Quarterly Earnings Studies

The Quarterly Earnings Studies are a part of time-series analysis. These studies aim at predicting future returns for a stock based on publicly available quarterly earnings reports.

Several studies were conducted by different groups to examine firms that experienced unanticipated changes in quarterly earnings based on three categories as to how actual earnings deviated from expectations i.e., (i) any deviation from expectations, (ii) a deviation plus or minus 20 percent, and (iii) a deviation of at least 40 percent. The study examined the abnormal price movements for all the above mentioned categories of deviations, and compared the post-announcement effects on the stocks with the earnings surprise (the amount by which the actual earnings is more than the expected results). The results of these studies suggested that favorable information contained in quarterly earnings reports is not instantaneously reflected in stock prices and a significant relationship exists between the size of the earnings surprise and the post announcement stock price change.

When the results of these studies were subsequently reviewed, it was found that the post-announcement risk-adjusted abnormal returns were consistently positive, which is inconsistent with market efficiency. The abnormal returns could be due to problems in the CAPM and not due to market inefficiencies.

Recent studies use the concept of the Standardized Unexpected Earnings (SUE), which normalizes the difference between actual and expected earnings for the quarter by the standard error of estimate from the regression used to derive the expected earnings figure, instead of just examining the percentage differences between actual and expected results. The SUE can be defined as:

The standard error of a statistic is the standard deviation of the sampling distribution of that statistic. Standard errors are important because they reflect how much sampling fluctuation a statistic will show. The standard error of a statistic depends on the sample size. In general, the larger the sample size, the smaller the standard error. The standard error of a statistic is usually designated by the Greek letter sigma (s) with a subscript indicating the statistic. For instance, the standard error of the mean is indicated by the symbol: sM.