Computing exact clustering posteriors with subset convolution

ABSTRACT

An exponential-time exact algorithm is provided for the task of clustering n items of data into k clusters. Instead of seeking one partition, posterior probabilities are computed for summary statistics: the number of clusters and pairwise co-occurrence. The method is based on subset convolution and yields the posterior distribution for the number of clusters in O(n3ⁿ) operations or O(n³2ⁿ) using fast subset convolution. Pairwise co-occurrence probabilities are then obtained in O(n³2ⁿ) operations. This is considerably faster than exhaustive enumeration of all partitions.     

FAMILY, COMMUNITY, AND LIFESTYLE: ADOLESCENT VICTIMIZATION IN HELSINKI

The proximate correlates of adolescent victimization are well documented in the literature. The purpose of our research is to examine the more fundamental sources of this outcome. Focusing on two basic social contexts—the family and the residential community—we develop a theoretical model and test it empirically against a multilevel data set on juveniles living in Helsinki. Consistent with our hypothesis, we find that the family context is an important determinant of violent victimization. Much of this effect is mediated by involvement in delinquent lifestyles. We also find support for the assumption that community context matters to the risk of victimization independently of the family context and individual-level risk factors. Our research underscores the need for a multilevel approach in explanations of violent victimization.     

Occurrence of breeding bird species in urban parks: Effects of park structure and broad-scale variables

Occurrences of breeding bird species in 54 urban parks were investigated in the city of Oulu in northern Finland. Park area, human activity, habitat, and landscape structure within a 9-ha square surrounding the study park were related to the bird species richness and occurrence of individual bird species. A total of 22 species was observed. The area of the park explained 39% of the variance of species richness. Seven species (wheatear [Oenanthe oenanthe], common rosefinch [Carpodacus erythrinus], garden warbler [Sylvia borin], lesser whitethroat [Sylvia curruca], linnet [Acanthis cannabina], redpoll [Carduelis flammea], and yellowhammer [Emberiza citrinella]) were not detected in parks of >0.75 ha. Species with lower area demands occurred closer to the town center than species with greater area requirements. Ground-nesting species were poor colonizers of urban parks, whereas high numbers of nest boxes in urban parks attracted many cavity-nesting species. The willow warbler (Phylloscopus trochilus) and the magpie (Pica pica) bred more often in unmanaged than in managed parks, probably because of the greater vegetation cover in unmanaged parks. Park structure variables were entered into models for 7 of the 12 most common bird species, whereas broad scale variables were entered into models for 6 of the 12 species. The number of adjacent buildings had a negative affect on three bird species (the willow warbler, hooded crow [Corvus corone cornix], and spotted flycatcher [Muscicapa striata]). The occurrence of breeding species in urban parks depends on the size of the park, park structure, and landscape structure outside the park.     

From Genius of the Home to Party Princess

The data for this article consist of alcohol-related advertisements published in seven Finnish women's magazines from 1967 to 2006. We are interested in finding out what kind of alcohol-related subject positions these magazines have created for women audiences from the 1960s onwards, to see how those positions have changed and what these changes tell us about the changes that have happened in the cultural position of drinking in Finland. Our analysis applies semiotic and discourse analytical methods. It shows that in the advertisements from the 1960s, women were placed in the subject position of full-time mother responsible for taking care of the heterosexual relationship. Women's drinking was associated with the private space of the home, with eating meals and socialising with family and friends. Women's subject positions in the 1970s and 1980s were still largely the same, but they also took on slightly new features. The 1990s and 2000s saw the emergence of the active woman who appears in public places, and drinking was associated with women's own time, enjoyment and pleasure. During the period under review we see the emergence of a drinking, self-assertive woman who is a responsible and distinctive consumer, a consumer who toys with stereotypes, and a partying consumer.     

Effects of Career Choice Intervention on Components of Career Preparation

This randomized experimental study (N = 1,034) examines both the direct and the indirect effects of the Towards Working Life intervention on 2 components of adolescents' career preparation: preparedness for career choice and attitude toward career planning. The intervention comprised a 1—week workshop program, the proximal goals of which were to enhance 9th graders' career choice preparedness and attitude toward career planning. Participants were assessed at baseline and immediately after the intervention. The results showed that the intervention had directly improved the students' career choice preparedness, which in turn increased positive attitude toward career planning. Implications for both theory and practice are discussed.     

