A new method for checking the stationarity of time series and making decisions about opening a short position
Abstract
Importance: weakly stationary random processes in the economy, implemented in the form of time series. Purpose: to improve the method of checking stationarity by the autocovariance function, to complement the method of checking stationarity by the mathematical expectation with the case of the mean value of the time series close to zero; to find examples of practical application of information about weak stationarity. Research design: was theoretical, mathematical and statistical in nature. The accuracy of the obtained results was verified using model and real examples of the time series, in particular, the example of the share quotations of Tatneft CJSC over a short period of time. Results: the new method for checking the time series for stationarity by the autocovariance function and the complemented method for checking stationarity by the mathematical expectation. The study of the problem of choosing the right moment to open a short position on the stock market has been conducted. Information about the stationarity by average values of stock or futures quotations is proposed to be used as an indicator for making decisions about opening a short position. This can help reduce risks for both traders and brokers when combined with technical analysis methods.
Downloads
References
2. Заико А.И. Эргодические случайные процессы. Определения и алгоритмы измерения характеристик // Вестник УГАТУ, 2012, т. 16, no. 6 (51), с. 74-85.
3. Зотьев Д.Б., Чернышова Д.И. Об эргодичности экономических процессов, представленных временными рядами. // Вестник Самарского университета. Экономика и управление, 2024, т. 15, no. 4, с. 45-62.
4. Мэрфи Д.Д. Технический анализ фьючерсных рынков: теория и практика. Пер. с англ.: Новицкая О., Сидоров В. Москва, Сокол, 1996. 592 с.
5. Яглом А.М. Корреляционная теория стационарных случайных функций. Ленинград, Гидрометеоиздат, 1981. 265 с.
6. Domowitz I., El-Gamal M.A. A consistent nonparametric test of ergodicity for time series with applications // Journal of Econometrics, 2001, vol. 102, no. 2, pp. 365-398.
7. Gimeno R., Manchado B., Minguez R. Stationarity tests for financial time series // Physica A: Statistical Mechanics and its Applications, Elsevier, 1999, v. 269, iss. 1, pp. 72-78.
8. Guo X., Wu C. Short Selling Activity and Effects on Financial Markets and Corporate Decisions // Encyclopedia of Finance, 2022, 3 ed., pp. 2313-2340.
9. Hongrui Wang, Cheng Wang, Yan Zhao, Xin Lin, Chen Yu Toward A Practical Approach for Ergodicity Analysis // Theoretical and Applied Climatology, 2019, vol. 138, nos. 3-4, pp. 1435-1444.
10. Jonathan K.A., Sampson T.-A., Kwasi B.G., Doris A., Wilhemina A.P. Evaluating the Performance of Unit Root Tests in Single Time Series Processes // Mathematics and Statistics, 2020, no. 8(6), pp. 656-664.
11. Markowitz H.M. Mean Variance Analysis in Portfolio Choice and Capital Markets. Oxford, Basil Blackwell, 1990. 387 p.
12. Morval G. and Weiss B. Forward estimation for ergodic time series // Ann. l’Institut Henri Poincare Probab. Stat, 2005, vol. 41, no. 5, pp. 859-870.
