A note on the predictability of the russian stock market

Reviewing the economic literature related to the stock market forecasting, we have arrived at the conclusion that the numerous approaches and studies can be grouped under the two main opposing viewpoints: (1) there are certain indicators that predict the future returns of the stock market under particular conditions; (2) the stock market prices are already adjusted to all the currently available information; therefore, the future stock price is unpredictable.

As regards the Russian stock market, it has been found that the impact of oil prices on the Russian stock market performance is weak and not regular, as confirmed by numerous authors. In fact, the oil price is not a significant predictor from 2006 onwards. However, dependence of the Russian stock market on foreign exchanges, such as the U.S. or German exchanges, was proved.

Testing the predictability of stock returns with the linear regression estimated by OLS, we have identified three out of nine industries and five out of eight macroeconomic indicators as significant predictors. The significant predictors (except for oil prices in U.S. dollars) have a positive impact on MICEX.

Through the out-of-sample analysis (of the last three observed years), it was found that all models based on significant predictors have higher MSFE than the model rested upon the historical mean (i.e., a negative pseudo-R2). This implies that prediction based on models underperforms prediction based on the historical mean.

Estimating the mean-variance investor's utility gains of using predictive models, we have revealed positive utility gains in two out of nine models based on the chemical industry and the dividend yield.

In our research, we have applied an industry-specific and macroeconomic approach to forecasting the Russian stock market for the first time. The results of our study are partly stipulated by the complicatedness of predicting stock market, in general, and by the problems inherent to the Russian stock market. Due to the lack of available data, the time period under study was constrained to a 7-year period for in-sample and a 3-year period for out-of-sample analysis, which is shorter compared to the 20-year period of the full sample. Consequently, the lack of data as well as the high market volatility and uncertainty associated with political and economic shocks (crises) may be partly responsible for the reduced predictive ability of models that we registered in the out-of-sample period.

Apparently, it is really difficult to predict the stock market movement. Employing only a separate conventional macroeconomic indicator or industry portfolio as a predictor, an analyst encounters the fact that not many of these predictors have predictive power. As a rule, implementation of predictive models based on traditional methods (e.g., predictive linear regression) without additional constraints or conditions and techniques fails to outperform the historical mean out of sample.

The open data accessibility for the forecasting model applied in our research weakens by the complexity and longtime calculations for the private investor, as well as by the large deviation of the model's forecast values from real economic values. Given that, we suppose that, for a private investor, it is easier and more proper to use the moving average method for forecasting and making an investment decision.

As for our model, taking the stated complications into account, we intend to continue our research. The following tasks are to be performed:

- Testing various constraints applicable to the existing OLS models (e.g., positive returns restrictions).

Calculating the index of the Russian stock market performance (in lieu of MICEX) because it comprises a greater number of Russian shares; thus, it is a more relevant base indicator of a new prediction model.

Extending the range of predictor indicators that have a significant impact on the Russian stock market.

Adopting other approaches to predicting the stock market (e.g., the GARCH (generalized autoregressive conditional heteroscedasticity model) model, which is superior to OLS in terms of the quality of prediction).

References

Danilova, T. & Danilova, M. (2010) Comparative analysis of household savings and investment decisions in the country context. Economic Analysis: Theory and Practice. 36(210). pp. 6-11. (In Russian).

Fama, F. (1989) Business conditions and expected returns on stocks and bonds. Journal of Financial Economics. 25(1). pp. 23-49.

Campbell, J. & Thompson, S. (2008) Predicting excess stock returns out of sample: Can anything beat the historical average? Review of Financial Studies. 21(4). pp. 1509-1531.

Rapach, D., Strauss, J. & Zhou, G. (2010) Out-of-sample equity premium prediction: Combination forecasts and links to the real economy. Review of Financial Studies. 23(2). pp. 821-862.

Pettenuzzo, D., Timmermann, A. & Valkanov, R. (2014) Forecasting stock returns under economic constraints. Journal of Financial Economics. 114(3). pp. 517-553.

Pцnkд, H. (2014) Predicting the direction of US stock markets using industry returns. HECER Discussion Paper. 385. pp. 1-16.

Govorkov, B. (2016) Forecasting stock market returns over multiple time horizons. Quantitative Finance. 16(11). pp. 1695-1712.

Anatolyev, S. (2008) A 10-year retrospective on the determinants of Russian stock returns. Research in International Business and Finance. 22(1). pp. 56-67.

Kutan, A. & Hayo, B. (2005) The impact of news, oil prices, and global market developments on Russian financial markets. Economics of Transition. 13(2). pp. 373-393.

Hong, H., Torous, W. & Valkanov, R. (2007) Do industries lead the stock market? Journal of Financial Economics. 83. pp. 367-396.

Ferreira, M. & Santa-Clara, P. (2011) Forecasting stock market returns: The sum of the parts is more than the whole. Journal of Financial Economics. 100(3). pp. 514-537. predictability market stock

Neely, C. (2014) Forecasting the Equity Risk Premium: The Role of Technical Indicators. Management Science. 60(7). pp. 1772-1791.

Kinnunen, J. (2013) Dynamic return predictability in the Russian stock market. Emerging Markets Review. 15. pp. 107-121.

OECD. (2017) Data of the OECD. [Online] Available from: https://data.oecd.org. (Accessed: 12.03.2017).

Cbonds. (2019) Indices of bond market. [Online] Available from:

http://cbonds.ru/indexes. (Accessed: 15.03.2019).

Moscow Exchange. (2019) Moscow Exchange indices. [Online] Available from: http://moex.com/en/indices. (Accessed: 17.03.2019).

Размещено на Allbest.ru