A regression-based smoothing spline Monte Carlo algorithm for pricing American options in discrete time

American options in discrete time can be priced by solving optimal stopping problems. This can be done by computing so-called continuation values, which we represent as regression functions defined recursively by using the continuation values of the next time step. We use Monte Carlo to generate data, and then we apply smoothing spline regression estimates to estimate the continuation values from these data. All parameters of the estimate are chosen data dependent. We present results concerning consistency and the estimates’ rate of convergence.     

Classifying At‐Risk High School Youth: The Influence of Exposure to Community Violence and Protective Factors on Academic and Health Outcomes

Using cluster analysis, 789 predominately Latino and African American high school youth were classified into varying academic at‐risk profiles using self‐reported levels of academic confidence, motivation to attend school, perceived family support, connections with teachers and peers, and exposure to violence. Six clusters emerged, 5 of which were identified as “at‐risk.” The clusters were examined in relation to academic stress, health status, grades, and school retention. Exposure to violence was one distinguishing feature of youth identified as most vulnerable, vulnerable, and resilient; however, youth identified as resilient recorded better academic outcomes.     

An Experimental Evaluation of the Serial Cost Sharing Rule

This paper proposes an experimental test to evaluate the performance of the serial cost sharing rule, originally proposed by Shenker [Sigmetrics, 241–242 (1990)] and then analyzed by Moulin and Shenker [Econometrica 60, 1009–1037 (1992)]. We report measures of the performance and efficiency of the serial mechanism by comparing the choices and payoffs attained by the subjects to the expected equilibrium allocations. Experimental evidence shows that learning is needed for the subjects to converge to the equilibrium strategy. However, in terms of efficiency, the serial mechanism leads to almost efficient allocations.     

Constituents’ economic interests and senator support for spending limitations

Peltzman [Peltzman, S., 1984. Constituent interest and congressional voting. Journal of Law and Economics 27, 181–210] argues that if constituents’ economic interests have well-defined “winners and losers” and are appropriately measured, then constituents’ economic interests, and not legislator ideology, are the most important determinates of legislator voting. We test Peltzman's theory by examining senatorial voting on three mandated spending limitation bills. We find, consistent with Peltzman's theory, that the ratio of federal spending in a senator's state to federal taxes paid by that state, and not a senator's personal ideology, matters on legislation where there are well-defined economic “winners and losers.” This is particularly important because unlike other constituents’ economic interest measures that only impact a fraction of the constituency, the ratio of federal spending to federal taxes in a state represents the economic interests of all the constituents in a state.     

How far does the gender gap extend?: Decision making on state Supreme Courts in Fourth Amendment Cases, 1980–2000

The importance of women on the bench and the influence of gender on judicial decision making has garnered much scholarly attention. We examine the voting behavior of male and female justices in 718 Fourth Amendment search and seizure votes cast on state Supreme Courts between 1980 and 2000. We find that women justices, controlling for institutional, political, and legal constraints, are more likely to rule in favor of the criminal defendant than their male brethren in cases decided after 1991 but not before. We also find women justices serving with female colleagues are more inclined to render liberal votes. We conclude the influence of gender may be evident in a wider variety of cases than those dealing with women's lives but that this influence is dependent upon the existence of a critical mass of women on the state court benches.     

Distal and Proximal Factors in Domestic Violence: A Test of an Integrated Model

We employed 4,095 couples from both waves of the National Survey of Families and Households (NSFH) to test a model of couple violence drawn from several theoretical perspectives. The outcome distinguishes among nonviolent couples and those experiencing either physical aggression or intense male violence. According to the model, background characteristics of couples are related to relationship stressors, which affect the risk of violence via their tendency to promote verbal conflict. Considerable support for the model was found. Couples were at higher risk for one or both forms of violence if they were younger at union inception, had been together for less time, were both in their first union, had only one partner who was employed, had a nontraditional woman paired with a traditional man, had at least one partner who abused substances, had more children, had more frequent disagreements, exhibited a more hostile disagreement style, or lived in an economically disadvantaged neighborhood. Moreover, the effects of stressors such as the number of children and couples' employment status disparities appear to be mediated by disagreement frequency and disagreement style.     

Data skeletons: simultaneous estimation of multiple quantiles for massive streaming datasets with applications to density estimation

We consider the problem of density estimation when the data is in the form of a continuous stream with no fixed length. In this setting, implementations of the usual methods of density estimation such as kernel density estimation are problematic. We propose a method of density estimation for massive datasets that is based upon taking the derivative of a smooth curve that has been fit through a set of quantile estimates. To achieve this, a low-storage, single-pass, sequential method is proposed for simultaneous estimation of multiple quantiles for massive datasets that form the basis of this method of density estimation. For comparison, we also consider a sequential kernel density estimator. The proposed methods are shown through simulation study to perform well and to have several distinct advantages over existing methods.     

Constrained allocation problems with single-peaked preferences: An axiomatic analysis

We introduce a new class of problems that contains two existing classes: allocation problems with single-peaked preferences and bankruptcy problems. On this class, we analyze the implications of well-known properties such as Pareto optimality, strategy-proofness, resource-monotonicity, no-envy, equal treatment of equals, and two new properties we introduce, hierarchical no-envy and independence of nonbinding constraints. Unlike earlier literature, we consider rules that allow free-disposability. We present characterizations of a rule we introduce on this domain. We relate this rule to well-known rules on the aforementioned subdomains. Based on this relation, we present a characterization of a well-known bankruptcy rule called the constrained equal awards rule. Received: 22 June 2000/Accepted: 21 March 2002 This paper is based on the first chapter of my Ph.D. thesis submitted to the University of Rochester. I wish to thank my advisor, William Thomson, for helpful comments and suggestions.