Skip to main content

A study of total beta specification through symmetric regression: the case of the Johannesburg Stock Exchange

Abstract

A topic of recent interest is risk management in equity investments from emerging markets. One traditional measure for systematic risk of an asset is beta, which is constructed through ordinary least squares (OLS) regression between historical returns on an individual asset and an index representing the overall market. OLS regression assumes all the error lies within the asset returns. Tofallis (Eur J Oper Res 187(3):1358–1367, 2008) made the case for constructing a systematic risk measure through symmetric regression, where error is assumed to be present in the returns of both the asset and the index. In this paper, we construct a systematic risk measure using symmetric regression for the case of the Johannesburg Stock Exchange (JSE). This paper makes the case that the so-called ‘total beta’ parameter provides a more realistic and stable estimator for market-related risk and return. The total beta estimate, explicitly allowing for error in both variables, is less likely to underestimate the magnitude of the beta parameter.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Notes

  1. 1.

    In single-index model, such as the CAPM model, the idiosyncratic portion of firms’ returns are independent across firms. The diagonality assumption in a single-index model is that the errors between firms are not correlated.

  2. 2.

    While we have chosen the JSE in order to illustrate our work, this work is easily replicable for dichotomous markets such as the Australian and Canadian markets.

  3. 3.

    Tofallis (2015) shows analytical methods to obtain the regression coefficients exactly. Due to the timing of this paper, we followed Draper and Yang (1997).

  4. 4.

    We used the same measure as Francis (1979) as mentioned in Tofallis (2008).

  5. 5.

    It should be noted that consecutive periods in longer time frame scenario have more data in common that consecutive periods in a shorter time frame scenario.

  6. 6.

    The specification of the structural break points of the financial crisis in South Africa are reflective of tests, the results of which were forwarded in a private communication.

References

  1. Brown S (1989) The number of factors in security returns. J Financ 44(5):1247–1262

    Article  Google Scholar 

  2. Camp R, Eubank A (1985) The beta quotient: a new measure of portfolio risk. J Portf Manag 7(4):53–57

    Article  Google Scholar 

  3. Campbell G (1979) Risk and return on the Johannesburg stock exchange. Unpublished MBA thesis, Johannesburg: Department of Business Administration, University of the Witwatersrand

  4. Conway DA, Reinganum MR (1988). Stable factors in security returns: Identification using cross-validation. J Bus Econ Stat 6(1):1–15

    Google Scholar 

  5. Damodaran A (2002) Investment valuation, 2nd edn. Wiley, Hoboken

    Google Scholar 

  6. Datastream (2014) Thomson Reuters Datastream. Available at: Subscription Service. Accessed Aug 2014

  7. Dhrymes P, Friend I, Bultekin B (1984) A critical examination of the empirical evidence on the arbitrage pricing theory. J Financ 39:323–346

    Article  Google Scholar 

  8. Draper N, Yang Y (1997) Generalization of the geometric mean functional relationship. Comput Stat Data Anal 23:355–372

    Article  Google Scholar 

  9. Francis J (1979) Statistical analysis of risk surrogates for NYSE stocks. J Financ Quant Anal 14(05):981–997

    Article  Google Scholar 

  10. Gilbertson B, Goldberg M (1981) The market model and the Johannesburg stock exchange. Invest Anal J 17:40–42

    Google Scholar 

  11. Kruger R (2004) A framework for evaluating the benchmark risk of South African equity portfolios. Unpublished MBusSci thesis, University of Cape Town, unpublished MBusSci thesis

  12. Lintner J (1965) The valuation of risk assets and the selection of risky investments in stock portfolios and capital budgets. Rev Econ Stat 47(1):13–37

    Article  Google Scholar 

  13. McElroy M, Burmeister E (1988) Arbitrage pricing theory as as restrictive nonlinear multivariate regression model. J Bus Econ Stat 6(1):29–42

    Google Scholar 

  14. Mossin J (1966) Equilibrium in a capital asset market. Econometrica 34(4):768–783

    Article  Google Scholar 

  15. Nel W (2011) The application of the capital asset pricing model (CAPM): a South African perspective. Afr J Bus Manag 5(13):5336–5347

    Google Scholar 

  16. Noakes MA, Rajaratnam K (2014) Testing market efficiency on the johannesburg stock exchange using the overlapping serial test. Ann Oper Res 1–28. doi:10.1007/s10479-014-1751-y

  17. Page M (1986) Empirical testing of the arbitrage pricing theory using data from the Johannesburg stock exchange. S Afr J Bus Manag 17(1):38–42

    Google Scholar 

  18. Page M (1989) Model selection for measuring security price performance. S Afr J Bus Manag 17(1):78–81

    Google Scholar 

  19. Ross S (1976) The arbitrage theory of capital asset pricing. J Econ Theory 13:341–360

    Article  Google Scholar 

  20. Sharpe WF (1964) Capital asset prices: a theory of market equilibrium under conditions of risk. J Financ 19(3):425–442

    Google Scholar 

  21. Strugnell D, Gilbert E, Kruger R (2011) Beta, size and value effects on the JSE, 1994–2007. Invest Anal J 74:1–17

    Google Scholar 

  22. Tofallis C (2008) Investment volatility: a critique of standard beta estimation and a simple way forward. Eur J Oper Res 187(3):1358–1367

    Article  Google Scholar 

  23. Tofallis C (2015) Fitting equations to data with the perfect correlation relationship. Hertfordshire business school working paper

  24. van Rensburg P (2002) Market segmentation on the Johannesburg stock exchange II. J Stud Econ Econom 26(1):83–100

    Google Scholar 

  25. van Rensburg P, Robertson M (2003a) Size, price-to-earnings and beta on the JSE securities exchange. Invest Anal J 58:7–16

    Google Scholar 

  26. van Rensburg P, Slaney K (1997) Market segmentation on the Johannesburg stock exchange. J Stud Econ Econom 23(3):1–23

    Google Scholar 

  27. Ward M, Muller C (2012) Empirical testing of the CAPM on the JSE. Invest Anal J 76:1–12

    Google Scholar 

  28. Wisehart D (2010) Bostons battle of the beta. Financ Valuat Litig Expert 22:12–15

    Google Scholar 

Download references

Acknowledgments

This work is based on the research supported in part by the National Research Foundation (NRF) of South Africa for the Grant No. 93649. Any opinion, finding and conclusion or recommendation expressed in this material is that of the authors, and the NRF does not accept any liability in this regard. Additional funding was provided by the NWU-DST-ABSA Risk Research Initiative.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Kanshukan Rajaratnam.

Appendices

Appendix A

Table 4 Overall beta estimates

Appendix B

Table 5 Pre-crisis beta estimates

Appendix C

Table 6 Crisis beta estimates

Appendix D

Table 7 Post-crisis beta estimates

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Laird-Smith, J., Meyer, K. & Rajaratnam, K. A study of total beta specification through symmetric regression: the case of the Johannesburg Stock Exchange. Environ Syst Decis 36, 114–125 (2016). https://doi.org/10.1007/s10669-016-9596-3

Download citation

Keywords

  • CAPM
  • APT
  • JSE
  • Beta
  • Systematic risk
  • Reduced major axis regression