On the correlation between fraud and default risk

Identity fraud is one of the fastest growing white-collar crimes today and a serious concern in our information-based economy. This paper studies one type of identity fraud: new account fraud, where an impostor opens lines of credit using a false identity, made-up or stolen. Relying on a unique data set of consumer bank accounts, that contains information on both, fraud and default losses, I analyze the correlation between fraud and default risk. I find that common socio-economic/demographic account holder characteristics have opposite effects on estimated default and fraud probabilities. For example, women possess a lower fraud probability, but a higher default probability, compared to men, and foreigners are more likely to engage in account fraud but less likely to default than Germans. Also, the portfolio level analysis indicates that portfolio loss distributions are quite sensitive to ex ante portfolio characteristics like the share of foreigners or blue-collar workers. These findings have important implications for banks managing their consumer credit portfolios using limiting rules based on borrower characteristics, and for the adequacy of banks’ capital levels.     

Estimation of Location Parameters Under Nonnormal Errors and Quadratic Loss

Assuming a statistical model in which the joint distribution of the unobservable errors is drawn from independent univariate Student t's that are identically and symmetrically distributed, the sampling performance of traditional robust estimators and a family of Stein-like estimators are compared and evaluated. These results suggest that under thick-tailed distributions, the relative sampling performances and risk characteristics for a range of nonconventional Stein estimators remains approximately the same as in the case of their normal counterparts. The empirical risk implications of misspecifying the error distribution are investigated.     

Children's Expression of Emotional Meaning in Music Through Expressive Body Movement

Recent research has demonstrated that preschool children can decode emotional meaning in expressive body movement; however, to date, no research has considered preschool children's ability to encode emotional meaning in this media. The current study investigated 4- (N = 23) and 5- (N = 24) year-old children's ability to encode the emotional meaning of an accompanying music segment by moving a teddy bear using previously modeled expressive movements to indicate one of four target emotions (happiness, sadness, anger, or fear). Adult judges visually categorized the silent videotaped expressive movement performances by children of both ages with greater than chance level accuracy. In addition, accuracy in categorizing the emotion being expressed varied as a function of age of child and emotion. A subsequent cue analysis revealed that children as young as 4 years old were systematically varying their expressive movements with respect to force, rotation, shifts in movement pattern, tempo, and upward movement in the process of emotional communication. The theoretical significance of such encoding ability is discussed with respect to children's nonverbal skills and the communication of emotion.     

Age structure effects and growth in the OECD, 1950–1990

Economic growth depends on human resources and human needs. The demographic age structure shapes both of these factors. We study five-year data from the OECD countries 1950–1990 in the framework of an age structure augmented neoclassical growth model with gradual technical adjustment. The model performs well in both pooled and panel estimations. The growth patterns of GDP per worker (labor productivity) in the OECD countries are to a large extent explained by age structure changes. The 50–64 age group has a positive influence, and the group above 65 contributes negatively, while younger age groups have ambiguous effects. However, the mechanism behind these age effects is not yet resolved. Received: 16 January 1997/Accepted: 2 July 1998     

Profiles of union organizers from manufacturing and service unions

This study uses data on 229 organizers from eight unions to assess differences in characteristics of organizers employed by manufacturing and service unions. The results suggest that a new breed of organizer is entering the labor movement through service unions-organizers who are younger, more highly educated, more socially mobile, and have less experience in the union movement than organizers from manufacturing unions. This article is based on data collected for a dissertation written at the Graduate School of Business at Columbia University. I gratefully acknowledge the support of committee members David Lewin, James Kuhn, Casey Ichniowski, and Seymour Spilerman of Columbia and Charles A. O’Reilly III of the University of California at Berkeley. I thank John Delaney for his many helpful insights and suggestions during the course of my research and Shannon Ratcliff and Rick Fuentes for comments on an earlier draft of this paper. This research was financially supported by the Industrial Relations Research Center and the Management Institute at Columbia University and the Department of Management at Texas A&M University.     

Accommodating stochastic departures from percentile invariance in causal models

Summary.  Consider a clinical trial in which participants are randomized to a single-dose treatment or a placebo control and assume that the adherence level is accurately recorded. If the treatment is effective, then good adherers in the treatment group should do better than poor ad- herers because they received more drug; the treatment group data follow a dose–response curve. But, good adherers to the placebo often do better than poor adherers, so the observed adherence–response in the treatment group cannot be completely attributed to the treatment. Efron and Feldman proposed an adjustment to the observed adherence–response in the treatment group by using the adherence–response in the control group. It relies on a percentile invariance assumption under which each participant's adherence percentile within their assigned treatment group does not depend on the assigned group (active drug or placebo). The Efron and Feldman approach is valid under percentile invariance, but not necessarily under departures from it. We propose an analysis based on a generalization of percentile invariance that allows adherence percentiles to be stochastically permuted across treatment groups, using a broad class of stochastic permutation models. We show that approximate maximum likelihood estimates of the underlying dose–response curve perform well when the stochastic permutation process is correctly specified and are quite robust to model misspecification.