White noise tests.
an object, such as sample autocorrelations or partial autocorrelations.
the null hypothesis, currently "iid" or "garch".
additional arguments passed on to methods.
whiteNoiseTest carries out tests for white noise. The null
hypothesis is identified by argument
h0, based on which
whiteNoiseTest chooses a suitable function to call. The
functions implementing the tests are also available to be called
directly and their documentation should be consulted for further
arguments that are available.
h0 = "iid", the test statistics and rejection regions can be
use to test if the underlying time series is iid. Argument
method specifies the method for portmanteau tests: one of
"LiMcLeod" (default), "LjungBox", "BoxPierce".
h0 = "garch", the null hypothesis is that the time series is
GARCH, see Francq \& Zakoian (2010). The
tests in this case are based on a non-parametric estimate of the
asymptotic covariance matrix.
Portmonteau statistics and p-values are computed for the lags
specified by argument
nlags. If it is missing, suitable lags
are chosen automatically.
interval is TRUE, confidence intervals for the
individual autocorrelations or partial autocorrelations are computed.
a list with component
test and, if
Further methods will be added in the future.
Georgi N. Boshnakov
1 2 3 4 5 6 7 8 9 10 11 12 13
n <- 5000 x <- sarima:::rgarch1p1(n, alpha = 0.3, beta = 0.55, omega = 1, n.skip = 100) x.acf <- autocorrelations(x) x.pacf <- partialAutocorrelations(x) x.iid <- whiteNoiseTest(x.acf, h0 = "iid", nlags = c(5,10,20), x = x, method = "LiMcLeod") x.iid x.iid2 <- whiteNoiseTest(x.acf, h0 = "iid", nlags = c(5,10,20), x = x, method = "LjungBox") x.iid2 x.garch <- whiteNoiseTest(x.acf, h0 = "garch", nlags = c(5,10,20), x = x) x.garch
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.