Timeline for Removing anomalous points from data
Current License: CC BY-SA 4.0
19 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 11, 2019 at 17:49 | comment | added | JimB | Where does the subject matter come into the picture? I find it hard to believe that getting rid of "outliers" does not require any knowledge of the subject matter. Could it be that the dataset "with" the "outlier" is not the problem but rather the dataset "without" the "outlier" is the problem? | |
| Feb 11, 2019 at 16:50 | history | edited | Alexey Popkov |
edited tags
|
|
| Jan 20, 2019 at 15:00 | history | tweeted | twitter.com/StackMma/status/1087002034509889536 | ||
| Jan 17, 2019 at 16:04 | answer | added | Daniel Lichtblau | timeline score: 5 | |
| Jan 17, 2019 at 10:25 | history | edited | mrz | CC BY-SA 4.0 |
deleted 1169 characters in body
|
| Jan 17, 2019 at 10:19 | history | edited | mrz | CC BY-SA 4.0 |
deleted 1169 characters in body
|
| Jan 16, 2019 at 17:46 | answer | added | Anton Antonov | timeline score: 6 | |
| Jan 16, 2019 at 17:26 | comment | added | Daniel Lichtblau |
Basically yes. Could use Nearest functions from each set, checking that items in the other set come "close enough" to not be deleted as non-associates.
|
|
| Jan 16, 2019 at 16:30 | history | edited | mrz | CC BY-SA 4.0 |
added 150 characters in body
|
| Jan 16, 2019 at 16:17 | comment | added | mrz |
@Daniel Lichtblau: yes the distances between all points of data1 and of data2 should a measure to find and remove the marked points. Do you mean that?
|
|
| Jan 16, 2019 at 16:13 | history | edited | mrz | CC BY-SA 4.0 |
edited title
|
| Jan 16, 2019 at 16:05 | history | edited | mrz | CC BY-SA 4.0 |
edited title
|
| Jan 16, 2019 at 15:59 | history | edited | mrz | CC BY-SA 4.0 |
edited title
|
| Jan 16, 2019 at 15:55 | comment | added | Daniel Lichtblau |
Maybe rescale to have ommon x axes and then use Complement with some SameTest to allow for modest numeric differences?
|
|
| Jan 16, 2019 at 15:46 | history | edited | mrz | CC BY-SA 4.0 |
edited title
|
| Jan 16, 2019 at 13:55 | history | edited | m_goldberg | CC BY-SA 4.0 |
edited title
|
| Jan 16, 2019 at 12:07 | comment | added | mrz |
@Alex Trounev: Without the points wihich should be removed you can see from the uppermost two plots that the points of data1 (red) and data2 (blue) are scattered in the same "structure" with nearly same distances among each other in data1 and data2. In the example data2 are shifted to higher x coordinates and have also a small shift in y direction. The marked points have no "associated" partner points in the two plots. The shift in x and y could be also of the same size.
|
|
| Jan 16, 2019 at 11:45 | comment | added | Alex Trounev | How do you know which points should be removed? How did you find them? | |
| Jan 16, 2019 at 11:29 | history | asked | mrz | CC BY-SA 4.0 |