Estimation of a CFAR process.
est_cfar(f, p = 3, df_b = 10, grid = 1000)The function returns a list with components:
the estimated spline coefficients for convolutional function values, a (2*grid+1)-by-p matrix.
the estimated convolutional function(s), a (df_b+1)-by-p matrix.
estimated rho for O-U process (noise process).
estimated sigma for O-U process (noise process).
the functional time series.
the CFAR order.
the degrees of freedom for natural cubic splines. Default is 10.
the number of gird points used to construct the functional time series and noise process. Default is 1000.
Liu, X., Xiao, H., and Chen, R. (2016) Convolutional autoregressive models for functional time series. Journal of Econometrics, 194, 263-282.