Timeline for Simple algorithm for online outlier detection of a generic time series
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 13, 2023 at 15:29 | comment | added | whuber♦ | @TheGoat Yes: it's an ad hoc way of getting the analysis started at the beginning of the time series. | |
| May 13, 2023 at 9:43 | comment | added | TheGoat | @whuber thanks for the great post. Is the purpose of "z <- c(rep(z[1], window-1), z) # Use z[1] throughout the initial period" to impute for values 1:29 due to the rolling window being right aligned and producing a result at position 30? Have I understood that correctly? Thanks again | |
| Mar 6, 2020 at 10:20 | comment | added | COOLSerdash | I think a (slightly modified) approach using the MAD is also known under the term "Hampel identifier". | |
| Apr 13, 2017 at 12:44 | history | edited | CommunityBot |
replaced http://stats.stackexchange.com/ with https://stats.stackexchange.com/
|
|
| Oct 10, 2015 at 7:45 | comment | added | hgoebl | This is a really interesting solution and I appreciate that I can implement it without using R (just using plain JavaScript in a web application). Thanks! | |
| Sep 3, 2012 at 16:10 | history | edited | whuber♦ | CC BY-SA 3.0 |
added 206 characters in body
|
| Sep 3, 2012 at 16:09 | history | post merged (destination) | |||
| Sep 3, 2012 at 16:04 | history | edited | whuber♦ | CC BY-SA 3.0 |
added 151 characters in body
|
| Sep 3, 2012 at 15:57 | history | answered | whuber♦ | CC BY-SA 3.0 |