Bayesian model selection for exponential random graph models

Exponential random graph models are a class of widely used exponential family models for social networks. The topological structure of an observed network is modelled by the relative prevalence of a set of local sub-graph configurations termed network statistics. One of the key tasks in the application of these models is which network statistics to include in the model. This can be thought of as statistical model selection problem. This is a very challenging problem—the posterior distribution for each model is often termed “doubly intractable” since computation of the likelihood is rarely available, but also, the evidence of the posterior is, as usual, intractable. The contribution of this paper is the development of a fully Bayesian model selection method based on a reversible jump Markov chain Monte Carlo algorithm extension of Caimo and Friel (2011) which estimates the posterior probability for each competing model.     

Assent-maximizing social choice

We take a decision theoretic approach to the classic social choice problem, using data on the frequency of choice problems to compute social choice functions. We define a family of social choice rules that depend on the population’s preferences and on the probability distribution over the sets of feasible alternatives that the society will face. Our methods generalize the well-known Kemeny Rule. In the Kemeny Rule, it is known a priori that the subset of feasible alternatives will be a pair. We define a distinct social choice function for each distribution over the feasible subsets. Our rules can be interpreted as distance minimization—selecting the order closest to the population’s preferences, using a metric on the orders that reflects the distribution over the possible feasible sets. The distance is the probability that two orders will disagree about the optimal choice from a randomly selected available set. We provide an algorithmic method to compute these metrics in the case where the probability of a given feasible set is a function only of its cardinality.     

The Path to Asylum in the US and the Determinants for Who Gets In and Why*

The migration of political asylum seekers into the United States has long been a salient political topic; however, social scientists have yet to examine this process in its entirety and in the context of political changes since September 11, 2001. Previous research shows that humanitarian and strategic interests are important for decisions made by asylum officers but that research overlooks the decisions made by immigration judges. Here we examine decisions made by both asylum officers and immigration judges using data from a global set of countries, from 1999 to 2004. We find that the waning importance of human rights is more pronounced for asylum officers than for immigration judges after the attack on the World Trade Center. We also find that language heritage, specifically for asylum seekers from English‐, Spanish‐, and Arabic‐speaking countries, substantially affects acceptance rates made by both decision‐makers between the two time periods of our study.     

Existence of efficient envy-free allocations of a heterogeneous divisible commodity with nonadditive utilities

This paper studies the existence of Pareto optimal, envy-free allocations of a heterogeneous, divisible commodity for a finite number of individuals. We model the commodity as a measurable space and make no convexity assumptions on the preferences of individuals. We show that if the utility function of each individual is uniformly continuous and strictly monotonic with respect to set inclusion, and if the partition matrix range of the utility functions is closed, a Pareto optimal envy-free partition exists. This result follows from the existence of Pareto optimal envy-free allocations in an extended version of the original allocation problem.     

Identification of domain restrictions over which acyclic, continuous-valued, and positive responsive social choice rules operate

We consider a social choice problem in various economic environments consisting of n individuals, 4≤n<+∞, each of which is supposed to have classical preferences. A social choice rule is a function associating with each profile of individual preferences a social preference that is assumed to be complete, continuous and acyclic over the alternatives set. The class of social choice rules we deal with is supposed to satisfy the two conditions; binary independence and positive responsiveness. A new domain restriction for the social choice rules is proposed and called the classical domain that is weaker than the free triple domain and holds for almost all economic environments such as economies with private and/or public goods. In this paper we explore what type of classical domain that admits at least one social choice rule satisfying the mentioned conditions to well operate over the domain. The results we obtained are very negative: For any classical domain admitting at least one social choice rule to well operate, the domain consists only of just one profile.     

