Content deleted Content added
Undid revision 1129034308 by 132.187.253.29 (talk) rv latest decision stream spamming |
→Advantages: added findings from a literature review to demonstrate how these may be valuable for health research |
||
Line 307:
* Non-parametric approach that makes no assumptions of the training data or prediction residuals; e.g., no distributional, independence, or constant variance assumptions
* '''Performs well with large datasets.''' Large amounts of data can be analyzed using standard computing resources in reasonable time.
* '''Accuracy with flexible modeling'''. These methods may be applied to healthcare research with increased accuracy.<ref>{{Cite journal |last=Hu |first=Liangyuan |last2=Li |first2=Lihua |date=2022-12-01 |title=Using Tree-Based Machine Learning for Health Studies: Literature Review and Case Series |url=https://www.mdpi.com/1660-4601/19/23/16080 |journal=International Journal of Environmental Research and Public Health |language=en |volume=19 |issue=23 |pages=16080 |doi=10.3390/ijerph192316080 |issn=1660-4601 |pmc=PMC9736500 |pmid=36498153}}</ref>
* '''Mirrors human decision making more closely than other approaches.'''<ref name=":0" /> This could be useful when modeling human decisions/behavior.
*'''Robust against co-linearity, particularly boosting.'''
| |||