因子的时间序列可预测性及其应用研究

本文使用基于宏观经济信息和金融市场的指标作为预测变量，研究了股票市场因子的超额收益与其方差的可预测性，通过组合预测方法验证了市场因子超额收益和方差的可预测性。本文进一步利用市场因子收益和方差的可预测性信息来构造动态的市场择时策略，发现该择时策略的超额收益不能被已有的多因子模型所解释。本文对该择时策略的收益来源进行分析。首先，本文通过构造三种择时策略，比较收益预测和方差预测的重要性。实证结果显示仅使用方差择时的择时策略表现较差，使用收益择时的择时策略表现更佳，而在收益预测的基础上加入方差预测的信息，所得的方差收益择时策略最有价值；因此，收益预测比方差预测在构造市场择时策略中更重要。其次，本文使用单一变量预测市场因子，构造择时策略，发现基于账面市值比、净权益增加率、生产者价格指数和换手率变量的择时策略也能在多个因子模型上产生显著为正的超额收益，说明这些变量可能是组合预测择时策略有价值的主要动因。
本文将预测对象从市场因子扩展到其他的定价因子，基于每个因子收益和方差的可预测性信息构造因子择时策略，并且检验择时策略的价值。实证结果表明盈利因子 ROE 和短周期行为因子 PEAD 的因子择时策略能在所有因子模型上产生显著为正的超额收益，并且因子收益预测的样本外R2与因子择时测略的alpha呈现正相关关系，但因子方差预测的样本外R2与因子择时策略的alpha并无显著正向关系。该结果进一步说明了在择时策略中，收益预测比方差预测更重要。本文的研究结果说明，因子的收益率和波动率存在可预测性，利用条件信息可以改进现有的因子模型，在实际投资中利用因子的可预测性信息也能帮助投资者构建更有价值的投资组合。

This paper investigates the predictability of the excess returns of the stock market factor and its variance using macroeconomic information and financial market-based indicators as predictor variables, and verifies the predictability of the market factor's excess returns and variance through a portfolio forecasting approach. The paper further uses the information on the predictability of market factor returns and variance to construct a dynamic market timing strategy and finds that the excess returns of this timing strategy cannot be explained by the existing multifactor model. This paper analyses the sources of returns of this time-timing strategy. First, the paper compares the importance of return forecasts and variance forecasts by constructing three time-timing strategies. The empirical results show that the timing strategy using only variance timing performs poorly, the timing strategy using earnings timing performs better, and the variance-earnings timing strategy obtained by adding information from variance forecasts to earnings forecasts is the most valuable; therefore, earnings forecasts are more important than variance forecasts in constructing a market timing strategy. Second, this paper constructs timing strategies using single-variable forecasts of market factors and finds that timing strategies based on the book-to-market ratio, net equity increase, producer price index, and turnover ratio variables also produce significantly positive excess returns on multiple-factor models, suggesting that these variables may be the main drivers of the value of the combined forecasting timing strategies.

This paper extends the forecasting object from the market factor to other pricing factors, constructs factor timing strategies based on information about the predictability of each factor's return and variance, and tests the value of the timing strategies. The empirical results show that the factor timing strategies for the profitability factor ROE and the short-period behavioural factor PEAD generate significantly positive excess returns on all factor models, and that the out-of-sample R2 of the factor return forecasts is positively related to the alpha of the factor timing strategy, but the out-of-sample R2s of the factor variance forecasts is not significantly positively related to the alphas of the factor timing strategy. This result further illustrates that return prediction is more important than variance prediction in time-timing strategies. The results of this paper illustrate that there is predictability in the return and volatility of factors, and the use of conditional information can improve the existing factor models, and the use of the predictability information of factors in actual investment can also help investors to construct more valuable investment portfolios.

[1] FAMA EF F K. Business conditions and expected returns on stocks and bonds[J]. Journal of Financial Economics, 1989: 25(21):23–49.
[2] KOTHARI S P, SHANKEN J. Book-to-market, dividend yield, and expected market returns: A time-series analysis[J]. Journal of Financial Economics, 1997, 44(2): 169-203.
