Statistical Decision Problems and Bayesian Nonparametric Methods

This paper considers parametric statistical decision problems conducted within a Bayesian nonparametric context. Our work was motivated by the realisation that typical parametric model selection procedures are essentially incoherent. We argue that one solution to this problem is to use a flexible enough model in the first place, a model that will not be checked no matter what data arrive. Ideally, one would use a nonparametric model to describe all the uncertainty about the density function generating the data. However, parametric models are the preferred choice for many statisticians, despite the incoherence involved in model checking, incoherence that is quite often ignored for pragmatic reasons. In this paper we show how coherent parametric inference can be carried out via decision theory and Bayesian nonparametrics. None of the ingredients discussed here are new, but our main point only becomes evident when one sees all priors—even parametric ones—as measures on sets of densities as opposed to measures on finite-dimensional parameter spaces.     

Initial public offerings in the gaming industry: an empirical study

The fastest growing segment of the hospitality industry is gaming-related business. This industry has experienced record numbers of companies going public, and their stocks are considered favorable long-term investments. Research in the initial public offering (IPO) area suggests that investors acquiring stock at the initial offering price earn large returns. The purpose of this study was to determine if large returns are being experienced for IPOs in the gaming segment of the hospitality industry, and if these large returns were limited to investors who purchased the stock at the initial offer price. There were 14 gaming-related companies selected for the study. The conclusions supported research reporting that the highest returns from IPO investments are made when the stock is purchased at the initial offer price. This study concludes that returns based on the initial offer price were greater than the casino index and the IPO index. When the investor purchased the stock at the first day's closing price, however, returns compared to the two indices were surpassed only after holding the stock for 8 weeks.     

Integration in the mortgage market

The deregulatory trend and advances in technology during the 1980s removed many restrictions on the ability of U.S. depository financial institutions to obtain and redistribute funds across diverse geographical markets. This pervasive deregulation and innovation should have increased the degree of integration between different geographical financial markets. Yet there is little empirical evidence available on the validity of this expectation. It is important to provide such evidence since much of the U.S. depository institution regulatory policy is predicated on the assumption of highly localized, segmented financial markets. Considering alternative breakpoints at 1980 (DIDMCA) and at 1982 (Garn-St Germain), the current study tests the hypothesis that the degree of geographical financial integration after this period exceeded that prior to this period. Mortgage markets are focused on due to their historical importance in the regulation of funds flows. The study finds a significant increase in the mean contemporaneous correlation among FHLB districts' mortagage rate residuals in a vector-autoregressive system between two test periods. Further analysis shows that the distance between FHLB districts' headquarters and their respective pairwise interdistrict correlation coefficients are negatively related in the prior period but not significantly related in the later period. Economic booms and busts alternated among the districts over the two sample periods in a manner consistent with the reallocation of capital among more integrated financial markets. Individual districts' mortgage rates have been more sensitive to variations in national credit market conditions since deregulation was legally recognized by DIDMCA in 1980. Thus, the collective empirical evidence found in this study indicates that mortgage markets have responded to deregulation and marked technological advances by moving toward a national, highly integrated market. Regulators' preoccupation with highly localized, segmented markets must consequently be reexamined.     

Corporate Reputation and Social Performance: The Importance of Fit

abstract    Utilizing data on a sample of large firms, we estimate a model of corporate reputation. We find reputation, derived from the assessments of managers and market analysts, to be determined by a firm's social performance, financial performance, market risk, the extent of long-term institutional ownership, and the nature of its business activities. Furthermore, the reputational effect of social performance is found to vary both across sectors, and within sectors across the various types of social performance. Specifically, our results demonstrate the need to achieve a 'fit' among the types of corporate social performance undertaken and the firm's stakeholder environment. For example, a strong record of environmental performance may enhance or damage reputation depending on whether the firm's activities 'fit' with environmental concerns in the eyes of stakeholders.     

