Library: | times |
See also: | roblm lobrob gph lo kpss rvlm pgram |
Quantlet: | robwhittle | |
Description: | Semiparametric Gaussian estimator of the degree of long memory of a time series, based on the Whittle estimator. The first argument is the series, the second argument is the vector of bandwidths, i.e., the number of frequencies after zero that are considered. By default, the bandwidth vector m = n/4, n/8, n/16, where n is the sample size. This quantlet displays the estimated parameter d, with the number of frequencies considered. |
Usage: | d = robwhittle(x{,bdvec}) | |
Input: | ||
x | vector | |
bdvec | vector of bandwidths | |
Output: | ||
d | vector |
;nonparametric estimation of degree of long-memory in volatility ;Since no vector of bandwidths is provided, the default vector of ;bandwidth parameter is used. library("times") x = read("dmus58.dat") x=x[1:1000] y = abs(tdiff(x)) d = robwhittle(y) d
Contents of d [1,] " d Bandwidth" [2,] "_____________________" [3,] "" [4,] " 0.0982 250" [5,] " 0.1200 125" [6,] " 0.0805 62"
;nonparametric estimation of degree of long-memory in volatility ;In this case, the vector of bandwidths m is provided library("times") x = read("dmus58.dat") x=x[1:1000] y = abs(tdiff(x)) m = #(50,100,150) d = robwhittle(y,m) d
Contents of d [1,] " d Bandwidth" [2,] "_____________________" [3,] "" [4,] " 0.0669 50" [5,] " 0.0940 100" [6,] " 0.1269 150"