[3] CAMPBELL J Y, SHILLER R J. The dividend-price ratio and expectations of future dividends and discount factors[J]. Review of Financial Studies, 1988, 1(3): 195-228.
[4] FAMA E F, SCHWERT G W. Asset returns and inflation[J]. Journal of Financial Economics, 1977, 5(2): 115-146.
[5] LETTAU M, LUDVIGSON S. Consumption, aggregate wealth, and expected stock returns[J]. Journal of Finance, 2001, 56(3): 815-849.
[6] BAKER M, WURGLER J. Investor sentiment and the cross-section of stock returns[J]. Journal of Finance, 2006, 61(4): 1645-1680.
[7] GUO H. On the out-of-sample predictability of stock market returns[J]. Journal of Business, 2006, 79(2): 645-670.
[8] COCHRANE J H. Presidential address: Discount rates[J]. The Journal of Finance, 2011, 66(4): 1047-1108.
[9] HARVEY C R, LIU Y, ZHU H. … and the cross-section of expected returns[J]. Review of Financial Studies, 2016, 29(1): 5-68.
[10] MOREIRA A, MUIR T. Volatility-managed portfolios[J]. Journal of Finance, 2017, 72(4): 1611-1644.
[11] HADDAD V, KOZAK S, SANTOSH S. Factor timing[J]. Review of Financial Studies, 2020, 33(5): 1980-2018.
[12] EHSANI S, LINNAINMAA J T. Factor momentum and the momentum factor[J]. Journal of Finance, 2022, 77(3): 1877-1919.
[13] NEUHIERL A, RANDL O, RESCHENHOFER C, ZECHNER J. Timing the factor zoo[J]. Available at SSRN, 2023.
[14] HOLLSTEIN F, PROKOPCZUK M. Managing the market portfolio[J]. Management Science, 2023, 69(6): 3675-3696.
[15] SUMMERS L H. Does the stock market rationally reflect fundamental values?[J]. Journal of Finance, 1986, 41(3): 591-601.
[16] FAMA E F, FRENCH K R. Permanent and temporary components of stock prices[J]. Journal of Political Economy, 1988, 96(2): 246-273.
[17] POTERBA J M, SUMMERS L H. Mean reversion in stock prices: Evidence and implications[J]. Journal of Financial Economics, 1988, 22(1): 27-59.
[18] LO A W, MACKINLAY A C. Stock market prices do not follow random walks: Evidence from a simple specification test[J]. Review of Financial Studies, 1988, 1(1): 41-66.
[19] FAMA E F, FRENCH K R. Dividend yields and expected stock returns[J]. Journal of Financial Economics, 1988, 22(1): 3-25.
[20] BOSSAERTS P, HILLION P. Implementing statistical criteria to select return forecasting models: What do we learn?[J]. Review of Financial Studies, 1999, 12(2): 405-428.
[21] RAPACH D E, STRAUSS J K, ZHOU G. Out-of-sample equity premium prediction: Combination forecasts and links to the real economy[J]. Review of Financial Studies, 2010, 23(2): 821-862.
[22] JORDAN S J, VIVIAN A J, WOHAR M E. Forecasting returns: New European evidence[J]. Journal of Empirical Finance, 2014, 26: 76-95.
[23] BAKER S R, BLOOM N, DAVIS S J. Measuring economic policy uncertainty[J]. Quarterly Journal of Economics, 2016, 131(4): 1593-1636.
[24] ANTONIOU C, DOUKAS J A, SUBRAHMANYAM A. Investor sentiment, beta, and the cost of equity capital[J]. Management Science, 2016, 62(2): 347-367.
[25] RAPACH D E, RINGGENBERG M C, ZHOU G. Short interest and aggregate stock returns[J]. Journal of Financial Economics, 2016, 121(1): 46-65.
[26] KELLY B, JIANG H. Tail risk and asset prices[J]. Review of Financial Studies, 2014, 27(10): 2841-2871.
[27] HOLLSTEIN F, NGUYEN D B B, PROKOPCZUK M, SIMEN C W. International tail risk and world fear[J]. Journal of International Money and Finance, 2019, 93: 244-259.
