Predicting Earnings Using a Model Based on Cost Variability and Cost Stickiness

This paper aims to evaluate the earning forecasting model based on cost variability and cost stickiness   in comparison to other forecasting models. Cost stickiness means that the rate of decrease in costs while sale declines is less than the rate of increase in costs while sale grows. In other word, costs are sticky downward. The data used in this research was gathered from 85 companies accepted in Tehran stock market from 1994 to 2004. To analyze the data two regression techniques called simple and rolling methods and also confidence coefficient R2 and F test are used. The results indicate that the power of the earning forecasting model based on cost variability and cost stickiness is significantly more than the others'.