dorsal/arxiv
View SchemaLarge dimension forecasting models and random singular value spectra
| Authors | Jean-Philippe Bouchaud, Laurent Laloux, M. Augusta Miceli, Marc Potters |
|---|---|
| Categories | |
| ArXiv ID | physics/0512090 |
| URL | https://arxiv.org/abs/physics/0512090 |
Abstract
We present a general method to detect and extract from a finite time sample statistically meaningful correlations between input and output variables of large dimensionality. Our central result is derived from the theory of free random matrices, and gives an explicit expression for the interval where singular values are expected in the absence of any true correlations between the variables under study. Our result can be seen as the natural generalization of the Marcenko-Pastur distribution for the case of rectangular correlation matrices. We illustrate the interest of our method on a set of macroeconomic time series.
{
"annotation_id": "f62d02c8-57ef-40c9-8f98-60b06c4e87d4",
"date_created": "2026-03-02T18:01:03.344000Z",
"date_modified": "2026-03-02T18:01:03.344000Z",
"file_hash": "611c41ba6aad0b72cadb41ebcf0485481ba7b49c85fc2e40e49f9e4c077d30c1",
"private": false,
"record": {
"abstract": "We present a general method to detect and extract from a finite time sample\nstatistically meaningful correlations between input and output variables of\nlarge dimensionality. Our central result is derived from the theory of free\nrandom matrices, and gives an explicit expression for the interval where\nsingular values are expected in the absence of any true correlations between\nthe variables under study. Our result can be seen as the natural generalization\nof the Marcenko-Pastur distribution for the case of rectangular correlation\nmatrices. We illustrate the interest of our method on a set of macroeconomic\ntime series.",
"arxiv_id": "physics/0512090",
"authors": [
"Jean-Philippe Bouchaud",
"Laurent Laloux",
"M. Augusta Miceli",
"Marc Potters"
],
"categories": [
"physics.data-an",
"cond-mat.stat-mech",
"q-fin.ST"
],
"title": "Large dimension forecasting models and random singular value spectra",
"url": "https://arxiv.org/abs/physics/0512090"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "706e32f4-df05-4933-9762-76a74e74dfec",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}