A-optimal designs for non-parametric symmetrical global sensitivity analysis View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2022-06-10

AUTHORS

Xueping Chen, Yujie Gai, Xiaodi Wang

ABSTRACT

In the early stage of exploring a complex system, a preliminary experiment is used to capture the key characteristics of the model. Symmetrical global sensitivity analysis (SGSA) is one such experiment that explores the symmetrical structure of model by decomposing the model into independent symmetric functions. However, the existing experimental plans for SGSA rely on deterministic computational models that produce unique values of outputs when executed for specific values of inputs. In this paper, the problem of designing experiments for non-parametric SGSA is considered. Here the phrase “non-parametric” refers to model outputs containing random errors. The main result in the paper shows that a symmetrical design with certain constraints achieves A-optimum for the estimation of each output element function, and guarantees the superiority of the SGSA result. The statistical properties of non-parametric SGSA based on the optimal designs are further discussed, showing that the non-influential sensitivity indices can be estimated with low bias and volatility. Two explicit structures of the optimal designs are obtained. The optimality of the derived design is validated by simulation in the end. More... »

PAGES

1-19

References to SciGraph publications

  • 1998. Lattice Rules: How Well Do They Measure Up? in RANDOM AND QUASI-RANDOM POINT SETS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s00184-022-00872-3

    DOI

    http://dx.doi.org/10.1007/s00184-022-00872-3

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1148575351


    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": "Department of Statistics, Jiangsu University of Technology, Changzhou, China", 
              "id": "http://www.grid.ac/institutes/grid.503014.3", 
              "name": [
                "Department of Statistics, Jiangsu University of Technology, Changzhou, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Chen", 
            "givenName": "Xueping", 
            "id": "sg:person.016336663122.33", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016336663122.33"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China", 
              "id": "http://www.grid.ac/institutes/grid.411054.5", 
              "name": [
                "School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Gai", 
            "givenName": "Yujie", 
            "id": "sg:person.013114074740.46", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013114074740.46"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China", 
              "id": "http://www.grid.ac/institutes/grid.411054.5", 
              "name": [
                "School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wang", 
            "givenName": "Xiaodi", 
            "id": "sg:person.07503063040.42", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07503063040.42"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-1-4612-1702-2_3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015938165", 
              "https://doi.org/10.1007/978-1-4612-1702-2_3"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2022-06-10", 
        "datePublishedReg": "2022-06-10", 
        "description": "In the early stage of exploring a complex system, a preliminary experiment is used to capture the key characteristics of the model. Symmetrical global sensitivity analysis (SGSA) is one such experiment that explores the symmetrical structure of model by decomposing the model into independent symmetric functions. However, the existing experimental plans for SGSA rely on deterministic computational models that produce unique values of outputs when executed for specific values of inputs. In this paper, the problem of designing experiments for non-parametric SGSA is considered. Here the phrase \u201cnon-parametric\u201d refers to model outputs containing random errors. The main result in the paper shows that a symmetrical design with certain constraints achieves A-optimum for the estimation of each output element function, and guarantees the superiority of the SGSA result. The statistical properties of non-parametric SGSA based on the optimal designs are further discussed, showing that the non-influential sensitivity indices can be estimated with low bias and volatility. Two explicit structures of the optimal designs are obtained. The optimality of the derived design is validated by simulation in the end.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s00184-022-00872-3", 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.8898369", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.8125962", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1041634", 
            "issn": [
              "0026-1335", 
              "1435-926X"
            ], 
            "name": "Metrika", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }
        ], 
        "keywords": [
          "optimal design", 
          "global sensitivity analysis", 
          "sensitivity analysis", 
          "statistical properties", 
          "deterministic computational model", 
          "symmetric functions", 
          "explicit structure", 
          "certain constraints", 
          "random errors", 
          "experimental plan", 
          "symmetrical design", 
          "complex systems", 
          "volatility", 
          "main results", 
          "model output", 
          "specific values", 
          "element functions", 
          "output", 
          "key characteristics", 
          "symmetrical structure", 
          "computational model", 
          "design", 
          "model", 
          "low bias", 
          "optimality", 
          "preliminary experiments", 
          "such experiments", 
          "unique value", 
          "simulations", 
          "experiments", 
          "estimation", 
          "constraints", 
          "structure", 
          "sensitivity index", 
          "bias", 
          "problem", 
          "function", 
          "plan", 
          "error", 
          "values", 
          "analysis", 
          "properties", 
          "input", 
          "index", 
          "results", 
          "superiority", 
          "characteristics", 
          "system", 
          "early stages", 
          "end", 
          "stage", 
          "phrases", 
          "paper"
        ], 
        "name": "A-optimal designs for non-parametric symmetrical global sensitivity analysis", 
        "pagination": "1-19", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1148575351"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s00184-022-00872-3"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s00184-022-00872-3", 
          "https://app.dimensions.ai/details/publication/pub.1148575351"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-09-02T16:08", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20220902/entities/gbq_results/article/article_928.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s00184-022-00872-3"
      }
    ]
     

    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/s00184-022-00872-3'

    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/s00184-022-00872-3'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00184-022-00872-3'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00184-022-00872-3'


     