[28] BOLLERSLEV T, TAUCHEN G, ZHOU H. Expected stock returns and variance risk premia[J]. Review of Financial Studies, 2009, 22(11): 4463-4492.
[29] HOLLSTEIN F, SIMEN C W. Variance risk: A bird’s eye view[J]. Journal of Econometrics, 2020, 215(2): 517-535.
[30] ENGELBERG J, MCLEAN R D, PONTIFF J. Analysts and anomalies[J]. Journal of Accounting and Economics, 2020, 69(1): 101249.
[31] DONG X, LI Y, RAPACH D E, ZHOU G. Anomalies and the expected market return[J]. Journal of Finance, 2022, 77(1): 639-681.
[32] 闫冀楠, 张维. 上海股市 EMH 实证检验[J]. 系统工程学报, 1997(03): 51-58.
[33] 姜富伟, 凃俊, DAVID E.RAPACH, JACK K.STRAUSS, 周国富. 中国股票市场可预测性的实证研究[J]. 金融研究, 2011, (09): 107-121.
[34] GOH J C, JIANG F, TU J, WANG Y. Can US economic variables predict the Chinese stock market?[J]. Pacific-Basin Finance Journal, 2013, 22: 69-87.
[35] 陈坚, 张轶凡. 中国股票市场的已实现偏度与收益率预测[J]. 金融研究, 2018(09): 107-125.
[36] JIANG F, TANG G, ZHOU G. Firm characteristics and Chinese stocks[J]. Journal of Management Science and Engineering, 2018, 3(4): 259-283.
[37] 张琳, 张军, 王擎. 宏观经济信息发布对股票市场收益率及其波动的影响[J]. 系统工程理论与实践, 2020, 40(06): 1439-1451.
[38] 黄金波, 尤亦玲, 李仲飞. 基于前瞻信息的广义风险与收益率预测[J]. 管理科学学报, 2024, 27(03): 91-111.
[39] 周倜, 王云奇. 高阶矩风险与市场收益：来自中国期权市场的证据[J]. 管理科学学报, 2024, 27(05): 122-140.
[40] STAMBAUGH R F. Predictive regressions[J]. Journal of Financial Economics, 1999, 54(3): 375-421.
[41] GOYAL A, WELCH I. Predicting the equity premium with dividend ratios[J]. Management Science, 2003, 49(5): 639-654.
[42] WELCH I, GOYAL A. A comprehensive look at the empirical performance of equity premium prediction[J]. Review of Financial Studies, 2008, 21(4): 1455-1508.
[43] MARKOWITS H M. Portfolio selection[J]. Journal of Finance, 1952, 7(1): 71-91.
[44] SHARPE W F. Capital asset prices: A theory of market equilibrium under conditions of risk[J]. Journal of Finance, 1964, 19(3): 425-442.
[45] LINTNER J. Security prices, risk, and maximal gains from diversification[J]. Journal of Finance, 1965, 20(4): 587-615.
[46] MOSSIN J. Equilibrium in a capital asset market[J]. Econometrica: Journal of the Econometric Society, 1966: 768-783.
[47] BLACK F. Capital market equilibrium with restricted borrowing[J]. Journal of Business, 1972, 45(3): 444-455.
[48] BLUME M E, FRIEND I. A new look at the capital asset pricing model[J]. Journal of Finance, 1973, 28(1): 19-33.
[49] FAMA E F, MACBETH J D. Risk, return, and equilibrium: Empirical tests[J]. Journal of Political Economy, 1973, 81(3): 607-636.
[50] ROSS S A. Options and efficiency[J]. The Quarterly Journal of Economics, 1976, 90(1): 75-89.
[51] STATTMAN J. The creative trance: A unitive approach toward the phenomena of mental imagery in therapy[J]. Studies in Non-deterministic Psychology, 1980, 5: 95.
[52] BANZ R W. The relationship between return and market value of common stocks[J]. Journal of Financial Economics, 1981, 9(1): 3-18.
[53] FAMA E F, FRENCH K R. Common risk factors in the returns on stocks and bonds[J]. Journal of Financial Economics, 1993, 33(1): 3-56.
