Hi everyone, I am performing the time series regression analysis on a series of data sets. A few data sets followed an ARMA(1,1) process. However, they all had a same value of moving average MA coefficients = -1, constantly, from output of function arima" . Example: > arima(residuals, order=c(1,0,1)) Call: arima(residuals, order = c(1, 0, 1)) Coefficients: ar1 ma1 intercept 0.3139 -1.0000 0e+00 s.e. 0.0871 0.0298 1e-04 sigma^2 estimated as 0.0002067: log likelihood = 336.72, aic = -665.43 > arima(residuals, order=c(2,1,1)) Call: arima(residuals, order = c(2,1, 1)) Coefficients: ar1 ar2 ma1 -0.4196 -0.3328 -1.0000 s.e. 0.0861 0.0857 0.0215 sigma^2 estimated as 0.0002529: log likelihood = 320.83, aic = -633.66 (a) Did this indicate a nonstationary/noninvertible process? (b) Did the algorithm converge? Would you trust the fit?? (c) What would you do next? Best, Ricardo
[[alternative HTML version deleted]]
______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.