台灣毛豬批發價格組合預測模型之比較

Comparison on the Composite Forecasting Models for Wholesale Prices of Hogs in Taiwan

黃聖茹(Sheng-Ju Huang) ； 李佳珍(Jia-Jan Lee) ； 蕭清仁(Chiang-Ren Show)

《農業與資源經濟》 7卷2期 (2010/12) Pp. 1-35

https://doi.org/10.29796/ARE.201012.0001

摘要

本文旨在估計組合預測方法之組合權數，並比較組合預測方法之優劣，以提高預測之準確度。文中以台灣毛豬批發價格爲例，採用1990年至2007年台灣毛豬價格相關資料，應用單一預測模型－供需計量模型與介入模型及組合預測方法－常態誤差組合方法、迴歸式組合方法與貝氏組合方法，分別進行台灣毛豬批發價格預測。實證結果發現：在單一預測模型方面，以介入模型較優於供需計量模型；在組合預測模型方面，以迴歸式組合模型A表現最佳。而組合預測方法較單一預測模型表現良好，有益於提高預測的精確度，以利生產者掌握未來毛豬價格的趨勢。

關鍵字

組合模型 ； 毛豬批發價格 ； 預測

並列摘要

The purpose of this study is mainly to estimate composite weight, and then compare the composite forecasting models to increase the precision of the forecast. This study applies the individual forecasting models-Econometric Model and Intervention Model; the composite forecasting models-Normal Error Model, Regression Model and Bayesian Model to proceed with forecast of wholesale prices of hogs in Taiwan by the data of Taiwan poultry quantities, price and related variables from 1990 through 2007. The empirical results have shown that the composite forecasting model performs better than individual forecasting model; on the individual forecasting models, Intervention Model is better than Econometric Model; on the composite forecasting models, Regression Model A is the best. Therefore, this implies that the result of this study could provide the price information for farmers of Hogs.

並列關鍵字

Composite Model ； Wholesale Prices of Hogs ； Forecast