Distortion Effects and Extreme Observations in Empirical Research: An Analysis of the Incremental Information Content of Cash Flows.

Linear regression models have been used in a number of studies examining the presence or absence of incremental information contents in cash flow. The results of these studies have not been consistent. This paper draws attention to the critical issue of extreme observations in the data. Extreme observations which exert undues influence on the parameter estimates in a regression model are shown ti cause results which whilst statistically significant may be invalid.