Robustness of score-driven location and scale models to extreme observations: An application to the Chinese stock market

Szabolcs Blazsek, Adrian Licht

Article ID: 699
Vol 3, Issue 1, 2020

VIEWS - 1005 (Abstract) 407 (PDF)

Abstract


Recently, the use of dynamic conditional score (DCS) time series models are suggested in the body of literature on time series econometrics. DCS models are robust to extreme observations because those observations are discounted by the score function that updates each dynamic equation. Examples of the DCS models are the quasi-autoregressive (QAR) model and the Beta-t-EGARCH (exponential generalized autoregressive conditional heteroscedasticity) model, which measure the dynamics of location and scale, respectively, of the dependent variable. Both QAR and Beta-t-EGARCH discount extreme observations according to a smooth form of trimming. Classical dynamic location and scale models (for example, the AR and the GARCH models) are sensitive to extreme observations. Thus, the AR and the GARCH modelsmay provide imprecise estimates of location and scale dynamics. In the application presented in this paper, we use data from the Shanghai Stock Exchange A-Share Index and the Shenzhen Stock Exchange A-Share Index for the period of 5th January 1998 to 29th December 2017. For the corresponding stock index return time series, a relatively high number of extreme values are observed during the sample period. We find that the statistical performance of QAR plus Beta-t-EGARCH is superior to that of AR plus t-GARCH, due to the robustness of QAR plus Beta-t-EGARCH to extreme unexpected returns.


Keywords


Dynamic conditional score (DCS) models; quasi-autoregressive (QAR) model; Beta-t-EGARCH (exponential generalized autoregressive conditional heteroscedasticity) model; robustness to extreme observations;Shanghai Stock Exchange A-Share Index; Shenzhen Stock

Full Text:

PDF


References


1. Ayala A, Blazsek S, Escribano A. Dynamic conditional score models with time-varying location, scale and shape parameters, Working Paper 17-08, Carlos III University of Madrid, Department of Economics, 2017.

2. https://e-archivo.uc3m.es/handle/10016/25043.

3. Blazsek S, Carrizo D, Eskildsen R, et al. Forecasting rate of return after extreme values when using AR-t-GARCH and QAR-Beta-t-EGARCH. Finance Research Letters 2018; 24: 193-198. doi: 10.1016/j.frl.2017.09.006.

4. Blazsek S, Chavez H, Mendez C. Model stability and forecast performance of Beta-t-EGARCH. Applied Economics Letters 2016; 23 (17): 1219-1223. doi: 10.1080/13504851.2016.1145343.

5. Blazsek S, Escribano A, Licht A. Score-driven nonlinear multivariate dynamic location models, Working Paper 17-14, Carlos III University of Madrid, Department of Economics, 2017. https://e-archivo.uc3m.es/handle/10016/25739.

6. Blazsek S, Escribano A, Licht A. Seasonal quasi-vector autoregressive models for macroeconomic data, Working Paper 18-03, Carlos III University of Madrid, Department of Economics, 2018.

7. https://e-archivo.uc3m.es/bitstream/handle/10016/26316/we1803.pdf

8. Blazsek S, Hernandez H. Analysis of electricity prices for Central American countries using dynamic conditional score models, Empirical Economics(forthcoming) 2017. doi: 10.1007/s00181-017-1341-3.

9. Blazsek S, Mendoza V. QARMA-Beta-t-EGARCH versus ARMA-GARCH: An application to S&P 500. Applied Economics 2016; 48 (12): 1119-1129. doi: 10.1080/00036846.2015.1093086.

10. Blazsek S, Monteros LA. Event-study analysis by using dynamic conditional score models. Applied Economics 2017; 49 (45): 4530–4541. doi: 10.1080/00036846.2017.1284996.

11. Blazsek S, Villatoro M. Is Beta-t-EGARCH(1,1) superior to GARCH(1,1)? Applied Economics 2015; 47 (17): 1764-1774. doi: 10.1080/00036846.2014.1000536.

12. Bollerslev T. Generalized autoregressive conditionalheteroscedasticity. Journal of Econometrics 1986; 31 (3): 307-327. doi:10.1016/0304-4076(86)90063-1.

13. Bollerslev T. A conditionally heteroskedastic time seriesmodel for speculative prices and rates of return. The Review of Economics and Statistics 1987; 69: 542-547. doi: 10.2307/1925546.

