Sektion Jugendsoziologie Tätigkeitsbericht 2004

Ohne Zusammenfassung     

Interpersonal dependency of preferences

Standard decision theoretic models disregard the phenomenon of interpersonal dependency of preferences. In this paper it is argued that interpersonal dependency of preferences is a serious challenge for standard utility theory. First we sketch the more philosophical aspects of the problem and then, using a simple, formal model for the two-person case, we show that interpersonal dependency of preferences generally results in indeterminacy of preferences (resp. of subjective utility).     

Editorial

Ohne Zusammenfassung     

Social Sources of Failure in Education: The Case in East and Southeast Turkey

The efficiency of education in East and Southeast Turkey (E&SE) has long been a subject of debate. Both regions are similar to each other and different from the other regions in terms of economy, culture, ethnic origin, and languages spoken. Sahin (1997) studied the efficiency of education in the E&SE and proposed that illiteracy is significantly the highest in both regions, the female student population is significantly lower, and students are significantly less successful in nationwide general proficiency examinations (OSS and OYS) compared to all the other regions. Social sources of failure were studied in terms of the distinguishing characteristics of both regions, from both practical and theoretical standpoints. The findings indicated inequality of educational opportunity rooted in geographical, economical, social (cultural, linguistic), and political factors.     

Beneficial safety decreases

We construct a model of rational choice under risk with biased risk judgement. On its basis, we argue that sometimes, a regulator aiming at maximising social welfare should affect the environment in such a way that it becomes ‘less safe’ in common perception. More specifically, we introduce a bias into each agent’s choice of optimal risk levels: consequently, in certain environments, agents choose a behaviour that realises higher risks than intended. Individuals incur a welfare loss through this bias. We show that by deteriorating the environment, the regulator can motivate individuals to choose behaviour that is less biased, and hence realises risk levels closer to what individuals intended. We formally investigate the conditions under which such a Beneficial Safety Decrease—i.e. a deteriorating intervention that has a positive welfare effect—exists. Finally, we discuss three applications of our model.     

On predictive distributions and Bayesian networks

In this paper we are interested in discrete prediction problems for a decision-theoretic setting, where the task is to compute the predictive distribution for a finite set of possible alternatives. This question is first addressed in a general Bayesian framework, where we consider a set of probability distributions defined by some parametric model class. Given a prior distribution on the model parameters and a set of sample data, one possible approach for determining a predictive distribution is to fix the parameters to the instantiation with the maximum a posteriori probability. A more accurate predictive distribution can be obtained by computing the evidence (marginal likelihood), i.e., the integral over all the individual parameter instantiations. As an alternative to these two approaches, we demonstrate how to use Rissanen's new definition of stochastic complexity for determining predictive distributions, and show how the evidence predictive distribution with Jeffrey's prior approaches the new stochastic complexity predictive distribution in the limit with increasing amount of sample data. To compare the alternative approaches in practice, each of the predictive distributions discussed is instantiated in the Bayesian network model family case. In particular, to determine Jeffrey's prior for this model family, we show how to compute the (expected) Fisher information matrix for a fixed but arbitrary Bayesian network structure. In the empirical part of the paper the predictive distributions are compared by using the simple tree-structured Naive Bayes model, which is used in the experiments for computational reasons. The experimentation with several public domain classification datasets suggest that the evidence approach produces the most accurate predictions in the log-score sense. The evidence-based methods are also quite robust in the sense that they predict surprisingly well even when only a small fraction of the full training set is used.     

A tutorial on rank-based coefficient estimation for censored data in small- and large-scale problems

The analysis of survival endpoints subject to right-censoring is an important research area in statistics, particularly among econometricians and biostatisticians. The two most popular semiparametric models are the proportional hazards model and the accelerated failure time (AFT) model. Rank-based estimation in the AFT model is computationally challenging due to optimization of a non-smooth loss function. Previous work has shown that rank-based estimators may be written as solutions to linear programming (LP) problems. However, the size of the LP problem is O(n ²+p) subject to n ² linear constraints, where n denotes sample size and p denotes the dimension of parameters. As n and/or p increases, the feasibility of such solution in practice becomes questionable. Among data mining and statistical learning enthusiasts, there is interest in extending ordinary regression coefficient estimators for low-dimensions into high-dimensional data mining tools through regularization. Applying this recipe to rank-based coefficient estimators leads to formidable optimization problems which may be avoided through smooth approximations to non-smooth functions. We review smooth approximations and quasi-Newton methods for rank-based estimation in AFT models. The computational cost of our method is substantially smaller than the corresponding LP problem and can be applied to small- or large-scale problems similarly. The algorithm described here allows one to couple rank-based estimation for censored data with virtually any regularization and is exemplified through four case studies.