Skip to main content

Timeline for Detecting initial trend or outliers

Current License: CC BY-SA 3.0

9 events
when toggle format what by license comment
Oct 17, 2012 at 10:37 comment added Toby Kelsey They are different systems. Although they are similar they all differ significantly and I can't assume any parameters are the same between them.
Oct 15, 2012 at 16:23 comment added whuber What, if anything, is common to each of the 15 or so runs? E.g., are they all measuring the same system? If not, are there some parameters you expect to remain the same between runs? I think it might be possible to "borrow strength" for outlier detection by suitably combining all data into one dataset, rather than viewing it as 15 separate datasets, and thereby overcome the pessimistic views expressed in comments elsewhere in this thread.
Oct 3, 2012 at 7:18 vote accept Toby Kelsey
Oct 2, 2012 at 9:18 history edited Toby Kelsey CC BY-SA 3.0
minor edit
Oct 2, 2012 at 8:45 history edited Toby Kelsey CC BY-SA 3.0
more details about hte processs
Oct 1, 2012 at 18:31 answer added Michael R. Chernick timeline score: 3
Oct 1, 2012 at 17:08 answer added IrishStat timeline score: 0
Oct 1, 2012 at 13:48 review First posts
Oct 1, 2012 at 14:20
Oct 1, 2012 at 13:43 history asked Toby Kelsey CC BY-SA 3.0