#TITLE_ALTERNATIVE#
In the literature, different methods to obtain robust estimate of location and covariance matrix are available. One of the most popular and widely used is the so-called fast minimum covariance determinant (FMCD). However, it is computationally not efficient when the number of variables is large beca...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/11221 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | In the literature, different methods to obtain robust estimate of location and covariance matrix are available. One of the most popular and widely used is the so-called fast minimum covariance determinant (FMCD). However, it is computationally not efficient when the number of variables is large because it depends on the computation of the determinant and inverse of covariance matrix. To handle this obstacle, in this final project a study literature on FMCD and a simulation experiment on RH method proposed by our supervisor will be presented. Simulation result shows that RH method is more efficient than FMCD. <br />
<br />
|
|---|