Robert N. Freeman, Senyo Tse, The Multiperiod Information Content of Accounting Earnings: Confirmations and Contradictions of Previous Earnings Reports, Journal of Accounting Research, Vol. 27, Current Studies on The Information Content of Accounting Earnings (1989), pp. 49-79
Baruch Lev, On the Usefulness of Earnings and Earnings Research: Lessons and Directions from Two Decades of Empirical Research, Journal of Accounting Research, Vol. 27, Current Studies on The Information Content of Accounting Earnings (1989), pp. 153-192
It is a great honor for me to be at this conference and speaking to you today. Nick Dopuch was not all that explicit when it came to a topic for this last session. Nick said, Talk about anything you like. I interpreted that to mean I should talk in general terms about my early work with Ray and its influence on the accounting literature; and in particular, about a paper we wrote about 20 years ago, which is now commonly referred to simply as Ball and Brown [1968]. I begin by covering the paper itself: the antecedent conditions, why the paper was written, what we attempted to do in the paper, and what was novel as far as we were concerned. Next, I give my view of the main strands in the accounting literature, since 1968, that are related to our work. I conclude by offering a few thoughts on directions that the capitalmarkets-based accounting literature might take in the years ahead.
Wayne R. Landsman, Aswath Damodaran, Using Shrinkage Estimators to Improve Upon Time-Series Model Proxies for the Security Market's Expectation of Earnings, Journal of Accounting Research, Vol. 27, No. 1 (Spring, 1989), pp. 97-115
To detect variance effects, researchers have primarily relied on the square of the standardized market model residual, i.e., Beaver's U.1 A similar statistic, the absolute value of the standardized residual, has also been used for this purpose. We call this statistic May's U.2 The rationale for using either Beaver's U or May's U is that, in a portfolio, a variance increase will be reflected in unusually large negative and positive residuals. These will tend to cancel out in a test based on ordinary residuals, but squared residuals or their absolute values will yield a cumulative effect. If the residuals are normally distributed (as assumed by the linear model), then Beaver's U is the best statistic, being most likely to detect a variance effect. Weekly and daily residuals are not normally distributed. They are leptokurtic (heavy-tailed) and skewed. Marais [1984] notes that the normal approximation to Beaver's U is unreliable for significantly leptokurtic residuals and attempts to correct this unreliability through bootstrapping. Marais does not, however, consider the impact of leptokurtosis on the optimality of Beaver's U. We show that Beaver's U is no longer optimal for leptokurtic residuals and that it is dominated by May's U.