HIGHLIGHTS
- who: Jumps and colleagues from the rtmund University of Technology, Germany have published the article: Robust Shift Detection in Time-Varying Autoregressive Processes, in the Journal: (JOURNAL)
- what: The empirical 99.9% percentiles of the absolute test statistics will be used as critical values in the following since the authors aim at incorrect detection of a shift only once within 1000 time points on average.
SUMMARY
A basic objective of time series analysis is the estimation of the time-varying level (the signal) underlying the series. Running medians (Tukey, 1977) are . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.