Testing Data Stationarity with Runs TestΒΆ

Non-Causal Step

This step applies the Runs Test algorithm to test whether a time-series is nonstationary in variance.

Input Parameters

  1. Input time-series data

Output Parameters

  1. Input time-series data
  2. Test result: stationary or nonstationary

Workflow

../../../../_images/workflow80.svg

Algorithm

Runs Test

References

  • I. Klevecka and J. Lelis, Pre-Processing of Input Data of Neural Networks: The Case of Forecasting Telecommunication Network Traffic, Telektronikk, vol. 3/4, pp. 168-178, 2008.