Re: [R] Breakpoints and non linear regression

2012-11-09 Thread Thomas Coquet
Hello, I already tried and looked at the bfast package (very nice package by the way!) as I am working on VI time series as well. However, my model is definitely not linear, so in worst case scenario my idea was to use the bfast package to find the breakpoints (with the harmonic fit) and then to

Re: [R] Breakpoints and non linear regression

2012-11-09 Thread Achim Zeileis
On Fri, 9 Nov 2012, Thomas Coquet wrote: Hello, I already tried and looked at the bfast package (very nice package by the way!) as I am working on VI time series as well. Good! :-) However, my model is definitely not linear, Not even after taking logs or some other transformation? In prin

Re: [R] Breakpoints and non linear regression

2012-11-09 Thread Achim Zeileis
On Fri, 9 Nov 2012, thomas88 wrote: Hello, I have done some research about breakpoints (I am not a statistician) and I found out about the breakpoint, strucchange and segmented packages in R allowing to find breakpoints assuming linear model. However, I would like to fit a periodic time series