pear (version 0.1-2)

peplot: Periodic Correlation Visualization Plot

Description

In order to visualize dependence at lag k in a periodic series it is useful to plot z[t] vs z[t-k] for each period, m=1,2,...,p. For example in a monthly series we look at scatter plots of Jan vs Dec (previous year), Feb vs Jan, Mar vs Feb, etc. for the lag 1 plots.

Usage

peplot(z, lag=1, label=FALSE, mfrow=c(2, 2))

Arguments

z

a univariate time series object. Note that the period of z is given by attr(z, "tsp")[3]. Additional information about the time series can be provided in a title string by setting attr(z, "title") to the desired string. This title will then be displayed o

lag

lag separation

label

if label = TRUE, the Splus identify() function will be called allowing one to identify and label particular data points on the plots.

mfrow

Since many plots may be produced, the default is to produced 4 plots per page.

Value

• NULL

Side Effects

plot produced

Details

The importance of looking at these plots was noted by Cox (1981)

References

Cox, D.R. (1981), "Statistical Analysis of Time Series: Some Recent Developments", Scandinavian Journal of Statistics, Vol. 8, pp.93--115.

Examples

data(fraser)
peplot(log(fraser))