[54] CARHART M M. On persistence in mutual fund performance[J]. Journal of Finance, 1997, 52(1): 57-82.
[55] NOVY-MARX R. The other side of value: The gross profitability premium[J]. Journal of Financial Economics, 2013, 108(1): 1-28.
[56] HOU K, XUE C, ZHANG L. Digesting anomalies: An investment approach[J]. Review of Financial Studies, 2015, 28(3): 650-705.
[57] FAMA E F, FRENCH K R. A five-factor asset pricing model[J]. Journal of Financial Economics, 2015, 116(1): 1-22.
[58] STAMBAUGH R F, YUAN Y. Mispricing factors[J]. Review of Financial Studies, 2017, 30(4): 1270-1315.
[59] FAMA E F, FRENCH K R. Choosing factors[J]. Journal of Financial Economics, 2018, 128(2): 234-252.
[60] DANIEL K, HIRSHLEIFER D, SUN L. Short-and Long-Horizon Behavioral Factors[R]: National Bureau of Economic Research, 2018.
[61] HOU K, MO H, XUE C, ZHANG L. Which factors?[J]. Review of Finance, 2019, 23(1): 1-35.
[62] HOU K, MO H, XUE C, ZHANG L. An augmented q-factor model with expected growth[J]. Review of Finance, 2021, 25(1): 1-41.
[63] 陈浪南, 屈文洲. 资本资产定价模型的实证研究[J]. 经济研究, 2000(04): 26-34.
[64] 朱宝宪, 何治国. β值和帐面/市值比与股票收益关系的实证研究[J]. 金融研究, 2002(04): 71-79.
[65] 朱宝宪, 何治国. 中国股市小公司效应的实证研究[J]. 经济管理, 2001(10): 55-60.
[66] 杨炘, 陈展辉. 中国股市三因子资产定价模型实证研究[J]. 数量经济技术经济研究, 2003(12): 137-141.
[67] 潘莉, 徐建国. A 股市场的风险与特征因子[J]. 金融研究, 2011(10): 140-154.
[68] 欧阳志刚, 李飞. 四因子资产定价模型在中国股市的适用性研究[J]. 金融经济学研究, 2016, 31(02): 84-96.
[69] 赵胜民, 闫红蕾, 张凯. Fama-French 五因子模型比三因子模型更胜一筹吗——来自中国 A 股市场的经验证据[J]. 南开经济研究, 2016(02): 41-59.
[70] 李志冰, 杨光艺, 冯永昌, 景亮. Fama-French 五因子模型在中国股票市场的实证检验[J]. 金融研究, 2017(06): 191-206.
[71] LIU J, STAMBAUGH R F, YUAN Y. Size and value in China[J]. Journal of Financial Economics, 2019, 134(1): 48-69.
[72] DANIEL K, MOSKOWITZ T J. Momentum crashes[J]. Journal of Financial Economics, 2016, 122(2): 221-247.
[73] CHI Y, QIAO X, YAN S, DENG B. Volatility and returns: Evidence from China[J]. International Review of Finance, 2021, 21(4): 1441-1463.
[74] CAMPBELL J Y, THOMPSON S B. Predicting excess stock returns out of sample: Can anything beat the historical average?[J]. Review of Financial Studies, 2008, 21(4): 1509-1531.
[75] CLARK T E, WEST K D. Approximately normal tests for equal predictive accuracy in nested models[J]. Journal of Econometrics, 2007, 138(1): 291-311.
[76] NEWEY W K, WEST K D. A simple, positive semi-definite, heteroskedasticity and autocorrelationconsistent covariance matrix[J]. 1986.
[77] CAMPBELL J Y, LO A W, MACKINLAY A C, WHITELAW R F. The econometrics of financial markets[M]. Macroeconomic Dynamics, 1998, 2(4): 559-562.
[78] GUO H. Limited stock market participation and asset prices in a dynamic economy[J]. Journal of Financial and Quantitative Analysis, 2004, 39(3): 495-516.
[79] RAPACH D E, ZHOU G. Time-series and cross-sectional stock return forecasting: New machine learning methods[J]. Machine Learning for Asset Management: New Developments and Financial Applications, 2020: 1-33.