How do you interpret a changepoint graph?

Question

What is the correct way of interpreting a changepoint graph? Here is what R gives for changepoint analysis of the mean of a data set:

----------
Changepoint type      : Change in mean 
Method of analysis    : AMOC 
Assumed Distribution  : Normal 
Type of penalty       : SIC with value, 4.770685 
Maximum no. of cpts   : 1 
Changepoint Locations : 15 118 

So changes occurred at t=15 and t = 118?

Answer 1

If you are using the changepoint package (which from the output I presume you are) then the changepoint locations always end with n. Thus the length of your data is 118 and there is a single change in mean at 15.

For info AMOC means At Most One Change and thus the maximum number of changepoints the method will identify is 1. As 1 has been identified then you should use an alternative method, see documentation for options.

You mention a changepoint graph but as far as I can see from your question you haven't plotted anything. To see the results on the original series you can use

out<-cpt.mean(data)
plot(out)