Hi Vito, I would treat the residuals as a time series. You can fit an arima model to the residuals. For example:
data(nottem) temp<-stl(nottem, "per") my.arima<-arima(temp$time.series[,3], order=c(1,0,0), include.mean = FALSE) my.arima tsdiag(my.arima) If the ar1 term is significant then the residuals are auto-correlated. The DW statistic is just another test for this. The command tsdiag gives diagnostic plots for the arima model fit. In terms of heteroskedasticity, the Bruce-Pagan test from package lmtest tests for variance changing as a function of another variable. I think (although I am less sure) you can still use the test. To test whether your variance of residuals is monotonically increasing (or maybe decreasing) over time I would use: library(lmtest) Y<- as.numeric(temp$time.series[,3]) X<-1:nrow(temp$time.series) bptest(Y~X) Regards Wayne -----Original Message----- From: Vito Ricci [mailto:[EMAIL PROTECTED] Sent: 21 July 2004 08:35 To: [EMAIL PROTECTED] Subject: [R] Testing autocorrelation & heteroskedasticity of residuals in ts Hi, I'm dealing with time series. I usually use stl() to estimate trend, stagionality and residuals. I test for normality of residuals using shapiro.test(), but I can't test for autocorrelation and heteroskedasticity. Is there a way to perform Durbin-Watson test and Breusch-Pagan test (or other simalar tests) for time series? I find dwtest() and bptest() in the package lmtest, but it requieres an lm object, while I've a ts object. Any help will be appreciated. Best Vito ===== Diventare costruttori di soluzioni Visitate il portale http://www.modugno.it/ e in particolare la sezione su Palese http://www.modugno.it/archivio/cat_palese.shtml ______________________________________________ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html KSS Ltd Seventh Floor St James's Buildings 79 Oxford Street Manchester M1 6SS England Company Registration Number 2800886 Tel: +44 (0) 161 228 0040 Fax: +44 (0) 161 236 6305 mailto:[EMAIL PROTECTED] http://www.kssg.com The information in this Internet email is confidential and m...{{dropped}} ______________________________________________ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