Gambling-Related Harms Among Adolescents: A Population-Based Study

Internationally, and also in Europe, adolescent gambling is increasingly recognized as an important public health issue. Most research on adolescent gambling, however, is prevalence-focused and population-based studies are scarce. Few studies have examined gambling-related harms among adolescents. In a national sample, we examined self-experienced harms related to gambling and the relationship between reported harms and gambling behavior among Finnish adolescents. A national survey of 12–18-year-olds was conducted in Finland in 2011 (N = 4,566). Main measures were frequency of gambling and gambling-related harms reported during the past 6 months. The relationship between reported harms and gambling behavior was assessed using logistic regression analysis. Overall, 44% had gambled during the past 6 months. Of the sample, 12% were frequent gamblers (at least weekly) and 32% were occasional gamblers (monthly or less often). Compared to occasional gamblers, frequent gamblers were more likely to experience harms. The most commonly reported harms among frequent gamblers were “felt guilty or shameful due to gambling” (17%) followed by “problems with relationships” (13%) and “disruptions of daily rhythm” (10%). In age and gender-adjusted analysis, daily gamblers were significantly more likely to report all different types of harms when compared to other groups. These findings suggest that when planning and targeting youth gambling prevention and harm reduction strategies the nature and extent to which gambling may contribute to the different types of harms are important to consider.     

Subtypes of Problem Gamblers,Sociocultural Factors,and Availability of Gambling

Finnish treatment-seeking gamblers were examined in light of predominant problem gambler subtype models. “Psy science” oriented problem gambler subtypes were found to be considerably influenced by gambling cultures and treatment traditions in the countries from which the mainstream problem gambler research originates. Thus, models that emphasize the psychopathology of the individual might cause some friction when applied to countries like Finland with a quite particular gambling culture and addiction treatment system that traditionally functions on a social work basis. It is suggested that specialists helping problem gamblers should acquire local knowledge with which to complete psychiatrically oriented scientific knowledge.     

The Emergence and Stability of the Attentional Bias to Fearful Faces in Infancy

Several studies have shown that at 7 months of age, infants display an attentional bias toward fearful facial expressions. In this study, we analyzed visual attention and heart rate data from a cross‐sectional study with 5‐, 7‐, 9‐, and 11‐month‐old infants (Experiment 1) and visual attention from a longitudinal study with 5‐ and 7‐month‐old infants (Experiment 2) to examine the emergence and stability of the attentional bias to fearful facial expressions. In both experiments, the attentional bias to fearful faces appeared to emerge between 5 and 7 months of age: 5‐month‐olds did not show a difference in disengaging attention from fearful and nonfearful faces, whereas 7‐ and 9‐month‐old infants had a lower probability of disengaging attention from fearful than nonfearful faces. Across the age groups, heart rate (HR) data (Experiment 1) showed a more pronounced and longer‐lasting HR deceleration to fearful than nonfearful expressions. The results are discussed in relation to the development of the perception and experience of fear and the interaction between emotional and attentional processes.     

A Modular Bayesian Salmonella Source Attribution Model for Sparse Data

Several statistical models for salmonella source attribution have been presented in the literature. However, these models have often been found to be sensitive to the model parameterization, as well as the specifics of the data set used. The Bayesian salmonella source attribution model presented here was developed to be generally applicable with small and sparse annual data sets obtained over several years. The full Bayesian model was modularized into three parts (an exposure model, a subtype distribution model, and an epidemiological model) in order to separately estimate unknown parameters in each module. The proposed model takes advantage of the consumption and overall salmonella prevalence of the studied sources, as well as bacteria typing results from adjacent years. The latter were used for a smoothed estimation of the annual relative proportions of different salmonella subtypes in each of the sources. The source‐specific effects and the salmonella subtype‐specific effects were included in the epidemiological model to describe the differences between sources and between subtypes in their ability to infect humans. The estimation of these parameters was based on data from multiple years. Finally, the model combines the total evidence from different modules to proportion human salmonellosis cases according to their sources. The model was applied to allocate reported human salmonellosis cases from the years 2008 to 2015 to eight food sources.