Unconstrained parametrizations for variance-covariance matrices View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

1996-09

AUTHORS

José C. Pinheiro, Douglas M. Bates

ABSTRACT

The estimation of variance-covariance matrices through optimization of an objective function, such as a log-likelihood function, is usually a difficult numerical problem. Since the estimates should be positive semi-definite matrices, we must use constrained optimization, or employ a parametrization that enforces this condition. We describe here five different parametrizations for variance-covariance matrices that ensure positive definiteness, thus leaving the estimation problem unconstrained. We compare the parametrizations based on their computational efficiency and statistical interpretability. The results described here are particularly useful in maximum likelihood and restricted maximum likelihood estimation in linear and non-linear mixed-effects models, but are also applicable to other areas of statistics. More... »

PAGES

289-296

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/bf00140873

DOI

http://dx.doi.org/10.1007/bf00140873

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1039962386


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/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Wisconsin\u2013Madison", 
          "id": "https://www.grid.ac/institutes/grid.14003.36", 
          "name": [
            "Department of Biostatistics, University of Wisconsin-Madison, Madison, Wisconsin, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pinheiro", 
        "givenName": "Jos\u00e9 C.", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Wisconsin\u2013Madison", 
          "id": "https://www.grid.ac/institutes/grid.14003.36", 
          "name": [
            "Department of Statistics, University of Wisconsin-Madison, Madison, Wisconsin, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bates", 
        "givenName": "Douglas M.", 
        "id": "sg:person.015071243407.62", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015071243407.62"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1137/0715022", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062852494"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/0908055", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062857102"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/aos/1176349012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064408749"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/1390625", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069468122"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/2529876", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069975465"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/2530695", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069976181"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/2532087", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069977517"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/9780470316436", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1109489408"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1109489408", 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/9780470316757", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1109496271"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1109496271", 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1996-09", 
    "datePublishedReg": "1996-09-01", 
    "description": "The estimation of variance-covariance matrices through optimization of an objective function, such as a log-likelihood function, is usually a difficult numerical problem. Since the estimates should be positive semi-definite matrices, we must use constrained optimization, or employ a parametrization that enforces this condition. We describe here five different parametrizations for variance-covariance matrices that ensure positive definiteness, thus leaving the estimation problem unconstrained. We compare the parametrizations based on their computational efficiency and statistical interpretability. The results described here are particularly useful in maximum likelihood and restricted maximum likelihood estimation in linear and non-linear mixed-effects models, but are also applicable to other areas of statistics.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/bf00140873", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1327447", 
        "issn": [
          "0960-3174", 
          "1573-1375"
        ], 
        "name": "Statistics and Computing", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "3", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "6"
      }
    ], 
    "name": "Unconstrained parametrizations for variance-covariance matrices", 
    "pagination": "289-296", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "be5d309378b399ac969e7108b54563af150561b58ca30eb773d52161edfd7bc4"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/bf00140873"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1039962386"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/bf00140873", 
      "https://app.dimensions.ai/details/publication/pub.1039962386"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T14:00", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000371_0000000371/records_130829_00000003.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007/BF00140873"
  }
]
 

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/bf00140873'

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/bf00140873'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/bf00140873'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/bf00140873'


 

