cross-correlation using ccf in R [closed]

问题

It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, visit the help center.

Closed 6 years ago.

I wanted to use ccf in R to compute the cross-correlation on two sets of time-series data. My question is how can I know if any of the correlation coefficients in the plot falls outside the dash blue lines without manually looking at it? Since I have tens of thousands sets of time-series data to deal with. Thanks in advance!

回答1:

Here is the way to calculate the confidence intervals:

res <- ccf(mdeaths, fdeaths, ylab = "cross-correlation")

upperCI <- qnorm((1 + 0.95)/2)/sqrt(res$n.used)
lowerCI <- -qnorm((1 + 0.95)/2)/sqrt(res$n.used)

However, help(plot.acf) warns:

The confidence interval plotted in plot.acf is based on an uncorrelated series and should be treated with appropriate caution. Using ci.type = "ma" may be less potentially misleading.

Look at getAnywhere(plot.acf) to learn how to calculate confidence intervals of type "ma".

来源：https://stackoverflow.com/questions/15551209/cross-correlation-using-ccf-in-r