards achieving universal health care coverage. Quantitative data from government and other sources, and qualitative data from discussions with stakeholders, were entered into SimIns, a health insurance simulation software, through which SHI revenue and expenditure for 11 years was projected. In principle, the assessment reveals that through a mix of tax financing and SHI contributions, all citizens of Lesotho could be covered with a defined benefit package of health services under the defined policy assumptions. Such a financing scheme would provide financial risk protection and enhance equity in access and health financing.     

Participation and health – a research review of child participation in planning and decision‐making

Effective child participation in child protection proceedings has proved difficult to achieve in Norway. Although participation is in principle accepted as a human right and something of benefit to children, when children's health is at stake there is a tendency to view participation in decision‐making processes by children as potentially disruptive to their well‐being. The purpose of this study is to review the research evidence for effects, positive or negative, of participation on health outcomes for children in care. A scoping review of major health and social work research databases was undertaken. Searches in five databases yielded 1830 studies of which 21 were finally included in this review. Studies were included if a relationship between health and participation was evident from the data presented, even if this was not the main objective in the study at hand. We conclude that when participation is successful, it may have beneficial side effects. Chief among these are that participation may improve children's safety, increase the success of care arrangements and increase feelings of well‐being for children involved. Evidence for long‐term effects of successful or failed participation attempts on subsequent health outcomes is however largely absent.