通貨膨脹預測：以台灣為例

Inflation Forecasting In Taiwan

張育菁

指導教授 ： 林靜儀

國立清華大學/科技管理學院/經濟學系/碩士(2012年)

https://doi.org/10.6843/NTHU.2012.00065

摘要

摘要
　　通貨膨脹率一直是總體經濟的重要指標，影響通貨膨脹率的因素很多，加入過多變數會造成自由度過低，因此本篇將影響通貨膨脹率的因素進行主成分分析(Principal component analysis)，不僅可以涵蓋各個變數，並且能避免自由度過低的問題。
　　本篇使用主成分分析(Principal component analysis)與傳統自我迴歸模型(Autoregressive, AR)、菲利浦曲線(Phillips curve)及以所有可獲得變數預測的最小平方法(ordinary least square, OLS)比較預測通貨膨脹準確性，結論是使用主成分分析(Principal component analysis)後通貨膨脹率預測能力明顯增加，菲利浦曲線(Phillips curve)對通貨膨脹率的預測能力較為不佳。

關鍵字

通貨膨脹 ； 通貨膨脹率 ； CPI

並列摘要

Abstract
Inflation forecasting is one of the most indexes in economic situation. There are a lot of factors that affect inflation, such as the interest rate, exchange rate and the oil price and etc. When adding all of the variables, that will make the degree of freedom problem and interaction problem between the variables.
This paper uses the principle component analysis to overcome the problem. And this paper uses Autoregressive model, Phillips curve model, and ordinary least square to compare with principle component analysis.
Most of the principle component analysis make more accurate to forecast in inflation.

參考文獻

Artis, M. J., Banerjee, A., Marcelino, M., 2001. Factor Forecasts for the UK. Journal of Forecasting 24, 279–298.

Atkeson and Ohanian, 2001. Can the Phillips Curve Help Forecast Inflation? Federal Reserve Bank of Minneapolis Quarterly Review, 25,2-11.

Bernanke, B., Boivin, J., 2003. Monetary Policy in a Data-rich Environment. Journal of Monetary Economics 50, 525–546.

Burdekin, R., Siklos, P., 2008. What has driven Chinese monetary policy since 1990s? Investigating the People's Bank's policy rule. Journal of International Money and Finance 27, 847–859.

Li,K. C., 1991. Sliced Inverse Regression for Dimension Reduction.Journal of the AmericanStatistical Association86, 316–327.