Bayesian nonparametric spectral density estimation using B-spline priors View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2018-01-12

AUTHORS

Matthew C. Edwards, Renate Meyer, Nelson Christensen

ABSTRACT

We present a new Bayesian nonparametric approach to estimating the spectral density of a stationary time series. A nonparametric prior based on a mixture of B-spline distributions is specified and can be regarded as a generalization of the Bernstein polynomial prior of Petrone (Scand J Stat 26:373–393, 1999a; Can J Stat 27:105–126, 1999b) and Choudhuri et al. (J Am Stat Assoc 99(468):1050–1059, 2004). Whittle’s likelihood approximation is used to obtain the pseudo-posterior distribution. This method allows for a data-driven choice of the number of mixture components and the location of knots. Posterior samples are obtained using a Metropolis-within-Gibbs Markov chain Monte Carlo algorithm, and mixing is improved using parallel tempering. We conduct a simulation study to demonstrate that for complicated spectral densities, the B-spline prior provides more accurate Monte Carlo estimates in terms of L1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$L_1$$\end{document}-error and uniform coverage probabilities than the Bernstein polynomial prior. We apply the algorithm to annual mean sunspot data to estimate the solar cycle. Finally, we demonstrate the algorithm’s ability to estimate a spectral density with sharp features, using real gravitational wave detector data from LIGO’s sixth science run, recoloured to match the Advanced LIGO target sensitivity. More... »

