Knowledge that Transforms

A. James Boness, Frank C. Jen, A Model of Information Diffusion, Stock Market Behavior, and Equilibrium Price, The Journal of Financial and Quantitative Analysis, Vol. 5, No. 3 (Sep., 1970), pp. 279-296

Stocks differ in the variability of their prices; thus, as the level of stock market prices swings periodically, one observes a change in structure as the prices of more volatile issues change relative to those of a more stable character. Here we attempt to empirically establish some of the differentiating characteristics of these volatile issues. In doing so we add to the empirical and analytical work of Fritzemeier [4], Clendenin [2], Latané [7], Malkiel [8], and Heins and Allison [6]. Only the last of these efforts used regression techniques.

This study is another attempt to analyze the behavior of common stock prices. In the last decade, and even before that, literature has spewed forth an abundant supply of studies in this area, from random walkers, to optimum portfolioers, to performance measurers. Terms such as risk and return, variance and covariance, and variability and volatility proliferate journal pages and our daily conversations.

P. A. Tinsley, Capital Structure, Precautionary Balances, and Valuation of the Firm: The Problem of Financial Risk, The Journal of Financial and Quantitative Analysis, Vol. 5, No. 1 (Mar., 1970), pp. 33-62

A normative theory of capital budgeting requires determination of the correct cost of capital for the evaluation and selection of risky investment projects. Since different uses of funds within the firm may involve different degrees of uncertainty, the normative theory should take into account the effects of changes in the composition of the firm's portfolio of productive assets on its market valuation. The normative theory must therefore be based on a positive theory of market valuation. The objective of this paper is to develop and test an empirical specification of the positive theory.

Clement G. Krouse, Portfolio Balancing Corporate Assets and Liabilities with Special Application to Insurance Management, The Journal of Financial and Quantitative Analysis, Vol. 5, No. 1 (Mar., 1970), pp. 77-104

This paper is concerned with the validity of the conventional t tests on regression coefficients when there is serious multicollinearity between the explanatory variables. It is well known that increasing multicollinearity causes the true standard errors of regression coefficients to rise. The crucial question, however, is whether the conventional formulas will in practice reflect this rise. The purpose of this note is to show that the conventional t tests will in practice reflect this rise. But this note also points out the danger involved in mechanically dropping variables from multiple regression equations by t tests because t values of the regression coefficients may not be significantly different from zero when the true (population) values of these coefficients are in fact not zero, if the explanatory variables are highly intercorrelated.

In testing hypotheses, researchers are almost always faced with the problem of isolating the effect of certain variables. This is a particularly acute problem in the social sciences, where the absence of an experimental environment means that researchers must resort to statistical methods of adjustment.