Self-stationarity for individual sample records can be accepted as proof of stationarity.
Weak stationarity will be acceptable, thus the verification can be restricted to the mean values and autocorrelation functions (i.e., variance values) for the data.
1) Divide the sample record into N equal time interval.
2) Compute a mean value and mean square value for each interval,
3) Perform Run and Trend Tests
All data variables passed the run test (6 < r < 15).
Fy failed the trend test with A = 133.
The average r and A values for 12 repeat tests indicate that all data variables are stationary in a mean sense.
― x; ― x2
 |
 |
Heave motion zmm data failed both of run and trend tests with r = 4 and A = 129, respectively.
The average r and A values for 12 repeat tests indicate that all data variables are stationary in a mean sense.
― x; ― x2
 |
 |
