FitARMA {FitARMA} | R Documentation |
Fits an ARIMA(p,d,q) model using the algorithm given in McLeod and Zhang (2007).
FitARMA(z, order = c(0, 0, 0), demean = TRUE, MeanMLEQ = FALSE, pApprox = 30, MaxLag = 30)
z |
time series |
order |
model order, c(p,d,q) |
demean |
if TRUE, mean parameter included otherwise assumed zero |
MeanMLEQ |
exact MLE for mean, ignorned unless demean=TRUE |
pApprox |
order of approximation to be used |
MaxLag |
maximum number of lags for portmanteau test |
See McLeod and Ying (2007).
A list with class name "FitARMA" and components:
loglikelihood |
value of the loglikelihood |
phiHat |
AR coefficients |
thetaHat |
MA coefficients |
sigsqHat |
innovation variance estimate |
muHat |
estimate of the mean |
covHat |
covariance matrix of the coefficient estimates |
racf |
residual autocorrelations |
LjungBox |
table of Ljung-Box portmanteau test statistics |
res |
innovation residuals, same length as z |
fits |
fitted values, same length as z |
demean |
TRUE if mean estimated otherwise assumed zero |
IterationCount |
number of iterations in mean mle estimation |
convergence |
value returned by optim – should be 0 |
MLEMeanQ |
TRUE if mle for mean algorithm used |
tsp |
tsp(z) |
call |
result from match.call() showing how the function was called |
ModelTitle |
description of model |
DataTitle |
returns attr(z,"title") |
When d>0 and demean=TRUE, the mean of the differenced series is estimated. This corresponds to including a polynomial of degree d.
When d>0, the AIC/BIC are computed for the differenced series and so they are not comparable to the values obtained for models with d=0.
A.I. McLeod, aimcleod@uwo.ca
McLeod, A.I. and Zhang, Y. (2007, tentatively accepted). Faster ARMA Maximum Likelihood Estimation. Computational Statistics and Data Analysis.
GetFitARMA
,
print.FitARMA
,
coef.FitARMA
,
residuals.FitARMA
,
fitted.FitARMA
,
arima
data(SeriesA) out1<-FitARMA(SeriesA, c(1,0,1)) out1 coef(out1) out2<-FitARMA(SeriesA, c(0,1,1)) out2 coef(out2)