Regression Revisited

Sir Francis Galton introduced median regression and the use of the quantile function to describe distributions. Very early on the tradition moved to mean regression and the universal use of the Normal distribution, either as the natural ‘error’ distribution or as one forced by transformation. Though the introduction of ‘quantile regression’ refocused attention on the shape of the variability about the line, it uses nonparametric approaches and so ignores the actual distribution of the ‘error’ term. This paper seeks to show how Galton's approach enables the complete regression model, deterministic and stochastic elements, to be modelled, fitted and investigated. The emphasis is on the range of models that can be used for the stochastic element. It is noted that as the deterministic terms can be built up from components, so to, using quantile functions, can the stochastic element. The model may thus be treated in both modelling and fitting as a unity. Some evidence is presented to justify the use of a much wider range of distributional models than is usually considered and to emphasize their flexibility in extending regression models.     

Psychographic constructs and demographic segments

As marketers attempt to place advertisements based on demographic profiles, the use of psychographic information becomes more important. The purpose of this research is to evaluate the validity of selected psychographic measures as well as to then relate these constructs to demographic segments. The analysis, using LISREL VI, assesses the constructs, which then, based on MANOV, are related to demographic segments. Implications of the study for validating psychographic measures and for applying this knowledge are discussed. © 1995 John Wiley & Sons, Inc.     

A Monte Carlo study of autoregressive integrated moving average processes

Six of the simpler ARMA type models are examined with respect to properties of a variety of proposed estimators of unknown parameters. The findings suggest that if only one estimation method were available to a researcher the choice should probably be maximum likelihood. Stationarity- and invertibility-restricted estimation would appear appropriate when parameters are thought to be within 5 percent of constraint boundaries.     

Firm Growth and Supply Chain Partnerships: An Empirical Analysis of U.K. SME Subcontractors

This paper examines the performance of a sample of 211 U.K.subcontractors to evaluate whether differences in how they manage their supply chain relationships are associated with differences in (sales and employment)growth rates over two consecutive 3 year periods from 1993 to 1999.We identified 34 firms that had close partnership relationships with members of their supply chain. Our empirical findings indicate that firms with inter-firm partnership arrangements with members of their supply chain experienced significantly higher growth rates. These results suggest that inter-firm partnerships may facilitate more rapid and sustained SME growth,though further research is required to determine the role played by partnerships and the extent to which this may vary to reflect differing owner-manager motivations and growth opportunities.     

ACCOUNTING FOR EMPLOYEE ENTITLEMENTS*

This paper considers the problem of accounting for employee entitlements. Accrued entitlements to annual leave, sick leave and long service leave are evaluated by reference to the basic characteristics of an accounting liability and a case is presented for liability recognition in each instance. An empirical survey undertaken by the authors shows current practice in this area and indicates the need for improved financial reporting.