A general concept of scoring rules: general definitions,statistical inference,and empirical illustrations

We develop the general conceptual, mathematical and statistical foundations of behavioral social choice for scoring rules. Traditional scoring rules are difficult to assess empirically because one rarely observes the deterministic complete linear orders that they require as input. We provide a general concept of scoring rules in terms of a broad range of mathematical representations of preference or utility, namely arbitrary finite binary relations, probability distributions over such relations, real valued multi-criteria utility vectors and real valued random utility representations. We extend Regenwetter et al.’s (Behavioral social choice. Cambridge University Press, Cambridge, 2006) statistical framework to a more general setting. We illustrate the general modeling and statistical tools by applying them to four well known sets of survey data. We illustrate two potential problems that have previously received little attention and that deserve systematic study in the future: (1) Scoring rule outcomes can suffer from model dependence in that the social welfare functions computed from ballot, survey, or hypothetical data may depend on implicit or explicit modeling assumptions. (2) Scoring rule outcomes may suffer from low statistical confidence in that the correct assessment of social orders from empirical data can be far from certain. We also illustrate the empirical congruence among conceptually competing social choice methods.     

Efficient Bayesian inference for exponential random graph models by correcting the pseudo-posterior distribution

Exponential random graph models are an important tool in the statistical analysis of data. However, Bayesian parameter estimation for these models is extremely challenging, since evaluation of the posterior distribution typically involves the calculation of an intractable normalizing constant. This barrier motivates the consideration of tractable approximations to the likelihood function, such as the pseudolikelihood function, which offers an approach to constructing such an approximation. Naive implementation of what we term a pseudo-posterior resulting from replacing the likelihood function in the posterior distribution by the pseudolikelihood is likely to give misleading inferences. We provide practical guidelines to correct a sample from such a pseudo-posterior distribution so that it is approximately distributed from the target posterior distribution and discuss the computational and statistical efficiency that result from this approach. We illustrate our methodology through the analysis of real-world graphs. Comparisons against the approximate exchange algorithm of Caimo and Friel (2011) are provided, followed by concluding remarks.     

The equivalence of the cost share equilibria and the core of a voting game in a public goods economy

We consider a social situation where individuals choose one or some alternative(s) from a set of feasible alternatives. When one alternative is socially chosen, each individual must share the cost for it according to an exogenously given sharing rule. Individuals are allowed to collude among themselves through money transfers. As the mechanism of choosing a social alternative, we consider the cost share equilibrium and a voting game. The cost share equilibrium is an allocation where each individual maximizes his/her utility independently and where unanimity is still maintained. We will show the equivalence between the set of all equilibrium allocations and the core of the voting game with compensation.I would like to thank Professors Mamoru Kaneko, Kotaro Suzumura, William Thomson, Mikio Nakayama, Hiroo Sasaki, Mr. Ken-ichi Shimomura and anonymous referees for their many useful suggestions and comments. I also acknowledge grammatical suggestions of Mr. Ronald M. Siani.     

Flexibility of choice versus reduction of ambiguity

This paper explores the problem of a social planner willing to improve the welfare of individuals who are unable to compare all available alternatives. The optimal decision trades off the individuals’ desire for flexibility versus their aversion towards ambiguous choice situations. We introduce an axiom system that formalizes this idea. Our main result characterizes the preference maximizing opportunity set. It is a maximal set that consists of mutually comparable alternatives. It also has the property that it maximizes the sum of the distances between its ordered elements for some appropriate pseudometric imposed on the set of possible choices.     

Lived Realities and the Construction of Social Problems: The Case of Wife Abuse

This article examines the official and subjective realities of one social problem, wife abuse, and it considers consequences of differences between these two types of reality. First, claims appearing in the professional literature are used to define the specific content of the official social problem. Then, characteristics of violence as experienced are compared with this official definition. Finally, data from a shelter for battered women are used to illustrate consequences of official definitions in organizations designed to ameliorate the individual troubles associated with social problems. The study demonstrates how the official definition of wife abuse acts and actors has reduced the recognizability of the phenomenon in lived experience and also set the stage for reality-definition contests in social services for abused wives. This illustrates the importance of examining sociologically the specific content of social problems claims and the necessity of attending to social problems in their full phenomenological realities.     