PAGES

67-78

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s11222-017-9796-9

DOI

http://dx.doi.org/10.1007/s11222-017-9796-9

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1100349076


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Physics and Astronomy, Carleton College, Northfield, MN, USA", 
          "id": "http://www.grid.ac/institutes/grid.253692.9", 
          "name": [
            "Department of Statistics, University of Auckland, Auckland, New Zealand", 
            "Physics and Astronomy, Carleton College, Northfield, MN, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Edwards", 
        "givenName": "Matthew C.", 
        "id": "sg:person.016041213011.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016041213011.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Statistics, University of Auckland, Auckland, New Zealand", 
          "id": "http://www.grid.ac/institutes/grid.9654.e", 
          "name": [
            "Department of Statistics, University of Auckland, Auckland, New Zealand"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Meyer", 
        "givenName": "Renate", 
        "id": "sg:person.010133522211.66", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010133522211.66"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Artemis, Universit\u00e9 C\u00f4te d\u2019Azur, Observatoire de C\u00f4te d\u2019Azur, CNRS, Nice, France", 
          "id": "http://www.grid.ac/institutes/grid.503124.1", 
          "name": [
            "Physics and Astronomy, Carleton College, Northfield, MN, USA", 
            "Artemis, Universit\u00e9 C\u00f4te d\u2019Azur, Observatoire de C\u00f4te d\u2019Azur, CNRS, Nice, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Christensen", 
        "givenName": "Nelson", 
        "id": "sg:person.0607020230.86", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0607020230.86"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s13571-011-0014-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010395105", 
          "https://doi.org/10.1007/s13571-011-0014-z"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4419-0320-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034653958", 
          "https://doi.org/10.1007/978-1-4419-0320-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4020-5614-7_3515", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031013171", 
          "https://doi.org/10.1007/978-1-4020-5614-7_3515"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11336-013-9354-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036633529", 
          "https://doi.org/10.1007/s11336-013-9354-0"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2018-01-12", 
    "datePublishedReg": "2018-01-12", 
    "description": "We present a new Bayesian nonparametric approach to estimating the spectral density of a stationary time series. A nonparametric prior based on a mixture of B-spline distributions is specified and can be regarded as a generalization of the Bernstein polynomial prior of Petrone (Scand J Stat 26:373\u2013393, 1999a; Can J Stat 27:105\u2013126, 1999b) and Choudhuri et al. (J Am Stat Assoc 99(468):1050\u20131059, 2004). Whittle\u2019s likelihood approximation is used to obtain the pseudo-posterior distribution. This method allows for a data-driven choice of the number of mixture components and the location of knots. Posterior samples are obtained using a Metropolis-within-Gibbs Markov chain Monte Carlo algorithm, and mixing is improved using parallel tempering. We conduct a simulation study to demonstrate that for complicated spectral densities, the B-spline prior provides more accurate Monte Carlo estimates in terms of L1\\documentclass[12pt]{minimal}\n\t\t\t\t\\usepackage{amsmath}\n\t\t\t\t\\usepackage{wasysym}\n\t\t\t\t\\usepackage{amsfonts}\n\t\t\t\t\\usepackage{amssymb}\n\t\t\t\t\\usepackage{amsbsy}\n\t\t\t\t\\usepackage{mathrsfs}\n\t\t\t\t\\usepackage{upgreek}\n\t\t\t\t\\setlength{\\oddsidemargin}{-69pt}\n\t\t\t\t\\begin{document}$$L_1$$\\end{document}-error and uniform coverage probabilities than the Bernstein polynomial prior. We apply the algorithm to annual mean sunspot data to estimate the solar cycle. Finally, we demonstrate the algorithm\u2019s ability to estimate a spectral density with sharp features, using real gravitational wave detector data from LIGO\u2019s sixth science run, recoloured to match the Advanced LIGO target sensitivity.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s11222-017-9796-9", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isFundedItemOf": [
      {
        "id": "sg:grant.3934184", 
        "type": "MonetaryGrant"
      }, 
      {
        "id": "sg:grant.5063789", 
        "type": "MonetaryGrant"
      }
    ], 
    "isPartOf": [
      {
        "id": "sg:journal.1327447", 
        "issn": [
          "0960-3174", 
          "1573-1375"
        ], 
        "name": "Statistics and Computing", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "29"
      }
    ], 
    "keywords": [
      "likelihood approximation", 
      "Bernstein polynomials", 
      "Markov chain Monte Carlo algorithm", 
      "accurate Monte Carlo estimates", 
      "pseudo-posterior distribution", 
      "Bayesian nonparametric approach", 
      "data-driven choice", 
      "nonparametric spectral density estimation", 
      "Monte Carlo algorithm", 
      "Monte Carlo estimates", 
      "stationary time series", 
      "spectral density", 
      "gravitational wave detector data", 
      "spline priors", 
      "posterior samples", 
      "spectral density estimation", 
      "location of knots", 
      "spline distributions", 
      "Carlo algorithm", 
      "nonparametric approach", 
      "coverage probability", 
      "LIGO\u2019s sixth science run", 
      "parallel tempering", 
      "density estimation", 
      "mixture components", 
      "simulation study", 
      "detector data", 
      "sixth science run", 
      "sunspot data", 
      "time series", 
      "polynomials", 
      "algorithm's ability", 
      "algorithm", 
      "sharp features", 
      "approximation", 
      "splines", 
      "priors", 
      "generalization", 
      "Petrone", 
      "estimation", 
      "et al", 
      "probability", 
      "estimates", 
      "distribution", 
      "approach", 
      "knots", 
      "terms", 
      "science run", 
      "choice", 
      "solar cycle", 
      "number", 
      "data", 
      "run", 
      "target sensitivity", 
      "density", 
      "series", 
      "metropolis", 
      "al", 
      "features", 
      "tempering", 
      "components", 
      "location", 
      "ability", 
      "cycle", 
      "mixture", 
      "sensitivity", 
      "study", 
      "samples", 
      "method", 
      "new Bayesian nonparametric approach", 
      "Choudhuri et al", 
      "Whittle\u2019s likelihood approximation", 
      "Gibbs Markov chain Monte Carlo algorithm", 
      "chain Monte Carlo algorithm", 
      "complicated spectral densities", 
      "Carlo estimates", 
      "annual mean sunspot data", 
      "mean sunspot data", 
      "real gravitational wave detector data", 
      "wave detector data", 
      "Advanced LIGO target sensitivity", 
      "LIGO target sensitivity", 
      "Bayesian nonparametric spectral density estimation"
    ], 
    "name": "Bayesian nonparametric spectral density estimation using B-spline priors", 
    "pagination": "67-78", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1100349076"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s11222-017-9796-9"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s11222-017-9796-9", 
      "https://app.dimensions.ai/details/publication/pub.1100349076"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2021-11-01T18:34", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211101/entities/gbq_results/article/article_788.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s11222-017-9796-9"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s11222-017-9796-9'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s11222-017-9796-9'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11222-017-9796-9'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11222-017-9796-9'


 

This table displays all metadata directly associated to this object as RDF triples.

