DOI: 10.1190/1.1441091. Algorithms for least‐squares linear prediction and maximum entropy spectral analysis

Algorithms for least‐squares linear prediction and maximum entropy spectral analysis—Part I: Theory

10.1190/1.1441091

Crossref journal-article

Society of Exploration Geophysicists

GEOPHYSICS (186)

Abstract

Experience with the maximum entropy spectral analysis (MESA) method suggests that (1) it can produce inaccurate frequency estimates of short sample sinusoidal data, and (2) it sometimes produces calculated values for the filter coefficients that are unduly contaminated by rounding errors. Consequently, in this report we develop an algorithm for solving the underlying least‐squares linear prediction (LSLP) problem directly, without forcing a Toeplitz structure on the model. This approach leads to more accurate frequency determination for short sample harmonic processes, and our algorithm is computationally efficient and numerically stable. The algorithm can also be applied to two other versions of the linear prediction problem. A Fortran program is given in Part II.

Authors 2

I. Barrodale (first)
R. E. Erickson (additional)

References 0 Referenced 101

None

Dates

Type	When
Created	22 years, 10 months ago (Oct. 11, 2002, 2:50 p.m.)
Deposited	4 years, 10 months ago (Oct. 15, 2020, 5:24 p.m.)
Indexed	1 month, 4 weeks ago (July 4, 2025, 7:47 a.m.)
Issued	45 years, 6 months ago (March 1, 1980)
Published	45 years, 6 months ago (March 1, 1980)
Published Print	45 years, 6 months ago (March 1, 1980)

Funders 0

None

BibTeX

@article{Barrodale_1980, title={Algorithms for least‐squares linear prediction and maximum entropy spectral analysis—Part I: Theory}, volume={45}, ISSN={1942-2156}, url={http://dx.doi.org/10.1190/1.1441091}, DOI={10.1190/1.1441091}, number={3}, journal={GEOPHYSICS}, publisher={Society of Exploration Geophysicists}, author={Barrodale, I. and Erickson, R. E.}, year={1980}, month=mar, pages={420–432} }

JSON

{
  "indexed": {
    "date-parts": [
      [
        2025,
        7,
        4
      ]
    ],
    "date-time": "2025-07-04T11:47:46Z",
    "timestamp": 1751629666729
  },
  "reference-count": 0,
  "publisher": "Society of Exploration Geophysicists",
  "issue": "3",
  "content-domain": {
    "domain": [],
    "crossmark-restriction": false
  },
  "published-print": {
    "date-parts": [
      [
        1980,
        3
      ]
    ]
  },
  "abstract": "<jats:p> Experience with the maximum entropy spectral analysis (MESA) method suggests that (1) it can produce inaccurate frequency estimates of short sample sinusoidal data, and (2) it sometimes produces calculated values for the filter coefficients that are unduly contaminated by rounding errors. Consequently, in this report we develop an algorithm for solving the underlying least\u2010squares linear prediction (LSLP) problem directly, without forcing a Toeplitz structure on the model. This approach leads to more accurate frequency determination for short sample harmonic processes, and our algorithm is computationally efficient and numerically stable. The algorithm can also be applied to two other versions of the linear prediction problem. A Fortran program is given in Part II. </jats:p>",
  "DOI": "10.1190/1.1441091",
  "type": "journal-article",
  "created": {
    "date-parts": [
      [
        2002,
        10,
        11
      ]
    ],
    "date-time": "2002-10-11T18:50:24Z",
    "timestamp": 1034362224000
  },
  "page": "420-432",
  "source": "Crossref",
  "is-referenced-by-count": 101,
  "title": "Algorithms for least\u2010squares linear prediction and maximum entropy spectral analysis\u2014Part I: Theory",
  "prefix": "10.1190",
  "volume": "45",
  "author": [
    {
      "given": "I.",
      "family": "Barrodale",
      "sequence": "first",
      "affiliation": [
        {
          "name": "Department of Mathematics, University of Victoria, P.O. Box 1700, Victoria, B.C., Canada V8W 2Y2"
        }
      ]
    },
    {
      "given": "R. E.",
      "family": "Erickson",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Electromagnetics Section, Defence Research Establishment Pacific, FMO, CFB Esquimalt, Victoria, B. C., Canada V0S 1B0"
        }
      ]
    }
  ],
  "member": "186",
  "container-title": "GEOPHYSICS",
  "original-title": [],
  "language": "en",
  "link": [
    {
      "URL": "https://library.seg.org/doi/pdf/10.1190/1.1441091",
      "content-type": "unspecified",
      "content-version": "vor",
      "intended-application": "similarity-checking"
    }
  ],
  "deposited": {
    "date-parts": [
      [
        2020,
        10,
        15
      ]
    ],
    "date-time": "2020-10-15T21:24:19Z",
    "timestamp": 1602797059000
  },
  "score": 1,
  "resource": {
    "primary": {
      "URL": "https://library.seg.org/doi/10.1190/1.1441091"
    },
    "secondary": [
      {
        "URL": "http://geophysics.geoscienceworld.org/cgi/doi/10.1190/1.1441091",
        "label": "geoscienceworld"
      }
    ]
  },
  "subtitle": [],
  "short-title": [],
  "issued": {
    "date-parts": [
      [
        1980,
        3
      ]
    ]
  },
  "references-count": 0,
  "journal-issue": {
    "issue": "3",
    "published-print": {
      "date-parts": [
        [
          1980,
          3
        ]
      ]
    }
  },
  "alternative-id": [
    "10.1190/1.1441091"
  ],
  "URL": "http://dx.doi.org/10.1190/1.1441091",
  "relation": {},
  "ISSN": [
    "0016-8033",
    "1942-2156"
  ],
  "subject": [],
  "container-title-short": "GEOPHYSICS",
  "published": {
    "date-parts": [
      [
        1980,
        3
      ]
    ]
  }
}