Absenteeism and the control of work*

The ‘individual’ forms of industrial conflict, such as absenteeism, have received little attention in industrial sociology. This paper attempts to correct this deficiency by attacking the conventional approach to these phenomena and by using recent research findings to develop a sociological alternative. The main characteristics of the conventional approach are the focus on absenteeism without reference to the patterns of work relations of which it is part, and a treatment of it as a ‘problem’ which requires a remedy. The weakness of the approach is that neither the social meaning of absence nor the structural context of work organization is investigated. The alternative approach examines absence as part of a set of workplace relations and is thus able to explore how far, in what ways, and with what consequences it represents a form of conflict. In combination with other recent studies of the links between absence and the contingencies of individual workers' situations, a more adequate sociological treatment is possible. This approach is, ironically, better able to grasp the managerial problem of absence and workplace control than is the ‘managerialist’ conventional approach.     

The impact of husband’s job loss on partners’ mental health

The objective of this paper is to examine the impact of job loss on family mental well-being. The negative income shock can affect the mental health status of the individual who directly experiences such displacement, as well as the psychological well-being of his partner; also, job loss may have a significantly detrimental effect on life satisfaction, self-esteem and on the individual’s perceived role in society. This analysis is based on a sample of married and cohabitating couples from the first 14 waves of the British Household Panel Survey. In order to correct for the possible endogeneity of job loss, data from employment histories is utilised and redundancies (different from dismissals) in declining industries are used as an indicator of exogenous job loss. Results show evidence that couples in which the husband experiences a job loss are more likely to experience poor mental health.     

Social Capital and Human Mortality: Explaining the Rural Paradox with County‐Level Mortality Data

The “rural paradox” refers to standardized mortality rates in rural areas that are unexpectedly low in view of well‐known economic and infrastructural disadvantages there. We explore this paradox by incorporating social capital, a promising explanatory factor that has seldom been incorporated into residential mortality research. We do so while being attentive to spatial dependence, a statistical problem often ignored in mortality research. Analyzing data for counties in the contiguous United States, we find that: (1) the rural paradox is confirmed with both metro‐nonmetro and rural‐urban continuum codes, (2) social capital significantly reduces the impacts of residence on mortality after controlling for race and ethnicity and socioeconomic covariates, (3) this attenuation is greater when a spatial perspective is imposed on the analysis, (4) social capital is negatively associated with mortality at the county level, and (5) spatial dependence is strongly in evidence. A spatial approach is necessary in county‐level analyses such as ours to yield unbiased estimates and optimal model fit.     

Personality and the enactment of emotion

The meaning of personality traits for social interaction was investigated by exploring the personality correlates of abilities to pose emotions. This framework focuses on individual differences in socio-emotional skills. Thirty one males and 37 females were videotaped while attempting to communicate seven basic emotions nonverbally (i.e., using standard content communications), and sending success was measured by showing edited videotapes to judges. Hypothesized relationships between acting ability and scores on the Jackson Personality Research Form and the Eysenck Personality Inventory were then examined. The findings were seen to have implications for predicting individual strengths and weaknesses in social interaction as a function of certain personality traits and for understanding person perception.This research was supported in part by NIMH Grant #RO3MH31453 and Intramural Research Grants from UC Riverside to Howard Friedman, and indirectly by the Biomedical Research Support Program of NIH (#RR077010-11). We would like to thank Louise M. Prince for her assistance.     

Using latent class analysis to detect behavioral patterns in systems of observational variables

Behavioral observation is widely used for data gathering in evaluation research. Yet it leaves the investigator with unique problems. Usually, multiple observations result in a hierarchical data set, where numerous data records exist for each subject. Researchers face data reduction problems at least at two levels. First, there is the well-known and often-addressed problem of reducing the number of variables in a data set with only one information record per individual. Second, there is the problem of summarizing data at the individual subject level. The easiest way to perform this latter type of aggregation involves using univariate summary measures as probabilities of “using” an item, means, or standard deviations for each item per subject. Other standard procedures include first order interactions between pairs of items. However, use of pair-wise interactions is restricted because of variable dependence within each subject (this Affects e.g. factor analysis), or because of the relatively high number of single observations (this Affects e.g., cluster analysis). In this paper we propose employing Latent Class Analysis (LCA) to reduce the amount of information in observational data sets. In a first step, LCA allows one to specify intraindividual behavior patterns. In a second step, LCA allows one to derive meaningful summary scores for each individual. The two steps are illustrated using data that describe peer play competence in Swedish toddlers.     