183 TRIPLES      22 PREDICATES      112 URIs      100 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s11222-017-9796-9 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author N14aca81b16d54e45ae418350430209a2
4 schema:citation sg:pub.10.1007/978-1-4020-5614-7_3515
5 sg:pub.10.1007/978-1-4419-0320-4
6 sg:pub.10.1007/s11336-013-9354-0
7 sg:pub.10.1007/s13571-011-0014-z
8 schema:datePublished 2018-01-12
9 schema:datePublishedReg 2018-01-12
10 schema:description We present a new Bayesian nonparametric approach to estimating the spectral density of a stationary time series. A nonparametric prior based on a mixture of B-spline distributions is specified and can be regarded as a generalization of the Bernstein polynomial prior of Petrone (Scand J Stat 26:373–393, 1999a; Can J Stat 27:105–126, 1999b) and Choudhuri et al. (J Am Stat Assoc 99(468):1050–1059, 2004). Whittle’s likelihood approximation is used to obtain the pseudo-posterior distribution. This method allows for a data-driven choice of the number of mixture components and the location of knots. Posterior samples are obtained using a Metropolis-within-Gibbs Markov chain Monte Carlo algorithm, and mixing is improved using parallel tempering. We conduct a simulation study to demonstrate that for complicated spectral densities, the B-spline prior provides more accurate Monte Carlo estimates in terms of L1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$L_1$$\end{document}-error and uniform coverage probabilities than the Bernstein polynomial prior. We apply the algorithm to annual mean sunspot data to estimate the solar cycle. Finally, we demonstrate the algorithm’s ability to estimate a spectral density with sharp features, using real gravitational wave detector data from LIGO’s sixth science run, recoloured to match the Advanced LIGO target sensitivity.
11 schema:genre article
12 schema:inLanguage en
13 schema:isAccessibleForFree true
14 schema:isPartOf N3f5cde9a758f4291a9be78445b03520e
15 N9420c7e5be324c6fbfd295007f7b5efc
16 sg:journal.1327447
17 schema:keywords Advanced LIGO target sensitivity
18 Bayesian nonparametric approach
19 Bayesian nonparametric spectral density estimation
20 Bernstein polynomials
21 Carlo algorithm
22 Carlo estimates
23 Choudhuri et al
24 Gibbs Markov chain Monte Carlo algorithm
25 LIGO target sensitivity
26 LIGO’s sixth science run
27 Markov chain Monte Carlo algorithm
28 Monte Carlo algorithm
29 Monte Carlo estimates
30 Petrone
31 Whittle’s likelihood approximation
32 ability
33 accurate Monte Carlo estimates
34 al
35 algorithm
36 algorithm's ability
37 annual mean sunspot data
38 approach
39 approximation
40 chain Monte Carlo algorithm
41 choice
42 complicated spectral densities
43 components
44 coverage probability
45 cycle
46 data
47 data-driven choice
48 density
49 density estimation
50 detector data
51 distribution
52 estimates
53 estimation
54 et al
55 features
56 generalization
57 gravitational wave detector data
58 knots
59 likelihood approximation
60 location
61 location of knots
62 mean sunspot data
63 method
64 metropolis
65 mixture
66 mixture components
67 new Bayesian nonparametric approach
68 nonparametric approach
69 nonparametric spectral density estimation
70 number
71 parallel tempering
72 polynomials
73 posterior samples
74 priors
75 probability
76 pseudo-posterior distribution
77 real gravitational wave detector data
78 run
79 samples
80 science run
81 sensitivity
82 series
83 sharp features
84 simulation study
85 sixth science run
86 solar cycle
87 spectral density
88 spectral density estimation
89 spline distributions
90 spline priors
91 splines
92 stationary time series
93 study
94 sunspot data
95 target sensitivity
96 tempering
97 terms
98 time series
99 wave detector data
100 schema:name Bayesian nonparametric spectral density estimation using B-spline priors
101 schema:pagination 67-78
102 schema:productId N2cba9f6200bb47f2990ce93738672d47
103 N685a4ca03b7a4891ad3d5b1da88255a6
104 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100349076
105 https://doi.org/10.1007/s11222-017-9796-9
106 schema:sdDatePublished 2021-11-01T18:34
