Search results

Constructing and evaluating behavioral science models is a complex process. Decisions must be made about which variables to include, which variables are related to each other, the functional forms of the relationships, and so on. The last 10 years have seen a substantial extension of the range of statistical tools available for use in the construction process. The progress in tool development has been accompanied by the publication of handbooks that introduce the methods in general terms (Arminger et al., 1995; Tinsley & Brown, 2000a). Each chapter in these handbooks cites a wide range of books and articles on specific analysis topics.

Gender inequality in paid work persists, in the form of a gender wage gap, occupational sex segregation and a “glass ceiling” for women, despite substantial institutional change in recent decades. Two classes of explanations that have been offered as partial explanations of persistent gender inequality include economic theories of statistical discrimination and social psychological theories of status-based discrimination. Despite the fact that the two theories offer explanations for the same phenomena, little effort has been made to compare them, and practitioners of one theory are often unfamiliar with the other. In this article, we assess both theories. We argue that the principal difference between the two theories lies in the mechanism by which discrimination takes place: discrimination in statistical models derives from an informational bias, while discrimination in status models derives from a cognitive bias. We also consider empirical assessments of both explanations, and find that while research has generally been more supportive of status theories than statistical theories, statistical theories have been more readily evoked as explanations for gender inequalities in the paid labor market. We argue that status theories could be more readily applied to understanding gender inequality by adopting the broader conception of performance favored by statistical discrimination theories. The goal is to build on the strong empirical base of status characteristic theory, but draw on statistical discrimination theories to extend its ability to explain macro level gender inequalities.

This chapter is designed to outline how current methods in formal policy analysis have evolved to better respect limits to an analyst's knowledge. These limits are referred to as model uncertainty both in order to capture the idea that formal policy analysis is predicated on mathematically precise formulations that embody assumptions on the part of an analyst and because model uncertainty, which represents a recognition of the potential for these assumptions to produce unsound analyses, has been an active area of research in economics and statistics for the last 15 or so years. The argumentation in this chapter is not original and is admittedly selective. For Austrian economists, the paper will hopefully be of interest in indicating how empirical work is evolving in a way that better respects limits to a social scientist's knowledge. I certainly do not mean to suggest that these arguments should eliminate the objections that have been raised by some Austrian economists to formal empirical work. Rather, the intent of this chapter is to indicate the possibility of dialog and debate between Austrian and non-Austrian economists on the role of formal empirical work. In several contexts, I have introduced arguments concerning the limits of formal econometric analysis by Hayek and von Mises to both illustrate how the perspectives in this chapter relate to their views in order to suggest why, in my judgment, some of their skepticism is unwarranted.

This chapter describes the complementary benefits of model-building and data analysis using algorithm and statistical modeling methods in the context of unobtrusive marketing field experiments and in transforming findings into isomorphic-management models. Relevant for marketing performance measurement, case-based configural analysis is a relatively new paradigm in crafting and testing theory. Statistical testing of hypotheses to learn net effects of individual terms in MRA equations is the current dominant logic. Isomorphic modeling might best communicate what executives should decide using the findings from algorithm and statistical models. Data testing these propositions here uses data from an unobtrusive field experiment in a retailing context and includes two levels of expertise, four price points, and presence versus absence of a friend (“pal” condition) during the customer-salesperson interactions (n = 240 store customers). The analyses support the conclusion that all three approaches to modeling provide useful complementary information substantially above the use of one or the other alone and that transforming findings from such models into isomorphic-management models is possible.

Jeliazkov and Poirier (2008) analyze the daily incidence of violence during the Second Intifada in a statistical way using an analytical Bayesian implementation of a second-order discrete Markov process. We tackle the same data and modeling problem from our perspective as cognitive scientists. First, we propose a psychological model of violence, based on a latent psychological construct we call “build up” that controls the retaliatory and repetitive violent behavior by both sides in the conflict. Build up is based on a social memory of recent violence and generates the probability and intensity of current violence. Our psychological model is implemented as a generative probabilistic graphical model, which allows for fully Bayesian inference using computational methods. We show that our model is both descriptively adequate, based on posterior predictive checks, and has good predictive performance. We then present a series of results that show how inferences based on the model can provide insight into the nature of the conflict. These inferences consider the base rates of violence in different periods of the Second Intifada, the nature of the social memory for recent violence, and the way repetitive versus retaliatory violent behavior affects each side in the conflict. Finally, we discuss possible extensions of our model and draw conclusions about the potential theoretical and methodological advantages of treating societal conflict as a cognitive modeling problem.

Graduate students often come to statistics courses with varying levels of motivation and previous academic preparation. Within the statistics education literature, there is a growing consensus to guide instructors who want to help their students gain the requisite statistical knowledge so they can conduct their own research and report their results accurately. Recommendations from the literature include using real data, showing worked-out example problems, and providing immediate feedback to allow students to reflect on the correct and incorrect decisions they made in their analyses. This chapter describes the use of expert decision models (EDMs) in two graduate-level statistics courses – multiple regression and structural equation modeling. Decision-Based learning is an effective way to support graduate students’ developing thinking about statistics. In both courses, the students encounter the EDM through a series of assignments which guides students through the process of specifying a statistical model, running that model in Statistical Package for the Social Sciences or Mplus, and interpreting the results. These assignments use real datasets whenever possible and are designed to expose students to various issues they may experience in their research (missing data, violations of assumptions, etc.) and to illustrate how an expert would have adapted to those issues to complete the analysis. The EDM, with its just-in-time, just-enough instruction, helps students navigate these obstacles through guided practice and allows them to develop the conditional knowledge to handle issues that will arise as they carry out their own research.

In class action antitrust litigation, the standards for acceptable economic analysis at class certification have continued to evolve. The most recent event in this evolution is the United States Supreme Court’s decision in Comcast Corp. v. Behrend, 133 S. Ct. 1435 (2013). The evolution of pre-Comcast law on this topic is presented, the Comcast decision is thoroughly assessed, as are the standards for developing reliable economic analysis. This article explains how economic evidence of both antitrust liability and damages ought to be developed in light of the teachings of Comcast, and how liability evidence can be used by economists to support a finding of common impact for certification purposes. In addition, the article addresses how statistical techniques such as averaging, price-dispersion analysis, and multiple regressions have and should be employed to establish common proof of damages.

This paper proposes the Student's t Dynamic Linear Regression (St-DLR) model as an alternative to the various extensions/modifications of the ARCH type volatility model. The St-DLR differs from the latter models of volatility because it can incorporate exogenous variables in the conditional variance in a natural way. Moreover, it also addresses the following issues: (i) apparent long memory of the conditional variance, (ii) distributional assumption of the error, (iii) existence of higher moments, and (iv) coefficient positivity restrictions. The model is illustrated using Dow Jones data and the three-month T-bill rate. The empirical results seem promising, as the contemporaneous variable appears to account for a large portion of the volatility.