Cohort size and age-specific suicide rates: A contingent relationship

Trends in age-specific suicide rates relate to debates about the consequences of population aging and changes in cohort size for social well-being. Easterlin argues that large cohort size increases suicide rates by reducing relative income; Preston claims that suicide rates fall in large cohorts with high levels of political and social power. To integrate these competing arguments, this paper uses aggregate data on 18 high-income nations from 1953 to 1986 to demonstrate that the direction and strength of the relationship between cohort size and suicide depend on (1) age of the cohort, (2) gender, (3) national context, and (4) time period. The results show that large cohort size raises suicide for the young and middle-aged, but reduces it for the elderly. Also, the effects of cohort size prove stronger for men than for women, for nations with less collectivist institutions than for nations with more collectivist institutions, and for the 1950s and 1960s than for the 1970s and 1980s.     

Family reunification in a social structural context

Using a multi-level discrete time hazard model, this study examines whether county level social structural characteristics affect the rate of family reunification, after adjusting for child attributes. Children who were placed in foster care for the first time during 2004 from 945 counties in 17 states are included. The county level characteristic examined included urbanicity, racial composition, percentage of female-headed households, proportion of households in poverty and foster care placement rate. The results show that with the exception of poverty, the other contextual variables affect family reunification, although the effects are most pronounced within the first six months of foster care placement.     

CONVERGENCE AND PREDICTION OF PRINCIPAL COMPONENT SCORES IN HIGH-DIMENSIONAL SETTINGS

A number of settings arise in which it is of interest to predict Principal Component (PC) scores for new observations using data from an initial sample. In this paper, we demonstrate that naive approaches to PC score prediction can be substantially biased towards 0 in the analysis of large matrices. This phenomenon is largely related to known inconsistency results for sample eigenvalues and eigenvectors as both dimensions of the matrix increase. For the spiked eigenvalue model for random matrices, we expand the generality of these results, and propose bias-adjusted PC score prediction. In addition, we compute the asymptotic correlation coefficient between PC scores from sample and population eigenvectors. Simulation and real data examples from the genetics literature show the improved bias and numerical properties of our estimators.     

Analysis and modelling of wind speed in New York

In this paper we propose an ARMA time-series model for the wind speed at a single spatial location, and estimate it on in-sample data recorded in three different wind farm regions in New York state. The data have a three-hour granularity, but based on applications to financial wind derivatives contracts, we also consider daily average wind speeds. We demonstrate that there are large discrepancies in the behaviour of daily average and three-hourly wind speed records. The validation procedure based on out-of-sample observations reflects that the proposed model is reliable and can be used for various practical applications, like, for instance, weather prediction, pricing of financial wind contracts, wind generated power, etc. Furthermore, we discuss some striking resemblances with temperature dynamics.     

Drug resistance in an age-of-infection model

ABSTRACT

In the case of a disease spreading over a time-scale comparable to the average lifetime in a host population, when the infectiousness of individuals depends on the tine since the onset of infection and when infections involve both drug-sensitive and drug-resistant strains of a pathogen, resistance may develop during the treatment of drug-sensitive strains. If increasing the treatment rate reduces the reproduction number of the drug-sensitive strain to a value below the reproduction number of the drug-resistant strain, then the disease may persist at a boundary equilibrium where only drug-resistant infection is present.     

The Dutch people and the euro: A structural equations analysis relating national identity and economic expectations to attitude towards the euro

National identity, macro and micro economic expectations affect the attitude toward the euro. In a study in The Netherlands, data were collected and relationships between the latent concepts were modelled with LISREL. In the best fitting model, national identity has a direct and an indirect effect on attitude, respectively, an unstructured and a structured effect. The indirect effect is mediated by macro and micro expectations. Macro expectations also have a direct and an indirect effect. The indirect effect is mediated by micro expectations. On one hand, macro expectations form a strong link between national identity and attitude. On the other hand, macro expectations have a strong direct effect on attitudes. The euro is mainly perceived and evaluated in a macro-economic perspective.PsycINFO classification: 2229; 3920     

Of Piddley Results and Unanticipated Consequences: Comments on Fein

Fein's discussion of race relations is anchored in two basic objections to planned social change. First, such attempts involve problematic ethical and values choices. Second, the very nature of society confounds our best efforts at reform. While this paper offers no solutions to the ethical dilemmas, it does contend that guided social change is not as fruitless or dangerous as Fein implies.