The ts Class

The ts class is used to represent time series data.
Packages for other classes of time series data, such as zoo or xts, can be downloaded and installed.

Suppose we want to create a ts object that represents turkey prices from January 2006 to April 2008. Use the ts function like this:

> prices <- c(1.71, 1.90, 1.68, 1.46, 1.86, 1.85, 
              1.88, 1.86, 1.62, 1.45, 0.67, 1.18,
              1.68, 1.74, 1.70, 1.49, 1.81, 1.96, 
              1.97, 1.91, 1.89, 1.65, 0.70, 1.17,
              1.76, 1.78, 1.53, 1.90)
> turkey.ts <- ts(prices, start=c(2006, 1), 
     end=c(2008, 4), frequency=12)
> turkey.ts
     Jan  Feb  Mar  Apr  May  Jun  Jul  Aug  Sep  Oct  Nov  Dec
2006 1.71 1.90 1.68 1.46 1.86 1.85 1.88 1.86 1.62 1.45 0.67 1.18
2007 1.68 1.74 1.70 1.49 1.81 1.96 1.97 1.91 1.89 1.65 0.70 1.17
2008 1.76 1.78 1.53 1.90

This timeseries object can now be plotted as plot(turkey.ts).

The time series parameters can be inspected with

> attributes(turkey.ts)
$tsp
[1] 2006.00 2008.25 12.00

$class
[1] "ts"

These parameters can also be inspected separately:

> start(turkey.ts)
[1] 2006 1
> end(turkey.ts)
[1] 2008 4
> frequency(turkey.ts)
[1] 12
> deltat(turkey.ts)
[1] 0.08333333

Here are two more functions that apply to ts objects:

> # Create a new ts object that lags 
> # the original by two time periods.
> lag(turkey.ts, 2)
     Jan  Feb  Mar  Apr  May  Jun  Jul  Aug  Sep  Oct  Nov  Dec
2005                                                   1.71 1.90
2006 1.68 1.46 1.86 1.85 1.88 1.86 1.62 1.45 0.67 1.18 1.68 1.74
2007 1.70 1.49 1.81 1.96 1.97 1.91 1.89 1.65 0.70 1.17 1.76 1.78
2008 1.53 1.90
> # Compute differences of successive observations.
> diff(turkey.ts)
      Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec
2006        0.19 -0.22 -0.22  0.40 -0.01  0.03 -0.02 -0.24 -0.17 -0.78  0.51
2007  0.50  0.06 -0.04 -0.21  0.32  0.15  0.01 -0.06 -0.02 -0.24 -0.95  0.47
2008  0.59  0.02 -0.25  0.37

Practice Problem: Create a ts timeseries object from this data: dow-jones.txt.