我从这开始.
> auto.arima(mntm)
Series: mntm
ARIMA(2,0,0)(2,0,0)[12] with non-zero mean
Coefficients:
ar1 ar2 sar1 sar2 intercept
0.0966 0.0883 0.5115 0.4622 139.5995
s.e. 0.0365 0.0358 0.0316 0.0319 19.8640
sigma^2 estimated as 380.2: log likelihood=-3440.66
AIC=6893.32 AICc=6893.42 BIC=6921.27
接下来
> auto.arima(mntm, stepwise=FALSE, approximation=FALSE)
Series: mntm
ARIMA(4,0,1) with non-zero mean
Coefficients:
ar1 ar2 ar3 ar4 ma1 intercept
1.0353 -0.0871 -0.1914 -0.2790 -0.5642 133.7108
s.e. 0.0417 0.0541 0.0513 0.0394 0.0290 0.5935
sigma^2 estimated as 391.5: log likelihood=-3438.04
AIC=6890.07 AICc=6890.22 BIC=6922.69
不逐步= FALSE,逼近= FALSE牺牲时间以获得更准确的模型？
mntm显然是季节性的.
> …