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

    129 TRIPLES      21 PREDICATES      76 URIs      67 LITERALS      4 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s00184-022-00872-3 schema:about anzsrc-for:01
    2 anzsrc-for:0104
    3 schema:author N7537d7d100a6482dac47a57dceb84db2
    4 schema:citation sg:pub.10.1007/978-1-4612-1702-2_3
    5 schema:datePublished 2022-06-10
    6 schema:datePublishedReg 2022-06-10
    7 schema:description In the early stage of exploring a complex system, a preliminary experiment is used to capture the key characteristics of the model. Symmetrical global sensitivity analysis (SGSA) is one such experiment that explores the symmetrical structure of model by decomposing the model into independent symmetric functions. However, the existing experimental plans for SGSA rely on deterministic computational models that produce unique values of outputs when executed for specific values of inputs. In this paper, the problem of designing experiments for non-parametric SGSA is considered. Here the phrase “non-parametric” refers to model outputs containing random errors. The main result in the paper shows that a symmetrical design with certain constraints achieves A-optimum for the estimation of each output element function, and guarantees the superiority of the SGSA result. The statistical properties of non-parametric SGSA based on the optimal designs are further discussed, showing that the non-influential sensitivity indices can be estimated with low bias and volatility. Two explicit structures of the optimal designs are obtained. The optimality of the derived design is validated by simulation in the end.
    8 schema:genre article
    9 schema:isAccessibleForFree false
    10 schema:isPartOf sg:journal.1041634
    11 schema:keywords analysis
    12 bias
    13 certain constraints
    14 characteristics
    15 complex systems
    16 computational model
    17 constraints
    18 design
    19 deterministic computational model
    20 early stages
    21 element functions
    22 end
    23 error
    24 estimation
    25 experimental plan
    26 experiments
    27 explicit structure
    28 function
    29 global sensitivity analysis
    30 index
    31 input
    32 key characteristics
    33 low bias
    34 main results
    35 model
    36 model output
    37 optimal design
    38 optimality
    39 output
    40 paper
    41 phrases
    42 plan
    43 preliminary experiments
    44 problem
    45 properties
    46 random errors
    47 results
    48 sensitivity analysis
    49 sensitivity index
    50 simulations
    51 specific values
    52 stage
    53 statistical properties
    54 structure
    55 such experiments
    56 superiority
    57 symmetric functions
    58 symmetrical design
    59 symmetrical structure
    60 system
    61 unique value
    62 values
    63 volatility
    64 schema:name A-optimal designs for non-parametric symmetrical global sensitivity analysis
    65 schema:pagination 1-19
    66 schema:productId N0da2b3b6bd6948379bbdf7a9c4dc2466
    67 N4ff16df292c34760ada888e043a1b90f
    68 schema:sameAs https://app.dimensions.ai/details/publication/pub.1148575351
    69 https://doi.org/10.1007/s00184-022-00872-3
    70 schema:sdDatePublished 2022-09-02T16:08
    71 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    72 schema:sdPublisher N458ab5fc8a6a4a4e8a760ea41e7ef16b
    73 schema:url https://doi.org/10.1007/s00184-022-00872-3
    74 sgo:license sg:explorer/license/
    75 sgo:sdDataset articles
    76 rdf:type schema:ScholarlyArticle
    77 N0da2b3b6bd6948379bbdf7a9c4dc2466 schema:name dimensions_id
    78 schema:value pub.1148575351
    79 rdf:type schema:PropertyValue
    80 N458ab5fc8a6a4a4e8a760ea41e7ef16b schema:name Springer Nature - SN SciGraph project
    81 rdf:type schema:Organization
    82 N4ff16df292c34760ada888e043a1b90f schema:name doi
    83 schema:value 10.1007/s00184-022-00872-3
    84 rdf:type schema:PropertyValue
    85 N7537d7d100a6482dac47a57dceb84db2 rdf:first sg:person.016336663122.33
    86 rdf:rest Nc96de6c3ce1547498204c35bde8b6ab2
    87 Nc96de6c3ce1547498204c35bde8b6ab2 rdf:first sg:person.013114074740.46
    88 rdf:rest Nea4032b5165745b69603fff0317f674f
    89 Nea4032b5165745b69603fff0317f674f rdf:first sg:person.07503063040.42
    90 rdf:rest rdf:nil
    91 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
    92 schema:name Mathematical Sciences
    93 rdf:type schema:DefinedTerm
    94 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
    95 schema:name Statistics
    96 rdf:type schema:DefinedTerm
    97 sg:grant.8125962 http://pending.schema.org/fundedItem sg:pub.10.1007/s00184-022-00872-3
    98 rdf:type schema:MonetaryGrant
    99 sg:grant.8898369 http://pending.schema.org/fundedItem sg:pub.10.1007/s00184-022-00872-3
    100 rdf:type schema:MonetaryGrant
    101 sg:journal.1041634 schema:issn 0026-1335
    102 1435-926X
    103 schema:name Metrika
    104 schema:publisher Springer Nature
    105 rdf:type schema:Periodical
    106 sg:person.013114074740.46 schema:affiliation grid-institutes:grid.411054.5
    107 schema:familyName Gai
    108 schema:givenName Yujie
    109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013114074740.46
    110 rdf:type schema:Person
    111 sg:person.016336663122.33 schema:affiliation grid-institutes:grid.503014.3
    112 schema:familyName Chen
    113 schema:givenName Xueping
    114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016336663122.33
    115 rdf:type schema:Person
    116 sg:person.07503063040.42 schema:affiliation grid-institutes:grid.411054.5
    117 schema:familyName Wang
    118 schema:givenName Xiaodi
    119 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07503063040.42
    120 rdf:type schema:Person
    121 sg:pub.10.1007/978-1-4612-1702-2_3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015938165
    122 https://doi.org/10.1007/978-1-4612-1702-2_3
    123 rdf:type schema:CreativeWork
    124 grid-institutes:grid.411054.5 schema:alternateName School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China
    125 schema:name School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China
    126 rdf:type schema:Organization
    127 grid-institutes:grid.503014.3 schema:alternateName Department of Statistics, Jiangsu University of Technology, Changzhou, China
    128 schema:name Department of Statistics, Jiangsu University of Technology, Changzhou, China
    129 rdf:type schema:Organization
     




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


    ...