PROBLEMS OF COMPARING or choosing among models of a stochastic process are frequently encountered in empirical research. In many such situations, conventional statistical procedures offer little guidance since they assume that the model is given. If the alternative models can be nested in a more general model, standard estimation and testing procedures can be employed. Often, however, such general models are not readily available and other considerations may dictate against their use. Recently, there has been considerable progress in the development of methods for comparing alternative non-rested models. A review of this work both Bayesian and non-Bayesian, is given in Gaver and Geisel [1]. Discussions of the Bayesian approach to the comparison of linear regression models are given in Zellner [3, Ch. 10] and Lempers [2], among others. In this paper we consider Bayesian comparison of linear models in which the disturbances have non-scalar covariance matrices. General posterior odds expressions are given and specialized to the case of first order autoregressive disturbances. We also consider a specification error problem in this context; that is, we examine the effect of ignoring the non-scalar covariance structure on the posterior odds ratio. For the first order autoregressive disturbance case we give an approximate expression indicating the magnitude of the error involved in computing the posterior odds ignoring the serial correlation. The accuracy of this approximation is investigated via a small sampling experiment. We use the following notatiori: Let the ith model, Mi (i = 1, 2,. .., N), be y = Xi/3i + yi where y is a T x 1 vector of observations on the random (dependent) variable of interest, Xi is a T x ki matrix of observations on the explanatory variables of Mi (Xi is assumed to be non-stochastic with rank ki), p3i is a ki x 1 vector of unknown parameters of Mi, and ui is a T x 1 vector of disturbances of Mi (yi is assumed to have a normal distribution with E(yi) = 0, and E(yiyii) = U22i where 2Ji is an unknown T x T positive definite symmetric matrix with trace (i) = T).2 Probability functions for the models are denoted by P( ), densities for parameters by 7r( ), and densities for observations by p( ).

This paper presents additional evidence on the relation between the investment opportunity set and financing, dividend, and compensation policies. Our results are based on a sample of 237 growth firms and 237 nongrowth firms. We find that growth firms have significantly lower debt/equity ratios and exhibit significantly lower dividend yields than nongrowth firms. We also find that growth firms pay significantly higher levels of cash compensation to their executives and have a significantly higher incidence of stock option plans than nongrowth firms. However, controlling for firm size, the incidence of bonus plans, performance plans, and restricted stock plans does not differ between growth and nongrowth samples.

We extend Healy (1985) by examining the relation between discretionary accruals and bonus plan bounds for a sample of 102 firms for the 1980–1990 period. Contrary to Healy, we find that when earnings before discretionary accruals fall below the lower bound, managers select income-increasing discretionary accruals (and vice versa). We believe that our results are more consistent with the income smoothing hypothesis than with Healy's bonus hypothesis. However, mechanical selection bias in portfolio formation cannot be entirely ruled out as an alternative explanation for our results.

This study investigates the rote of alternative earnings components in the CEO cash compensation function. We find that cash compensation is significantly positively related to above the line earnings, as long as results are positive. Compensation is shielded from the effects of above the line losses. Similarly, nonrecurring transactions that increase income flow through to compensation, but nonrecurring losses do not. This effect is noted for gains and losses that arise both from extraordinary transactions, discontinued operations and nonrecurring items that do not qualify for below the line presentation. Thus, the data tell a remarkably consistent story: gains flow through to compensation, but losses do not. The classification of the gain or loss on the income statement is of relatively little importance.

Examines the stock market reaction to the adoption of long-term compensation agreements for top management that are based on accounting goals. Method of study; Reaction observed for the adopting firms due to the impending shareholders' meeting rather than to the performance plan adoption per se; Caution in the interpretation of announcements made around the time of the annual shareholders' meeting.

Paul A. Copley, Jennifer J. Gaver, Kenneth M. Gaver, Simultaneous Estimation of the Supply and Demand of Differentiated Audits: Evidence from the Municipal Audit Market, Journal of Accounting Research, Vol. 33, No. 1 (Spring, 1995), pp. 137-155