The purpose of this study is to determine which of three forecasting methods provides the most accurate short-term forecasts, in terms of absolute and mean absolute percentage error, for a unique set of data. The study applies three forecasting techniques--the Box-Jenkins or ARIMA method, cycle regression analysis, and multiple regression analysis--to quarterly sales tax revenue data. The final results show that, with varying success, each model identifies the direction of change in the future, but does not closely identify the period to period fluctuations. Indeed, each model overestimated revenues for every period forecasted. Cycle regression analysis, with a mean absolute percentage error of 7.21, is the most accurate model. Multiple regression analysis has the smallest absolute percentage error of 3.13.
| Identifer | oai:union.ndltd.org:unt.edu/info:ark/67531/metadc501220 |
| Date | 08 1900 |
| Creators | Renner, Nancy A. (Nancy Ann) |
| Contributors | McKee, William L., Sharp, Walton H. |
| Publisher | North Texas State University |
| Source Sets | University of North Texas |
| Language | English |
| Detected Language | English |
| Type | Thesis or Dissertation |
| Format | iv, 51 leaves, Text |
| Coverage | United States - Texas - Denton County - Denton, 1974-1985 |
| Rights | Public, Renner, Nancy A. (Nancy Ann), Copyright, Copyright is held by the author, unless otherwise noted. All rights reserved. |
Page generated in 0.0019 seconds