| Abstract | Dividend forecasting is a primary element in event-type studies which examine the market's reaction to information conveyed by dividend announcements. This study compares five dividend forecasting models: naive model, univariate time series model, vector autoregressive model, analyst forecast and composite dividend model for 112 listed companies in Taiwan for each of three years 1989-1991. The empirical results indicate that the analyst forecast model makes better dividend forecasts in Taiwan than the other four models. These results support the rationality assumptions of analyst forecasts in the market. |
|---|
