dorsal/arxiv
View SchemaMultiscale reconstruction of time series
| Authors | A. P. Nawroth, J. Peinke |
|---|---|
| Categories | |
| ArXiv ID | physics/0608069 |
| URL | https://arxiv.org/abs/physics/0608069 |
| DOI | 10.1016/j.physleta.2006.08.024 |
Abstract
A new method is proposed which allows a reconstruction of time series based on higher order multiscale statistics given by a hierarchical process. This method is able to model the time series not only on a specific scale but for a range of scales. It is possible to generate complete new time series, or to model the next steps for a given sequence of data. The method itself is based on the joint probability density which can be extracted directly from given data, thus no estimation of parameters is necessary. The results of this approach are shown for a real world dataset, namely for turbulence. The unconditional and conditional probability densities of the original and reconstructed time series are compared and the ability to reproduce both is demonstrated. Therefore in the case of Markov properties the method proposed here is able to generate artificial time series with correct n-point statistics.
{
"annotation_id": "de23f8f2-0060-47a4-9d96-cd55aeac5d5e",
"date_created": "2026-03-02T18:01:10.966000Z",
"date_modified": "2026-03-02T18:01:10.966000Z",
"file_hash": "a21d86317f797cf3d3edbb36088a0a55a7e59e6e120a4b72dd88d6b180895b1c",
"private": false,
"record": {
"abstract": "A new method is proposed which allows a reconstruction of time series based\non higher order multiscale statistics given by a hierarchical process. This\nmethod is able to model the time series not only on a specific scale but for a\nrange of scales. It is possible to generate complete new time series, or to\nmodel the next steps for a given sequence of data. The method itself is based\non the joint probability density which can be extracted directly from given\ndata, thus no estimation of parameters is necessary. The results of this\napproach are shown for a real world dataset, namely for turbulence. The\nunconditional and conditional probability densities of the original and\nreconstructed time series are compared and the ability to reproduce both is\ndemonstrated. Therefore in the case of Markov properties the method proposed\nhere is able to generate artificial time series with correct n-point\nstatistics.",
"arxiv_id": "physics/0608069",
"authors": [
"A. P. Nawroth",
"J. Peinke"
],
"categories": [
"physics.data-an"
],
"doi": "10.1016/j.physleta.2006.08.024",
"title": "Multiscale reconstruction of time series",
"url": "https://arxiv.org/abs/physics/0608069"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "bd7fc000-b2df-4113-9adb-210d3d5f375b",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}