107 schema:sdLicense https://scigraph.springernature.com/explorer/license/
108 schema:sdPublisher Nab936193a7de431c963466460b407b3c
109 schema:url https://doi.org/10.1007/s11222-017-9796-9
110 sgo:license sg:explorer/license/
111 sgo:sdDataset articles
112 rdf:type schema:ScholarlyArticle
113 N14aca81b16d54e45ae418350430209a2 rdf:first sg:person.016041213011.17
114 rdf:rest N7abec7f424cb4eca8feb33eecf79351c
115 N2cba9f6200bb47f2990ce93738672d47 schema:name doi
116 schema:value 10.1007/s11222-017-9796-9
117 rdf:type schema:PropertyValue
118 N3f5cde9a758f4291a9be78445b03520e schema:volumeNumber 29
119 rdf:type schema:PublicationVolume
120 N685a4ca03b7a4891ad3d5b1da88255a6 schema:name dimensions_id
121 schema:value pub.1100349076
122 rdf:type schema:PropertyValue
123 N7abec7f424cb4eca8feb33eecf79351c rdf:first sg:person.010133522211.66
124 rdf:rest N850bb96cf7d445a59af22460e53d4613
125 N850bb96cf7d445a59af22460e53d4613 rdf:first sg:person.0607020230.86
126 rdf:rest rdf:nil
127 N9420c7e5be324c6fbfd295007f7b5efc schema:issueNumber 1
128 rdf:type schema:PublicationIssue
129 Nab936193a7de431c963466460b407b3c schema:name Springer Nature - SN SciGraph project
130 rdf:type schema:Organization
131 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
132 schema:name Mathematical Sciences
133 rdf:type schema:DefinedTerm
134 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
135 schema:name Statistics
136 rdf:type schema:DefinedTerm
137 sg:grant.3934184 http://pending.schema.org/fundedItem sg:pub.10.1007/s11222-017-9796-9
138 rdf:type schema:MonetaryGrant
139 sg:grant.5063789 http://pending.schema.org/fundedItem sg:pub.10.1007/s11222-017-9796-9
140 rdf:type schema:MonetaryGrant
141 sg:journal.1327447 schema:issn 0960-3174
142 1573-1375
143 schema:name Statistics and Computing
144 schema:publisher Springer Nature
145 rdf:type schema:Periodical
146 sg:person.010133522211.66 schema:affiliation grid-institutes:grid.9654.e
147 schema:familyName Meyer
148 schema:givenName Renate
149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010133522211.66
150 rdf:type schema:Person
151 sg:person.016041213011.17 schema:affiliation grid-institutes:grid.253692.9
152 schema:familyName Edwards
153 schema:givenName Matthew C.
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016041213011.17
155 rdf:type schema:Person
156 sg:person.0607020230.86 schema:affiliation grid-institutes:grid.503124.1
157 schema:familyName Christensen
158 schema:givenName Nelson
159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0607020230.86
160 rdf:type schema:Person
161 sg:pub.10.1007/978-1-4020-5614-7_3515 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031013171
162 https://doi.org/10.1007/978-1-4020-5614-7_3515
163 rdf:type schema:CreativeWork
164 sg:pub.10.1007/978-1-4419-0320-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034653958
165 https://doi.org/10.1007/978-1-4419-0320-4
166 rdf:type schema:CreativeWork
167 sg:pub.10.1007/s11336-013-9354-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036633529
168 https://doi.org/10.1007/s11336-013-9354-0
169 rdf:type schema:CreativeWork
170 sg:pub.10.1007/s13571-011-0014-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1010395105
171 https://doi.org/10.1007/s13571-011-0014-z
172 rdf:type schema:CreativeWork
173 grid-institutes:grid.253692.9 schema:alternateName Physics and Astronomy, Carleton College, Northfield, MN, USA
174 schema:name Department of Statistics, University of Auckland, Auckland, New Zealand
175 Physics and Astronomy, Carleton College, Northfield, MN, USA
176 rdf:type schema:Organization
177 grid-institutes:grid.503124.1 schema:alternateName Artemis, Université Côte d’Azur, Observatoire de Côte d’Azur, CNRS, Nice, France
178 schema:name Artemis, Université Côte d’Azur, Observatoire de Côte d’Azur, CNRS, Nice, France
179 Physics and Astronomy, Carleton College, Northfield, MN, USA
180 rdf:type schema:Organization
181 grid-institutes:grid.9654.e schema:alternateName Department of Statistics, University of Auckland, Auckland, New Zealand
182 schema:name Department of Statistics, University of Auckland, Auckland, New Zealand
183 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...