Statistical classification models applied to common stock analysis

The application of statistical classification techniques to various aspects of equity financing and returns performance has been an attractive and fairly prolific area of research in the last 10–15 yrs. The various aspects of equity analysis relevant to classification techniques are more diverse than fixed income analysis and, until recently, presented more interesting empirical as well as theoretical challenges.The purpose of this paper is to review and comment upon numerous classification studies related to several aspects of common stock analysis, and, in so doing, to provide a clear picture of the variety of application areas amenable to statistical classification techniques. These areas include (1) common stock investment categories; (2) price-earnings and return-risk equity classification; (3) information content and return performance; and (4) capital structure questions.     

Concept testing

This paper is a review of concept testing based on the published literature and a series of personal interviews with leading practitioners. While there is considerable agreement on the usefulness of concept testing, practitioners disagree on the best way to perform them. In addition to highlighting these disagreements, the paper covers general suggestions for improving concept testing.     

Exponents of multiattribute models

The effect of different exponents on the predictive ability of multiattribute models is examined. Survey data on 1202 individuals concerning their preferences for television shows is analyzed. The results indicate that the optimal power is not 1, and that consequently it may be somewhat more advantageous to improve on an already strong attribute than on relatively weak ones.     

Price elasticity and bid-ask price spreads in the treasury bond market

Typical analyses of transactions costs in the bond markets explain these costs in terms of yield, term to maturity, coupons, and issue size. However, these analyses do not recognize the price elasticity of bonds to interest rate movements, which provides better measures of market risk and bid-ask price spreads. Elasticity or duration and issue size together display stronger associations with bid-ask price spreads than do the traditional variables. The association is also less subject to multicollinearity of the independent variables. Finally, stepwise regressions show that coupon and yield data add no information about bid-ask price spreads not already impounded in the duration statistic. This casts doubt on the nonduration arguments often used to support these variables as separately meaningful in transactions cost analyses.     

Predictive power of joint space models constructed with composition techniques

A comparison of different methods of building joint spaces indicates significant differences across both product classes and modeling techniques in the ability to predict preferences for validation brands. Perceptual spaces constructed with discriminant analysis combined with vector representations of preference gave the best predictions across the product clases analyzed. Also, segment-specific perceptual spaces did not, in general, improve the predictive ability of the models studied.     

Culture and organizational control

The influence of socio-cultural processes on organizational control is explored. The concepts of external and internal control are developed and related to several key dimensions of socio-cultural analysis which vary cross-culturally. Ethnographic evidence is presented to illustrate these different relationships.     

International bank lending: Political risk and portfolio diversification

The extent to which a large U.S. bank, all U.S. banks, and banks in the Group of Ten took account of political risk in their international country exposures in 1976 is tested using a simple portfolio diversification model. Assuming that political risks are important relative to economic risks, and that political risks are uncorrelated across countries, these banks' exposures should be negatively related to political risk indices. However, the portfolios of these banks appear to be related to political risk only insofar as political risk is roughly approximated by GNP per capita. International banks were not yet able to systematically vary their international portfolios with respect to political risk.     

Behavior of default-risk premiums for corporate bonds and commercial paper

The question addressed in this paper is whether default-risk premiums for short-term and for long-term securities behave differently over time. The question is important because it affects decisions by corporations and state and local governments as to the maturity structure of their debt. It also affects decisions by investors as to the maturity and the type and grade of security in which they invest. Several hypotheses have been advanced about the behavior of default-risk premiums for different maturities. The purpose of this paper is to test these hypotheses empirically with a set of data heretofore unused. In so doing, new insights are gained into the behavior of default-risk premiums for different maturities.     

Estimating temporal trends in preferences measured by graded paired comparisons

A sizable marketing research literature on preference measurement, prediction, and explanation has thus far been more concerned with point estimates of preference than with consistent changes over time. Such temporal trends can be estimated using data collected from graded paired comparisons. An appropriate technique for deriving individual and group trend parameters is first described and then illustrated using data from an experiment dealing with aesthetic preferences. Suggestions are offered concerning its advantages and limitations for applications in marketing.     

Variations in municipal bond default risk premia by term-to-maturity

A recent study by McInish of the influence of term-to-maturity on municipal bond default risk premia concluded that default risk premia were not invariant with respect to maturity. That study, as well as an earlier one by Robinson, failed to consider the effects of issuer credit quality. Using a large cross-sectional sample of general obligation bonds sold between 1977 and 1980, the influence of issuer credit quality on the relationship between term-to-maturity and default risk premia is investigated. The results indicate that default risk premia were an increasing function of maturity, and that this effect was larger for lower rated bonds.     

Price-Anderson act declared unconstitutional: The decision and its effects on nuclear power

In March 1977, the $560 million limit on liability in the Price-Anderson Act was declared unconstitutional. The Price-Anderson Act sets forth a combination private-public insurance and compensation system for handling risks associated with commercial nuclear operations. The limit was found to violate the due process and equal protection provisions of the Fifth Amendment of the U.S. Constitution. This paper examines the salient points of the decision which include: (a) the effects of nuclear plant operations on the plaintiffs; (b) the dependence of nuclear power development on the Price-Anderson Act; (c) the plaintiff's right to bring suit; and (d) the rationale for declaring the Act unconstitutional. The potential effects include the possibility that many utilities and suppliers of nuclear plant components will terminate their nuclear business, the availability of capital funds for nuclear plants will be reduced, and that cost of capital will be increased to reflect the greater risk of nuclear development.     

Parameter nonstationarity in retail choice models

The question of spatial nonstationarity in retail choice models generally has been ignored in the literature. This paper discusses why such nonstationarity might arise and presents an empirical test of nonstationarity in grocery choice data collected from a midwestern city. Based on these findings a nonstationarity retail choice model is proposed. The nonstationary model predicts data from a hold-out sample better than the stationary model.     

The anatomy of the Korean general trading company

The historical development of Japanese trading companies is reviewed. The concept of “trading company” is developed along three dimensions: product diversification, area diversification, and functional diversification. The seven year history of Korean General Trading Companies is analyzed with regard to their historical background, modus operandi, and current problems. The analysis reveals that most of the Korean GTCs, in spite of their impressive performance in terms of trade volume, have experienced severe deterioration of profitability. Finally, the paper states the change of the Korean Government's policy on the GTCs and contemplates its implication for GTCs' future direction within the context of the definition of trading company.     

Stability of mutual fund systematic risk statistics

Empirical data for 85 mutual funds are used to test the intertemporal stability of their systematic risk statistics. Reasons why the portfolios may be nonstationary are suggested. A random coefficient model developed by Theil [37] is employed to test for the stability of each fund's beta. The data suggest that some funds do exhibit a beta that is best described as being a random coefficient. However, the percentage of funds exhibiting this characteristic was not statistically different from the percentage of randomly created portfolios that exhibited a random beta coefficient. The findings of this study support the statistical models employed in two other recent studies [18,21] to test for the stability of beta. Yet, for mutual funds that do exhibit a random beta coefficient, the partitioning of the total risk of the portfolio return into systematic and unsystematic risk is no longer valid for explaining the total risk.     

Integrating strength-weakness analysis into strategic planning

Strength-weakness assessment, which must be performed as a part of any strategic planning process, is presented in terms of a process, termed SWA, that involves managers in making the critical informational choices that are implicit in strategic assessments of strengths and weaknesses. The process is illustrated in terms of its underlying premises, their implications, its benefits, and an illustrative substantive framework that can be used to guide the process.