Abstract
Movements in stock returns arise from changes in expected future discount rates and cash-flow growth. However, which variables best proxy for these changes remains unknown. This chapter considers twenty-five variables arranged into five groups and examines both in-sample predictability and out-of-sample forecasting. Our variables span categories including financial ratios, macro-, labour market and housing variables as well as others, which incorporate measures of sentiment and leverage. Significant in-sample results occur across these five groups. Of note, price ratios, GDP acceleration, inflation, unemployment and consumer sentiment feature prominently. In conducting out-of-sample forecasts, we utilise a range of forecast performance measures and consider single model and combined forecasts. The results show that, with one exception, the combined model forecasts outperform the single model forecasts across all measures. This supports the view that a range of variables from across the economy can help predict future stock returns.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
Acceleration, whether economic growth is speeding up or slowing, is suggested to be more important than just growth itself.
- 4.
Of course, given the selected variables, there is likely to exist a degree of multicollinearity between the explanatory variables, indeed an examination of the variance inflation factors (not reported) would support this. However, the presence of multicollinearity is to increase the standard errors and thus reduce significance. Therefore, we are confident in the identified significant variables here.
- 5.
An explanation for the wrong sign on the cyclically adjusted price-to-earnings ratio is its high negative correlation with the dividend-price ratio (approx. −0.9) and reasonably high positive correlation with the price-to-earnings ratio (approx. 0.3). Removing these other variables does result in a negative coefficient on the cyclically adjusted price-to-earnings ratio, but also a statistically insignificant one.
References
Aiolfi, M., and A. Timmermann. 2006. Persistence of performance and combination strategies. Journal of Forecasting 24: 233–254.
Ang, A., and G. Bekaert. 2007. Stock return predictability: Is it there? Review of Financial Studies 20: 651–707.
Bali, T., K. Ozgur Demirtas, and H. Tehranian. 2008. Aggregate earnings firm level earnings, and expected stock returns. Journal of Financial and Quantitative Analysis 43: 657–684.
Black, A.J., O. Klinkowska, D.G. McMillan, and F.J. McMillan. 2014. Predicting: Do commodities prices help? Journal of Forecasting 33: 627–639.
Campbell, J.Y., and R.J. Shiller. 1988a. The dividend-price ratio and expectations of future and discount factors. Review of Financial Studies 1: 195–228.
Campbell, J.Y., and R.J. Shiller. 1988b. Stock prices, earnings, and expected dividends. Journal of Finance 43 (3): 661–676.
Campbell, J.Y., and S.B. Thompson. 2008. Predicting excess out of sample: Can anything beat the historical average? Review of Financial Studies 21: 1509–1531.
Cochrane, J. 2008. The dog that did not bark: A defense of return predictability. Review of Financial Studies 21: 1533–1575.
Cochrane, J. 2011. Discount rates: American finance association presidential address. Journal of Finance 66: 1047–1108.
Cooper, I., and R. Priestly. 2008. Time-varying risk premiums and the output gap. Review of Financial Studies 22: 2801–2833.
Cooper, I., and R. Priestley. 2013. The world business cycle and expected stock returns. Review of Finance 17: 1029–1064.
Goyal, A., and I. Welch. 2003. Predicting the equity premium with dividend ratios. Management Science 49: 639–654.
Hjalmarsson, E. 2010. Predicting global. Journal of Financial and Quantitative Analysis 45: 49–80.
Kellard, N.M., J.C. Nankervis, and F.I. Papadimitriou. 2010. Predicting the equity premium with dividend ratios: Reconciling the evidence. Journal of Empirical Finance 17: 539–551.
Lamont, O. 1998. Earnings and expected returns. Journal of Finance 53: 1563–1587.
Lettau, M., and S. Ludvigson. 2001. Consumption, aggregate wealth and expected. Journal of Finance 56: 815–849.
McMillan, D.G., and M.E. Wohar. 2010. Stock return predictability and dividend-price ratio: A nonlinear approach. International Journal of Finance and Economics 15: 351–365.
McMillan, D.G., and M.E. Wohar. 2013. A panel analysis of the stock return relation: Predicting returns and dividend growth. Manchester School 81: 386–400.
Narayan, P.K., and D. Bannigidadmath. 2015. Are Indian predictable? Journal of Banking & Finance 58: 506–531.
Pesaran, M.H., and A. Timmermann. 1995. Predictability of: Robustness and economic significancess. Journal of Finance 50: 1201–1228.
Pesaran, M.H., and A. Timmermann. 2000. A recursive modelling approach to predicting UK. Economic Journal 110: 159–191.
