Nonstationary Daily Healthcare Stock Market Price using Non-Transformed Dimensionality Reduction Technique
Healthcare stock market price is usually nonstationary. General practice of handling nonstationary stock market price is through transformation process, which may cause loss of data originality. To overcome this, an alternative way of direct handling of the stock market price is of interest. The dimensionality reduction of nonstationary stock market price was performed by using generalized dynamic principal component (GDPC), adapting Brillinger dynamic principal component (BDPC) concept based on the reconstruction of the stock market price. Daily observations of healthcare stock market price were considered for this study. Stationarity test was carried out and the analysis were two-based, transformed and non-transformed. Then, three principal component methods were used to reduce the dimensionality. The results shows that GDPC have a higher percentage of explained variance percentage (above 90%) and lower mean squared error among the other methods. Thus, this shows that a direct application may also achieved better result performance.
Akaike, H. (1974). A new look at the statistical model identification. IEEE transactions on automatic control, 19(6), 716-723.
Androniceanu, A., Kinnunen, J., & Georgescu, I. (2021). Circular economy as a strategic option to promote sustainable economic growth and effective human development. Journal of International Studies, 14(1).
Andu, Y., Lee, M. H., & Algamal, Z. Y. (2019). Non-transformed Principal Component Technique on Weekly Construction Stock Market Price. MATEMATIKA: Malaysian Journal of Industrial and Applied Mathematics, 139-147.
Andu, Y., Lee, M. H., & Algamal, Z. Y. (2018). Generalized dynamic principal component for monthly nonstationary stock market price in technology sector. In Journal of Physics: Conference Series (Vol. 1132, No. 1, p. 012076). IOP Publishing.
Brillinger, D. R. (1981). Time Series: Data Analysis and Theory. San Francsico.
Brillinger, D. R. (1964). The asymptotic behaviour of Tukey's general method of setting approximate confidence limits (the jackknife) when applied to maximum likelihood estimates. Revue de l'Institut International de Statistique, 202-206.
Caporale, G. M., Gil-Alana, L. A., & Tripathy, T. (2020). Volatility persistence in the Russian stock market. Finance Research Letters, 32, 101216.
Crump, R. K., & Gospodinov, N. (2022). On the factor structure of bond returns. Econometrica, 90(1), 295-314.
Dickey, D. A., & Fuller, W. A. (1979). Distribution of the estimators for autoregressive time series with a unit root. Journal of the American statistical association, 74(366a), 427-431.
Kim, C. (2021). Deviance information criteria for mixtures of distributions. Communications in Statistics-Simulation and Computation, 50(10), 2935-2948.
Kwiatkowski, D., Phillips, P. C., Schmidt, P., & Shin, Y. (1992). Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root?. Journal of econometrics, 54(1-3), 159-178.
Peña, D., & Yohai, V. J. (2016). Generalized dynamic principal components. Journal of the American Statistical Association, 111(515), 1121-1131.
Phillips, P. C., & Perron, P. (1988). Testing for a unit root in time series regression. Biometrika, 75(2), 335-346.
Sánchez, M. Á., Trinidad, J. E., García, J., & Fernández, M. (2015). The effect of the underlying distribution in Hurst exponent estimation. PLoS One, 10(5), e0127824.
Worden, K., Iakovidis, I., & Cross, E. J. (2021). New results for the ADF statistic in nonstationary signal analysis with a view towards structural health monitoring. Mechanical Systems and Signal Processing, 146, 106979.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.