Nonstationary Time Series in Financial Markets

  • A large proportion of financial data are nonstationary due to either time trend or unit root. An important tool to deal with nonstationary time series is cointegration, which transforms multiple nonstationary time series into a stationary one by linear combination. In contrast to simple difference, cointegration keeps the long-run characteristics of the data. Therefore, it is very popular when analyzing financial data.

     

    Literature:

    Lütkepohl, H. (2005). New introduction to multiple time series analysis. Springer Science & Business Media.

    Gatev, E., Goetzmann, W. N., & Rouwenhorst, K. G. (2006). Pairs trading: Performance of a relative-value arbitrage rule. Review of Financial Studies, 19(3), 797-827

    Hautsch, N., & Huang, R. (2012). The market impact of a limit order. Journal of Economic Dynamics and Control, 36(4), 501-522.

     

    Kontakt: Rebekka Buse