dorsal/arxiv
View SchemaA method for extracting the scaling exponents of a self-affine, non-Gaussian process from a finite length timeseries
| Authors | K. Kiyani, S. C. Chapman, B. Hnat |
|---|---|
| Categories | |
| ArXiv ID | physics/0607238 |
| URL | https://arxiv.org/abs/physics/0607238 |
| DOI | 10.1103/PhysRevE.74.051122 |
| Journal | Phys. Rev. E 74, 051122 (2006) |
Abstract
We address the generic problem of extracting the scaling exponents of a stationary, self-affine process realised by a timeseries of finite length, where information about the process is not known a priori. Estimating the scaling exponents relies upon estimating the moments, or more typically structure functions, of the probability density of the differenced timeseries. If the probability density is heavy tailed, outliers strongly influence the scaling behaviour of the moments. From an operational point of view, we wish to recover the scaling exponents of the underlying process by excluding a minimal population of these outliers. We test these ideas on a synthetically generated symmetric alpha-stable Levy process and show that the Levy exponent is recovered in up to the 6th order moment after only ~0.1-0.5% of the data are excluded. The scaling properties of the excluded outliers can then be tested to provide additional information about the system.
{
"annotation_id": "0fad911c-477e-4849-a155-1ea3752704f6",
"date_created": "2026-03-02T18:01:10.912000Z",
"date_modified": "2026-03-02T18:01:10.912000Z",
"file_hash": "5c99a6b3e66055b60a1920068bf3b10ebdbcf45cdfd4505052cd716078f194f0",
"private": false,
"record": {
"abstract": "We address the generic problem of extracting the scaling exponents of a\nstationary, self-affine process realised by a timeseries of finite length,\nwhere information about the process is not known a priori. Estimating the\nscaling exponents relies upon estimating the moments, or more typically\nstructure functions, of the probability density of the differenced timeseries.\nIf the probability density is heavy tailed, outliers strongly influence the\nscaling behaviour of the moments. From an operational point of view, we wish to\nrecover the scaling exponents of the underlying process by excluding a minimal\npopulation of these outliers. We test these ideas on a synthetically generated\nsymmetric alpha-stable Levy process and show that the Levy exponent is\nrecovered in up to the 6th order moment after only ~0.1-0.5% of the data are\nexcluded. The scaling properties of the excluded outliers can then be tested to\nprovide additional information about the system.",
"arxiv_id": "physics/0607238",
"authors": [
"K. Kiyani",
"S. C. Chapman",
"B. Hnat"
],
"categories": [
"physics.data-an",
"physics.gen-ph"
],
"doi": "10.1103/PhysRevE.74.051122",
"journal_ref": "Phys. Rev. E 74, 051122 (2006)",
"title": "A method for extracting the scaling exponents of a self-affine, non-Gaussian process from a finite length timeseries",
"url": "https://arxiv.org/abs/physics/0607238"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "5980c3ee-489d-45f1-9d96-f1953cc0b53d",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}