ftsa (version 4.4)

T_stationary: Testing stationarity of functional time series

Description

A hypothesis test for stationarity of functional time series.

Usage

T_stationary(sample, L = 49, J = 500, reps = 1000, seedlen = 50, 
		quan = c(0.9, 0.95), Ker1 = FALSE, Ker2 = TRUE)

Value

reject9THypothesis testing results at 90%. In the first column, the amount of the proportion of variation used for determining the number of components is 85%. In the second column, the amount of the proportion of variation used for determining the number of components is 95%. If a value is 0, this indicates non-stationarity of a functional time series for one repetition.reject95THypothesis testing results at 95%. In the first column, the amount of the proportion of variation used for determining the number of components is 85%. In the second column, the amount of the proportion of variation used for determining the number of components is 95%. If a value is 0, this indicates non-stationarity of a functional time series for one repetition.

Details

As in traditional (scalar and vector) time series analysis, the underlying assumption for inference in such models is stationarity. Stationarity is also required for functional dynamic regression models, for bootstrap and resampling methods for functional time series and for the functional analysis of volatility.

References

L. Horvath, P. Kokoszka, G. Rice (2014) "Testing stationarity of functional time series", Journal of Econometrics, 179, 66-82.

D. N. Politis (2003) "Adaptive bandwidth choice", Journal of Nonparametric Statistics, 25, 517-533.

See Also

farforecast

Examples

N = 50
sampling_points = 10
sample = matrix(0,sampling_points+1,N)
for(ss in c(1:N))
{
     sample[,ss] = BBridge(x = 0, y = 0, t0 = 0, T = 1, N = sampling_points)
}
dum = T_stationary(sample = sample, reps=10)