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

99 TRIPLES      21 PREDICATES      38 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/bf00140873 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author Nc233361189914958b724e0fc949fd371
4 schema:citation https://app.dimensions.ai/details/publication/pub.1109489408
5 https://app.dimensions.ai/details/publication/pub.1109496271
6 https://doi.org/10.1002/9780470316436
7 https://doi.org/10.1002/9780470316757
8 https://doi.org/10.1137/0715022
9 https://doi.org/10.1137/0908055
10 https://doi.org/10.1214/aos/1176349012
11 https://doi.org/10.2307/1390625
12 https://doi.org/10.2307/2529876
13 https://doi.org/10.2307/2530695
14 https://doi.org/10.2307/2532087
15 schema:datePublished 1996-09
16 schema:datePublishedReg 1996-09-01
17 schema:description The estimation of variance-covariance matrices through optimization of an objective function, such as a log-likelihood function, is usually a difficult numerical problem. Since the estimates should be positive semi-definite matrices, we must use constrained optimization, or employ a parametrization that enforces this condition. We describe here five different parametrizations for variance-covariance matrices that ensure positive definiteness, thus leaving the estimation problem unconstrained. We compare the parametrizations based on their computational efficiency and statistical interpretability. The results described here are particularly useful in maximum likelihood and restricted maximum likelihood estimation in linear and non-linear mixed-effects models, but are also applicable to other areas of statistics.
18 schema:genre research_article
19 schema:inLanguage en
20 schema:isAccessibleForFree false
21 schema:isPartOf N4e58dda3730d43d39878c9d5fb4d5d88
22 N812a81247ce0470f84a78b065a9751bb
23 sg:journal.1327447
24 schema:name Unconstrained parametrizations for variance-covariance matrices
25 schema:pagination 289-296
26 schema:productId N02e3ec6f4a83453dab29bf2c112fa7b7
27 N75a50915c7be40a08beb513a4d72a8ac
28 Na97d3368d82e49a98949f0c43728a567
29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039962386
30 https://doi.org/10.1007/bf00140873
31 schema:sdDatePublished 2019-04-11T14:00
32 schema:sdLicense https://scigraph.springernature.com/explorer/license/
33 schema:sdPublisher N51eca17536054f8c9dc5af6d1c48fad3
34 schema:url http://link.springer.com/10.1007/BF00140873
35 sgo:license sg:explorer/license/
36 sgo:sdDataset articles
37 rdf:type schema:ScholarlyArticle
38 N02e3ec6f4a83453dab29bf2c112fa7b7 schema:name dimensions_id
39 schema:value pub.1039962386
40 rdf:type schema:PropertyValue
41 N4e58dda3730d43d39878c9d5fb4d5d88 schema:volumeNumber 6
42 rdf:type schema:PublicationVolume
43 N51eca17536054f8c9dc5af6d1c48fad3 schema:name Springer Nature - SN SciGraph project
44 rdf:type schema:Organization
45 N75a50915c7be40a08beb513a4d72a8ac schema:name doi
46 schema:value 10.1007/bf00140873
47 rdf:type schema:PropertyValue
48 N812a81247ce0470f84a78b065a9751bb schema:issueNumber 3
49 rdf:type schema:PublicationIssue
50 Na6921124598947ba8051b6496fa7c0f1 rdf:first sg:person.015071243407.62
51 rdf:rest rdf:nil
52 Na97d3368d82e49a98949f0c43728a567 schema:name readcube_id
53 schema:value be5d309378b399ac969e7108b54563af150561b58ca30eb773d52161edfd7bc4
54 rdf:type schema:PropertyValue
55 Nc233361189914958b724e0fc949fd371 rdf:first Ne2647263dc2e4ce0bc348fbaf711b70c
56 rdf:rest Na6921124598947ba8051b6496fa7c0f1
57 Ne2647263dc2e4ce0bc348fbaf711b70c schema:affiliation https://www.grid.ac/institutes/grid.14003.36
58 schema:familyName Pinheiro
59 schema:givenName José C.
60 rdf:type schema:Person
61 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
62 schema:name Mathematical Sciences
63 rdf:type schema:DefinedTerm
64 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
65 schema:name Statistics
66 rdf:type schema:DefinedTerm
67 sg:journal.1327447 schema:issn 0960-3174
68 1573-1375
69 schema:name Statistics and Computing
70 rdf:type schema:Periodical
71 sg:person.015071243407.62 schema:affiliation https://www.grid.ac/institutes/grid.14003.36
72 schema:familyName Bates
73 schema:givenName Douglas M.
74 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015071243407.62
75 rdf:type schema:Person
76 https://app.dimensions.ai/details/publication/pub.1109489408 schema:CreativeWork
77 https://app.dimensions.ai/details/publication/pub.1109496271 schema:CreativeWork
78 https://doi.org/10.1002/9780470316436 schema:sameAs https://app.dimensions.ai/details/publication/pub.1109489408
79 rdf:type schema:CreativeWork
80 https://doi.org/10.1002/9780470316757 schema:sameAs https://app.dimensions.ai/details/publication/pub.1109496271
81 rdf:type schema:CreativeWork
82 https://doi.org/10.1137/0715022 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062852494
83 rdf:type schema:CreativeWork
84 https://doi.org/10.1137/0908055 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062857102
85 rdf:type schema:CreativeWork
86 https://doi.org/10.1214/aos/1176349012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064408749
87 rdf:type schema:CreativeWork
88 https://doi.org/10.2307/1390625 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069468122
89 rdf:type schema:CreativeWork
90 https://doi.org/10.2307/2529876 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069975465
91 rdf:type schema:CreativeWork
92 https://doi.org/10.2307/2530695 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069976181
93 rdf:type schema:CreativeWork
94 https://doi.org/10.2307/2532087 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069977517
95 rdf:type schema:CreativeWork
96 https://www.grid.ac/institutes/grid.14003.36 schema:alternateName University of Wisconsin–Madison
97 schema:name Department of Biostatistics, University of Wisconsin-Madison, Madison, Wisconsin, USA
98 Department of Statistics, University of Wisconsin-Madison, Madison, Wisconsin, USA
99 rdf:type schema:Organization
 




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


...