Phan, D.H.B., S.S. Sharma, and P.K. Narayan. 2015. Stock return: Some new evidence. International Review of Financial Analysis 40: 38–51.
Stock, J.H., and M. Watson. 2001. A comparison of linear and nonlinear univariate models for macroeconomic time series. In Festschrift in Honour of Clive Granger, ed. R.F. Engle and H. White, 1–44. Cambridge: Cambridge University Press.
Timmermann, A. 2006. Forecast combinations. Handbook of Economic Forecasting (Chapter 4). Elsevier: Netherlands.
Welch, I., and A. Goyal. 2008. A comprehensive look at the empirical performance of equity premium prediction. Review of Financial Studies 21: 1455–1508.
Author information
Authors and Affiliations
Corresponding author
Appendix—Data Series
Appendix—Data Series
Excess Stock Returns: First-difference of the log of S&P composite index minus the yield on a 3-month Treasury bill; source is Shiller and Federal Reserve.
Dividend-Price Ratio: the log of the dividend index minus the log of the price index; source is Shiller.
Price-Earnings Ratio: the log of the price index minus the log of the earnings index; source is Shiller.
Cyclically Adjusted Price-Earnings Ratio: as the price-earnings ratio except earnings are taken as a 10-year lagged moving average; source is Shiller.
Tobin’s Q: the ratio of the market value of a company’s of its outstanding stock and debt divided by the book value of the company’s assets; source is Federal Reserve.
Market Capitalisation to GDP: Ratio of total market capitalisation to GDP; source is the Federal Reserve (Wilshere 5000 Total Market Index to GDP).
GDP Cycle: Seasonally adjusted Real GDP detrended using the Hodrick-Prescott Filter; source is the Federal Reserve.
GDP Acceleration: The rate of change in GDP Growth, i.e. the second difference of logged GDP; source is the Federal Reserve.
Consumption Growth: The first-difference of the log of Personal Consumption; source is the Federal Reserve.
Term Structure: The difference between a 10-year Treasury bond and a 3-month Treasury bill; source is the Federal Reserve.
Inflation: The annualised rate of growth in the Consumer Price Index (CPI); source is the Federal Reserve.
Wage Growth: The first-difference of log wages; source is the Bureau of Labor Statistics.
Unemployment: The civilian unemployment rate; source is the Federal Reserve.
Natural Rate of Unemployment: Long-term natural rate of unemployment; source is the Federal Reserve.
Productivity Growth: The first-difference of log industrial productivity; source is Bureau of Labor Statistics.
Labour Market Conditions: The change in labour market conditions where a higher value denotes an improving labour market; source is the Federal Reserve.
House Price Growth: The first-difference of the all transactions house price index; source is the Federal Reserve.
House Price Affordability: National house affordability index where a higher value means housing is more affordable; source is National Association of Realtors.
Home Ownership: The home ownership rate is the proportion of households that are owner-occupied; source is Federal Reserve (from US Bureau of the Census).
Housing Supply: Monthly supply of houses as the ratio of houses for sale to houses sold; source is Federal Reserve (from US Bureau of the Census).
House Sales: New houses for sale; source is Federal Reserve (from US Bureau of the Census).
Consumer Sentiment: University of Michigan consumer sentiment index; source is Federal Reserve.
PMI: Purchasing Managers Index, a value above 50 indicates an expanding economy and a value below indicates a contracting economy; source is Federal Reserve (from Institute for Supply Management).
National Financial Conditions Index (NFCI): Chicago FED national financial conditions index where higher values (above zero) indicate tighter conditions (tighter than average) while lower (below zero) values indicate looser financial conditions (looser than average); source is Federal Reserve.
Leverage: Chicago FED national financial conditions leverage sub-index where higher values (above zero) indicate tighter conditions (tighter than average) while lower (below zero) values indicate looser financial conditions (looser than average); source is Federal Reserve.
Non-Financial Leverage: Chicago FED national financial conditions non-financial leverage sub-index where higher values (above zero) indicate tighter conditions (tighter than average) while lower (below zero) values indicate looser financial conditions (looser than average); source is Federal Reserve.
Rights and permissions
Copyright information
© 2018 The Author(s)
About this chapter
Cite this chapter
McMillan, D.G. (2018). Which Variables Predict and Forecast Stock Market Returns?. In: Predicting Stock Returns. Palgrave Pivot, Cham. https://doi.org/10.1007/978-3-319-69008-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-69008-7_5
Published:
Publisher Name: Palgrave Pivot, Cham
Print ISBN: 978-3-319-69007-0
Online ISBN: 978-3-319-69008-7
eBook Packages: Economics and FinanceEconomics and Finance (R0)