Arrow's paradox and mathematical theory of democracy

Two measures, the weight of coalitions and the probability of situations in decision making, are used to characterize the representativeness, i.e. the capability of individuals to represent the social preference. It is proved that there always exists an individual who represents a majority on average, and an individual who represents a majority in most cases. This result is applied to Arrow's social choice model. It follows that there always exists a dictator who is a representative of the society rather than a dictator in a proper sense. After the concept of dictator has been refined to a dictator in a proper sense, Arrow's axioms become consistent. The idea of optimal representation is extended to limited groups of representatives which make decisions on behalf of the whole society. We consider the cabinet (named by analogy with the cabinet of ministers) which consists of a few representatives with delimited domains of competence, and the council which makes decisions by means of voting. It is shown that the representativeness of optimal cabinets and councils tends to 100% of maximally possible values as the number of their members increases, independently of the size of the society. We suggest a geometric interpretation of optimal representatives, cabinets, and councils, based on approximation formulas for the indicators of representativeness derived for the model with a large number of independent individuals. Finally, for cabinets and councils we establish the consistency of different concepts of optimality with respect to different indicators of representativeness. Our consideration is applicable to multicriteria decision making. An appointment of a cabinet or a council corresponds to selecting a few partial criteria. Therefore, the obtained results can be used for reducing the set of partial criteria to a certain sufficient minimum. The concepts of dictator, cabinet, and council can be understood as models of president, government, and parliament, respectively. Thus our results justify reducing social choice to individual choice or small group choice. Although it is in use in all democratic systems, its acceptability is not evident at all. In other words, we justify the demoncraticity of such forms of political power as the president, the parliament, and the government.     

从“郭美美炫富”看多元社会思潮对90后青年的影响

对于郭美美炫富,国人除了谩骂并未进行理性反思,事实上,郭美美事件折射的是90后青年的价值观问题。由于国内多元社会思潮的兴起,使得90后青年在价值理想、价值取向、价值选择和价值尺度等方面发生扭曲。为帮助新一代年轻人面对社会思潮多元的环境,树立正确的价值观念,社会、学校和家庭应三管齐下,共同努力承担其正确价值观养成的责任。     

THE INFLUENCE OF CLASS POSITION ON THE FORMAL AND INFORMAL SANCTIONING OF WHITE-COLLAR OFFENDERS

Although researchers have investigated formal legal reactions to white-collar crime, few data exist on informal reactions to white-collar lawbreakers and how these reactions influence sentencing decisions. Even so, commentators often assert that whitecollar offenders receive lenient criminal penalties because judges sympathize with such offenders due to the losses they incur through informal sanctions. In this light, a causal model is used to explore the influence of class position on an important informal sanction—loss of job—and the influence of loss of job on sentence severity. Class position is found to determine the likelihood of loss of job but not that of incarceration. Further, offenders who commit large-scale offenses are less likely to suffer loss of job than those who commit small-scale crimes. Social reactions to white-collar crime are inconsistent, and class position more strongly influences informal, nongovernmental social control than social control through law.     

GAMES AND TRUTHS: Learning To Construct Social Problems In High School Debate

Although social constructionists have taken the process by which people learn to present social problems for granted, these skills are acquired in the course of socialization. Through high school debate, adolescents acquire techniques for making arguments, using evidence, and presenting claims to multiple audiences. In the process, they learn that taking a public position does not necessarily require a deeply held commitment. This model resonates with the institutional structure of politics and law in the United States in which adversaries battle each other in a rule-governed "game,'a contest ultimately evaluated by judges assumed to be impartial. To understand the process by which adolescents gain the skills to construct social problems, I conducted an ethnographic study of debate teams at two high schools. The ability to take both sides of an argument, express ideas with which one does not personally agree, and present powerful, if questionable, evidence, constrained by time, teaches teenagers how to engage in social problem discourse and provides a training ground for moral entrepreneurs.