Part (B): Using R to show how to address issues of correlations between successive values of the time series. In many cases you can make a better predictive model by taking correlations in the data into account. We use a technique in Statistics called Autoregressive Integrated Moving Average (ARIMA) models for this irregular component of a time series.

This assignment is to practice using R to address autocorrelation issues. Please use the data set in "A Little of R for Time Series" ARIMA Models in section 2.6 (pp.45-57), the following data set is in page

> volcanodust <- scan("http://robjhyndman.com/tsdldata/annual/dvi.dat", skip=1)

> volcanodustseries <- ts(volcanodust,start=c(1500))

Then you can use the following to show how you can decompose the time series and then subtract the seasonal effect from the data:

Use acf(), pacf() and auto.arima() function show how to use R functions to address autocorrelation issues in data sets with insights.