本研究使用S&P 500指數由1991年1月至2024年3月之價格資料，以及該期間的數個總體經濟數據，透過 SOP (Sum-of-the-part) 方法來建構股市報酬預測模型。研究發現reversion加上PLS的第一模型組合 (REPLS1) 在預測效能上表現最佳，遠超越過去傳統SOP方法的預測表現，而在Markowitz optimal weight的交易策略當中則是單純PLS模型表現最好，在使用7個主成分時Sharpe ratio達2.77
、確定等值 (certainty equivalent) 達48.67，同時發現MOP (momentum-of-predictability) 預測限制方法可以廣泛的改善所有的模型組合表現。總體而言，本研究的結果表明，過去的傳統SOP模型在近年的股市報酬預測表現已不如以往，甚至不論是在預測準確度於策略Sharpe ratio上皆略遜於基準模型 (歷史平均法)，不過在經過本研究中多個方法增強模型預測能力後發現SOP法仍能夠為較複雜的模型增加預測的效能，因此仍建議在預測股市報酬時採用 SOP 法的框架，除此之外，在本研究中發現REPLS1所有主成分模型組合於兩個子期間 (2016年~2019年、2020年~2024年) 皆可保持高水準的預測效果，不同於其他模型組合，在疫情與後疫情期間預測能力明顯減弱。

This study utilizes the price data of the S&P 500 Index from January 1991 to March 2024, along with several macroeconomic indicators during the same period, to construct a stock return prediction model using the Sum-of-the-Parts (SOP) method. The findings reveal that the first model combination of reversion and PLS (REPLS1) demonstrates the best predictive performance, significantly surpassing traditional SOP methods. In trading strategies based on Markowitz optimal weight, the pure PLS model performed the best, achieving a Sharpe ratio of 2.56 and a certainty equivalent of 48.67 when using eight principal components. Additionally, the Momentum-of-Predictability (MOP) restriction method was found to broadly enhance the performance of all model combinations. Overall, the results indicate that traditional SOP models have underperformed in recent years in terms of both predictive accuracy and strategy Sharpe ratio, even when compared to benchmark models such as historical averages. However, after enhancing the predictive capabilities of the SOP framework with the methods proposed in this study, SOP still proves to be beneficial for improving the performance of more complex models. Furthermore, it was found that the REPLS1 model combination with all principal components maintained high predictive performance in two subperiods (2016–2019 and 2020–2024), unlike other model combinations whose performance significantly declined during the pandemic and post-pandemic periods.

Ang, A., Hodrick, R. J., Xing, Y., & Zhang, X. (2007). Stock return predictability: Is it there? Review of Financial Studies, 20(3), 651–707.
Brandt, M. W., Kang, Q., & Santa-Clara, P. (2004). On the relationship between the conditional mean and volatility of stock returns: A latent VAR approach. Journal of Financial Economics, 72(2), 217–257.
Campbell, J. Y. (1987). Stock returns and the term structure. Journal of Financial Economics, 18(2), 373–399.
Campbell, J. Y., Giglio, S., Polk, C., & Turley, R. (2006). Efficient tests of stock return predictability. Journal of Financial Economics, 81(1), 27–60.
Clark, T. E., & McCracken, M. W. (2001). Tests of equal forecast accuracy and encompassing for nested models. Journal of Econometrics, 105(1), 85–110.
Fama, E. F., & French, K. R. (1988). Dividend yields and expected stock returns. Journal of Financial Economics, 22(1), 3–25.
Fama, E. F., & Schwert, G. W. (1977). Asset returns and inflation. Journal of Financial Economics, 5(2), 115–146.
Ferreira, M. A., & Santa-Clara, P. (2011). Forecasting stock market returns: The sum of the parts is more than the whole. Journal of Financial Economics, 100(3), 514–537.
Ghysels, E., Santa-Clara, P., & Valkanov, R. (2005). There is a risk-return trade-off after all. Journal of Financial Economics, 76(3), 509–548.
Kothari, S. P., Shanken, J., & Sloan, R. G. (1997). Book-to-market, dividend yield, and expected market returns: A time-series analysis. Journal of Financial Economics, 44(2), 169–203.
Lewellen, J. (2004). Predicting returns with financial ratios. Journal of Financial Economics, 74(2), 209–235.
Ludvigson, S. C., & Ng, S. (2007). The empirical risk-return relation: A factor analysis approach. Journal of Financial Economics, 83(1), 171–222.
Liu, C., Zhang, X., Nguyen, T. T., Liu, J., Wu, T., Lee, E., & Tu, X. M. (2022). Partial least squares regression and principal component analysis: Similarity and differences between two popular variable reduction approaches. General Psychiatry, 35(1), e100662.
McCracken, M. W. (2007). Asymptotic tests of predictive ability. Journal of Econometrics, 138(1), 291–311.
McCracken, M. W. (2007). Asymptotics for out-of-sample tests of Granger causality. Journal of Econometrics, 140(2), 719–752.
Meese, R. A., Rogoff, K. (1983). Empirical exchange rate models of the seventies: Do they fit out of sample? Journal of International Economics, 14(1–2), 3–24.
Pontiff, J., & Schall, L. D. (1998). Book-to-market ratios as predictors of market returns. Journal of Financial Economics, 49(2), 141–160.
Stambaugh, R. F. (1999). Predictive regressions. Journal of Financial Economics, 54(3), 375–421.
Valkanov, R. (2003). Long-horizon regressions: Theoretical results and applications. Journal of Financial Economics, 68(1), 201–232.
Wang, Y., Liu, L., Ma, F., & Diao, X. (2018). Momentum of return predictability. Journal of Empirical Finance, 45, 141–156.