14. Box EP, Jenkins GM. Time Series Analysis: Forecasting and Control, Holden-Day, San Francisco, 1976.

15. Caivano M, Harvey AC. Time-series models with an EGB2 conditional distribution. Journal of Time Series Analysis 2014; 35 (6):558-571. doi: 10.1111/jtsa.12081.

16. Caivano M, Harvey AC, Luati A. Robust time series models with trend and seasonal components. SERIEs Journal of the Spanish Economic Association 2016; 7 (1): 99-120. doi: 10.1007/s13209-015-0134-1.

17. Carpenter JN, Lu F, Whitelaw RF. The real valueof China's stock market, NBER Working Paper 2018. no. 20957, http://www.nber.org/papers/w20957.

18. Creal, D., Koopman, S. J. and Lucas, A. (2013) Generalized autoregressivescore models with applications, Journal of Applied Econometrics 28 (5):777-795. doi:10.1002/jae.1279.

19. Davidson R, MacKinnon JG. Econometric Theory and Methods, Oxford University Press, New York, 2003.

20. Engle R. Autoregressive conditional heteroscedasticitywith estimates of the variance of United Kingdom inflation, Econometrica 1982; 50 (4): 987-1008. doi:10.2307/1912773.

21. Financial Times(2015a) FT Explainer: Why are China’sstock markets so volatile? Dominance of retail investors is one reason

22. for wild swings. Financial Times July 2, 2015, https://www.ft.com/content/e5af8da0-1fc7-11e5-aa5a-398b2169cf79.

23. Financial Times(2015b) Explainer: Margin finance in China.History of China's approach to trading with borrowed money. Financial Times January19, 2015, https://www.ft.com/content/7d667138-9fd3-11e4-aa89-00144feab7de.

24. Foucault T, Sraer D, Thesmar DJ. Individual Investorsand Volatility. The Journal of Finance 2011; 66 (4): 1369-1406.

25. doi: 10.1111/j.1540-6261.2011.01668.x.

26. Glosten LR, Jagannathan R, Runkle DE. On the relation between the expected value and the volatility of the nominal excess return on stocks. The Journal of Finance 1993; 48 (5): 1779-1801.

27. Harvey AC. Dynamic Models for Volatility and Heavy Tails, Cambridge University Press, Cambridge, 2013.

28. Harvey AC, Chakravarty T. Beta-t-(E)GARCH, CambridgeWorking Papers in Economics 0840, Faculty of Economics, University of Cambridge, Cambridge, 2008.

29. Hussain SI. Modelling Extreme Returns in Chinese StockMarket Using Extreme Value Theory and Copula Approach. Ph.D. thesis, RMIT University, 2016. https://researchbank.rmit.edu.au/eserv/rmit:161841/Hussain.pdf.

30. Jensen ST, Rahbek A. Asymptotic inference fornonstationary GARCH. Econometric Theory 2004; 20 (6): 1203-1226. doi: 10.1017/S0266466604206065.

31. Ljung GM, Box GEP. On a measure of a lack offit in time series models. Biometrika 1978; 65 (2): 297-303. doi: 10.2307/2335207.

32. Macquarie Research. Margin lending: The twilight zone(III). Macquarie Capital Securities Limited, A-Share Research 24 June 2015. https://www.macquarieresearch.com/rp/d/r/p/_MTAwOTUxMQ?u=MjE1Nzk.

33. Marszk A. The transformation of the Chinese stock marketbetween 1990 and 2012. International Business and Global Economy 2014; 33: 340-351, doi 10.4467/23539496IB.13.024.2409.

34. Taylor S. Modelling Financial Time Series, Wiley, Chichester, 1986.

35. Wong S. China's stock market: amarriage of capitalismand socialism. The Cato Journal 2006; 26 (3):389-424.

36. https://object.cato.org/sites/cato.org/files/serials/files/cato-journal/2006/11/cj26n3-1.pdf.

37. Xinhua (2015) Chinese stock volatility's family wealth impactlimited: CICC. Xinhua news agency, English on line edition 2014-07-20, 20:48:18. http://www.xinhuanet.com/english/2015-07/20/c_134429275.htm.




DOI: https://doi.org/10.24294/fsj.v3i1.699

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Creative Commons License

This site is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.