Tukey-Type Distributions in the Context of Financial Data

Abstract

In one-parameter (θ) families, we were not aware of explicit hypothesis testing scenarios where maximal invariant statistics failed to distinguish the models. We start with a concrete example (Sec. 2.2) to highlight such a hypothesis testing problem involving markedly different models. In this problem, because of the absence of a nontrivial uniformly most powerful invariant (UMPI) test, we briefly suggest two approaches to test the hypothesis. The first resolution (Sec. 3.1) is frequentist in nature. It utilizes a weight function on the parameter space and compares “average” distributions obtained under the null and alternative models in the sense of Wald (1947 Wald , A. ( 1947 ). Sequential Analysis . New York : Wiley . [Google Scholar] 1950 Wald , A. ( 1950 ). Statistical Decision Functions . New York : Wiley . [Google Scholar]). In contrast, a fully Bayesian resolution (Sec. 3.2) is also included. The note ends with a series of other interesting examples involving one-parameter families where maximal invariant statistics fail to distinguish the hypothesized models. The examples include easy-to-construct families of probability models involving only a single location or scale parameter θ.     

Semiparametric estimation of plane similarities: application to fast computation of aeronautic loads

In the big data era, it is often needed to resolve the problem of parsimonious data representation. In this paper, the data under study are curves and the sparse representation is based on a semiparametric model. Indeed, we propose an original registration model for noisy curves. The model is built transforming an unknown function by plane similarities. We develop a statistical method that allows to estimate the parameters characterizing the plane similarities. The properties of the statistical procedure are studied. We show the convergence and the asymptotic normality of the estimators. Numerical simulations and a real-life aeronautic example illustrate and demonstrate the strength of our methodology.     

Marketing Category Forecasting: An Alternative of BVAR‐Artificial Neural Networks*

Analyzing scanner data in brand management activities presents unique difficulties due to the vast quantity of the data. Time series methods that are able to handle the volume effectively often are inappropriate due to the violation of many statistical assumptions in the data characteristics. We examine scanner data sets for three brand categories and examine properties associated with many time series forecasting methods. Many violations are found with respect to linearity, normality, autocorrelation, and heteroscedasticity. With this in mind we compare the forecasting ability of neural networks that require no assumptions to two of the more robust time series techniques. Neural networks provide similar forecasts to Bayesian vector autoregression (BVAR), and both outperform generalized autoregressive conditional herteroscedasticty (GARCH) models.     

A Method for Computing the Fraction of Attributable Risk Related to Climate Damages

The recent decision of the U.S. Supreme Court on the regulation of CO₂ emissions from new motor vehicles^{( 1 )} shows the need for a robust methodology to evaluate the fraction of attributable risk from such emissions. The methodology must enable decisionmakers to reach practically relevant conclusions on the basis of expert assessments the decisionmakers see as an expression of research in progress, rather than as knowledge consolidated beyond any reasonable doubt.^{( 2,3,4 )} This article presents such a methodology and demonstrates its use for the Alpine heat wave of 2003. In a Bayesian setting, different expert assessments on temperature trends and volatility can be formalized as probability distributions, with initial weights (priors) attached to them. By Bayesian learning, these weights can be adjusted in the light of data. The fraction of heat wave risk attributable to anthropogenic climate change can then be computed from the posterior distribution. We show that very different priors consistently lead to the result that anthropogenic climate change has contributed more than 90% to the probability of the Alpine summer heat wave in 2003. The present method can be extended to a wide range of applications where conclusions must be drawn from divergent assessments under uncertainty.     

Pair‐copula constructions for non‐Gaussian DAG models

We propose a new type of multivariate statistical model that permits non‐Gaussian distributions as well as the inclusion of conditional independence assumptions specified by a directed acyclic graph. These models feature a specific factorisation of the likelihood that is based on pair‐copula constructions and hence involves only univariate distributions and bivariate copulas, of which some may be conditional. We demonstrate maximum‐likelihood estimation of the parameters of such models and compare them to various competing models from the literature. A simulation study investigates the effects of model misspecification and highlights the need for non‐Gaussian conditional independence models. The proposed methods are finally applied to modeling financial return data. The Canadian Journal of Statistics 40: 86–109; 2012 © 2012 Statistical Society of Canada     

Registration,Residency Restrictions,and Community Notification: A Social Capital Perspective on the Isolation of Registered Sex Offenders in Our Communities

This article highlights the importance of social capital for registered sex offenders who are reintegrating back into their communities. Although not always identified among community corrections, the sex offender registry creates a punitive atmosphere that diminishes the amount of available social capital for all involved—community members, sex offenders, and the government. Lost social capital contributes to recidivism, reentry problems, and mental health issues among registered sex offenders. We argue that deterrent and protective features of the sex offender registry are overemphasized and the goal of reintegration has been undermined. The loss of social capital exacerbates (1) the minimization of trust, (2) low expectations of rehabilitation and reentry, (3) limited contact and information from role models, (4) increased access to criminal capital, (5) formal sanctioning power of the registry, and (6) loss of sanctioning power from family and communities. Through this in-depth analysis, we argue that the current state of the registry system harms the social capital of all involved when a sex offense occurs—not just the offender—and we assess directions for future practices, as well as policy implications.     

Wrangling Rumors of Corruption: Institutional Neutralization of the Jerry Sandusky Scandal at Penn State University

The Jerry Sandusky scandal erupted nationally in November 2011, dragging with it accusations of child molestation, manipulation, perjury, and ultimately a blatant disregard for the suffering of 10 young victims. This article examines how senior university officials covered up the scandal and inevitably allowed Sandusky to continue molesting children for over 15 years. University officials broke the law by failing to report the abuses, and later when they lied to the investigating grand jury assigned to the case. Using Sykes and Matza’s techniques of neutralization, we explain how university officials downplayed these victimizations to preserve the reputation of Penn State.     

Perceived Prevalence and Definitions of Sexual Dysfunction as Predictors of Sexual Function and Satisfaction

Evidence for the influence of sexual beliefs on sexual functioning and satisfaction has mainly emanated from clinical lore. Empirical investigations on this topic remain sparse. This study investigated whether beliefs regarding prevalence and definitions of male and female sexual dysfunctions predicted sexual function and satisfaction in a sample of 131 undergraduate students. Results indicated that higher perceived prevalence of male and female sexual dysfunctions was predictive of lower sexual functioning and poorer sexual satisfaction in women. For the male participants, none of the examined sexual beliefs emerged as significant predictors of their sexual functioning or satisfaction. Surprisingly, it was also found that participants estimated the prevalence of female sexual dysfunctions to be higher than male sexual dysfunctions, while defining male sexual dysfunctions more broadly than female sexual dysfunctions. Possible mechanisms for the findings are provided.