The Development of Corporate Charitable Contributions in the UK: A Stakeholder Analysis

This paper investigates the determinants of corporate charitable donations within a comparative study of corporate behaviour in two time periods, 1989–90 and 1998–99. The analysis is based on a longitudinal data set that includes over 400 UK listed companies. The determinants of corporate charitable donations are explored within a stakeholder model and the relationship between corporate charitable donations and a set of firm and industry variables is estimated using OLS. Particular emphasis is placed on industry effects and the impact of social and environmental stakeholders. The results highlight a significant change in behaviour between 1989–90 and 1998–99 that may reflect a strategic response by corporate decision‐makers to external concerns over corporate social responsibility. In the early period corporate charitable donations were substantially determined by profits. However, this relationship has weakened during the 1990s as firms have become increasingly responsive to stakeholder influences. The results for the later period emphasize the increasing importance of corporate visibility, and the development of social and environmental influences on corporate charitable contributions.     

The relationship between major-league sports’ official sponsorship announcements and the stock prices of sponsoring firms

This study presents analysis of the impact of “official product” sports sponsorships with the National Football League (NFL), Major League Baseball (MLB), the National Hockey League (NHL), the National Basketball Association (NBA), and the Professional Golfers Association (PGA) on the stock prices of sponsoring firms. The primary finding of the study is that, in the main, announcements were accompanied by increases in shareholder wealth. The 53 sponsors analyzed experienced mean increases in stock valuations of about $257 million. A multiple regression analysis of firm-specific stock price changes and selected corporate and sponsorship attributes indicates that official product sponsorships with the NBA, NHL, and PGA and those with smaller market shares were associated with the largest gains in share prices. Although corporate cashflow (a proxy for agency conflicts) is statistically unrelated to shareholder approval, sponsorships by high-technology companies were associated with stronger stock price reactions than otherwise. Finally, product congruence with the sponsored sport was positively related to changes in stock prices. T. Bettina Cornwell (b.cornwell@business.uq.edu.au) is Professor of Marketing and Leader of the Marketing cluster in the UQ Business School at the University of Queensland, Australia. She was formerly Professor of Marketing in the Fogelman College of Business and Economics at the University of Memphis. She received her Ph.D. from the University of Texas. Her research focuses on promotion and consumer behavior, especially with regard to international and public policy issues. Other articles on the topic of sponsorship-linked marketing have recently appeared in theJournal of Advertising, the Journal of Advertising Research, theJournal of Business Research, andPsychology & Marketing. Stephen W. Pruitt (pruittst@umkc.edu) is the holder of the Arvin Gottlieb/Missouri Endowed Chair of Business Economics and Finance in the Henry W. Bloch School of Business and Public Administration at the University of Missouri-Kansas City. He received his Ph.D. from Florida State University. He has published more than 45 articles, most of which employ event study methodologies, in journals such as theJournal of Finance, theJournal of Political Economy, Financial Management, theJournal of Public Policy and Marketing, and theJournal of Advertising Research. John M. Clark (clarkj@cba.usm.edu) is an assistant professor of finance at the University of Southern Mississippi. He received his Ph.D. from the University of Alabama. His research interests include options and other derivatives, investments, and the impact of real events upon the stock prices of corporations. His work has appeared in scholarly outlets such as theJournal of Advertising Research, theFinancial Review, and theJournal of Business Ethics.     

Class length and student performance: An extended study

Many accounting educators believe that the student learning of accounting is better facilitated over a longer period of time, rather than a shorter period of time. This study examined the results of student performance in two introductory accounting courses, comparing student performance results of four-week summer classes with the results of traditional 16-week courses. In this research, the same professor taught the spring and summer ACC 201 courses, and two other professors taught both the spring and summer ACC 211 courses. Also held constant were the lecture material, course assignment, and test content. The results of the study indicate that in general, students taking introductory accounting over four weeks fare about as well as students who take introductory accounting over a traditional 16-week period. These results have potential importance beyond accounting education and provide support to universities offering more block courses to better serve individual student needs.