Timeline for Random Forest and cluster-level bootstrapping
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 4, 2013 at 13:35 | comment | added | yoyo | I don't think it's possible. I think I will lost a lot of the information contained in my data | |
| Jul 2, 2013 at 17:47 | comment | added | Mina | I see. Could you just aggregate your data at the household level, so that each household is a sample, before modeling it? | |
| Jun 29, 2013 at 13:04 | comment | added | yoyo | Thank you for your answer. I don't think this option is appropriate for my problem. I think the "strata" and "sampsize" options are more appropriate with factor such as "sex" or "age class" to ensure that each class has the same probability to be sampled. Am I wrong ? My aim was to ensure that all individuals in a household are still part of the bootstrap sample used to construct each tree. Thank you | |
| Jun 28, 2013 at 16:39 | history | answered | Mina | CC BY-SA 3.0 |