Timeline for Is this cluster analysis / prediction?
Current License: CC BY-SA 3.0
23 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 21, 2016 at 13:38 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Sep 21, 2016 at 13:17 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Aug 22, 2016 at 12:04 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jul 23, 2016 at 11:15 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jun 23, 2016 at 10:48 | answer | added | Sandeep S. Sandhu | timeline score: 1 | |
| Jun 20, 2016 at 17:18 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| May 21, 2016 at 16:48 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Mar 22, 2016 at 15:45 | answer | added | Marcus D | timeline score: 1 | |
| Mar 4, 2016 at 0:07 | comment | added | Emre | Not only Markovian models. | |
| Mar 4, 2016 at 0:05 | comment | added | user3791372 | what do you mean by "not just Markovian ones"? | |
| Mar 4, 2016 at 0:04 | comment | added | Emre | That's fine, but you will want more data than this to build a good model, and not just Markovian ones. | |
| Mar 3, 2016 at 23:44 | comment | added | user3791372 | Not three users but the same system at four different points in time, days apart. I'm assuming I need many more samples before being able to build a markov model for every possible state? | |
| Mar 3, 2016 at 23:11 | comment | added | Emre | Can the three tables be likened to three users, and you want to find event patterns across users and time? If so, I would try using a Markov model since the state space is well defined, and there is a temporal dimension. This would allow you predict the distribution (column) at the next moment. | |
| Mar 3, 2016 at 23:09 | comment | added | user3791372 | @Emre that's correct, the blue squares are an empty bucket, at that moment in time, and the white is the observation that the event took place at that moment for that value and so placed in that bucket. Each column represents a new sample with bucket values being reset to 0 | |
| Mar 3, 2016 at 22:27 | comment | added | Emre | What does each bucket in the y dimension contain; a real number? Do empty buckets mean there were no event/observation at that time? Do events "update" the state for the corresponding row (e.g., increment it)? | |
| Mar 3, 2016 at 22:25 | comment | added | user3791372 | @Emre x is time, and y is the value i'm trying to analyse and predict from the earlier samples. | |
| Mar 3, 2016 at 22:18 | comment | added | Emre | For each of the three tables, what do the x and y dimensions represent? Does its shape change over time? | |
| Mar 3, 2016 at 22:09 | comment | added | Has QUIT--Anony-Mousse | I don't see any clusters in your examples. If you want to answer this question, you will need to formalize it. I.e. what is a cluster, what is not a cluster. What would a random process generate? Then you can estimate or simulate random data to get thresholds. | |
| Mar 3, 2016 at 17:30 | history | edited | user3791372 | CC BY-SA 3.0 |
deleted 18 characters in body
|
| Mar 3, 2016 at 0:50 | history | edited | user3791372 | CC BY-SA 3.0 |
added 36 characters in body
|
| Mar 3, 2016 at 0:41 | history | edited | user3791372 | CC BY-SA 3.0 |
added 126 characters in body
|
| Mar 3, 2016 at 0:26 | history | edited | user3791372 | CC BY-SA 3.0 |
added 61 characters in body
|
| Mar 3, 2016 at 0:21 | history | asked | user3791372 | CC BY-SA 3.0 |