本文的主要目的，是找出一個簡單且有效的方法，預測台灣的股市報酬。比較許多不同的研究後，我發現無論面對多重共線性亦或變動要素結構等問題，主要要素模型(Principal Components Analysis)都可以表現地比其他模型優異。因此，在此篇文章中，我結合了資產訂價理論(Asset Pricing Theory)與主要要素模型的概念，來預測台灣八大產業股票指數的報酬。分析結果顯示，雖然主要要素模型在本文中的預測表現不如預期，但是整體仍優於隨機漫步(Random Walk)的預測。這意味著，主要要素模型對台灣股市的預測，可以在某種程度上推翻效率市場假說(Efficient Market Hypothesis)。 / The original purpose of this paper is to find a useful and simple way to forecast the return rates of Taiwan stock market. Comparing different empirical studies, I found that no matter with problems of multicollinearity or changing factor structure, the Principal Components Analysis (PCA) can usually outperform other models. Therefore, I combined the concepts of Asset Pricing Theory (APT) and PCA, to predict the movements of eight industrial indexes return rates of Taiwan stock market. The analysis indicates that, although PCA forecasting results couldn’t be very impressive in Taiwan stock market, it still can perform better than Random Walk Regression. That means the forecasting results of PCA to Taiwan stock market can overthrow the Efficient Market Hypothesis (EMH), which represents the trends of stock return rates are unpredictable, to some extents.