dorsal/arxiv
View SchemaImproving on the empirical covariance matrix using truncated PCA with white noise residuals
| Authors | Stephen Jewson |
|---|---|
| Categories | |
| ArXiv ID | physics/0506055 |
| URL | https://arxiv.org/abs/physics/0506055 |
Abstract
The empirical covariance matrix is not necessarily the best estimator for the population covariance matrix: we describe a simple method which gives better estimates in two examples. The method models the covariance matrix using truncated PCA with white noise residuals. Jack-knife cross-validation is used to find the truncation that maximises the out-of-sample likelihood score.
{
"annotation_id": "c35fbf5c-c621-4864-be40-44c49b9dd398",
"date_created": "2026-03-02T18:01:00.403000Z",
"date_modified": "2026-03-02T18:01:00.403000Z",
"file_hash": "fdb10f87d4e7847dda377606a67a5e4c43361968861f062718e8632e23ec9291",
"private": false,
"record": {
"abstract": "The empirical covariance matrix is not necessarily the best estimator for the\npopulation covariance matrix: we describe a simple method which gives better\nestimates in two examples. The method models the covariance matrix using\ntruncated PCA with white noise residuals. Jack-knife cross-validation is used\nto find the truncation that maximises the out-of-sample likelihood score.",
"arxiv_id": "physics/0506055",
"authors": [
"Stephen Jewson"
],
"categories": [
"physics.ao-ph"
],
"title": "Improving on the empirical covariance matrix using truncated PCA with white noise residuals",
"url": "https://arxiv.org/abs/physics/0506055"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "5c9c9a03-dc42-41b9-8ffc-c135027f0ad7",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}