Evaluation of graphical diagnostics for assessing goodness of fit of logistic regression models View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2011-04

AUTHORS

Venkata V. Pavan Kumar, Stephen B. Duffull

ABSTRACT

The aim of the current work was to evaluate graphical diagnostics for assessment of the fit of logistic regression models. Assessment of goodness of fit of a model to the data set is essential to ensure the model provides an acceptable description of the binary variables seen. For logistic regression the most common diagnostic used for this purpose is binning the data and comparing the empirical probability of the occurrence of a dependent variable with the model predicted probability against the mean covariate value in the bin. Although intuitively appealing this method, which we term simple binning, may not have consistent properties for diagnosing model problems. In this report we describe and evaluate two different diagnostic procedures, random binning and simplified Bayes marginal model plots. These procedures were assessed via simulation under three different designs. Design 1: studies which were balanced on binary variables and a continuous covariate. Design 2: studies that were balanced on binary variables but unbalanced on the continuous covariate. Design 3: studies that were unbalanced on both the binary variables and the covariate. Each simulated study consisted of 500 individuals. Thirty studies were simulated. The covariate of interest was dose which could range from 0 to 20 units. The data were simulated with the dose being related to the outcome according to an E (max) model on the logit scale. A logit E (max) model (correct model) and a logit linear model (wrong model) were fitted to all data sets. The performance of the above diagnostics, in addition to simple binning, was compared. For all designs the proposed diagnostics performed at least as well and in many instances better than simple binning. In case of design 1 random binning and simple binning are identical. In the case of designs 2 and 3 random binning and simplified Bayes marginal model plots were superior in assessing the model fit when compared to simple binning. For the examples tested, both random binning and simplified Bayesian marginal model plots performed acceptably. More... »

PAGES

205-222

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s10928-010-9189-6

DOI

http://dx.doi.org/10.1007/s10928-010-9189-6

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1038068526

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/21153868


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"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Computer Simulation", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Data Display", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Data Interpretation, Statistical", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Logistic Models", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Models, Statistical", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Probability", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Otago", 
          "id": "https://www.grid.ac/institutes/grid.29980.3a", 
          "name": [
            "School of Pharmacy, University of Otago, Dunedin, New Zealand"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pavan Kumar", 
        "givenName": "Venkata V.", 
        "id": "sg:person.014061754602.47", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014061754602.47"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Otago", 
          "id": "https://www.grid.ac/institutes/grid.29980.3a", 
          "name": [
            "School of Pharmacy, University of Otago, Dunedin, New Zealand"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Duffull", 
        "givenName": "Stephen B.", 
        "id": "sg:person.01126715720.45", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01126715720.45"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1111/j.1467-842x.2007.00497.x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015821136"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10928-005-0016-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015863917", 
          "https://doi.org/10.1007/s10928-005-0016-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10928-005-0016-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015863917", 
          "https://doi.org/10.1007/s10928-005-0016-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10928-005-0016-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015863917", 
          "https://doi.org/10.1007/s10928-005-0016-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1011555016423", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032175473", 
          "https://doi.org/10.1023/a:1011555016423"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/j.1460-9592.2000.00575.x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040674094"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.cmpb.2007.12.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048645146"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11095-007-9361-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050287322", 
          "https://doi.org/10.1007/s11095-007-9361-x"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1081/bip-100102501", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052383947"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1198/000313002560", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064196951"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/aos/1176345513", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064407809"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/1390865", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069468305"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/0471249688", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098661133"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/0471249688", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098661133"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1109491887", 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1109491887", 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2011-04", 
    "datePublishedReg": "2011-04-01", 
    "description": "The aim of the current work was to evaluate graphical diagnostics for assessment of the fit of logistic regression models. Assessment of goodness of fit of a model to the data set is essential to ensure the model provides an acceptable description of the binary variables seen. For logistic regression the most common diagnostic used for this purpose is binning the data and comparing the empirical probability of the occurrence of a dependent variable with the model predicted probability against the mean covariate value in the bin. Although intuitively appealing this method, which we term simple binning, may not have consistent properties for diagnosing model problems. In this report we describe and evaluate two different diagnostic procedures, random binning and simplified Bayes marginal model plots. These procedures were assessed via simulation under three different designs. Design 1: studies which were balanced on binary variables and a continuous covariate. Design 2: studies that were balanced on binary variables but unbalanced on the continuous covariate. Design 3: studies that were unbalanced on both the binary variables and the covariate. Each simulated study consisted of 500 individuals. Thirty studies were simulated. The covariate of interest was dose which could range from 0 to 20 units. The data were simulated with the dose being related to the outcome according to an E (max) model on the logit scale. A logit E (max) model (correct model) and a logit linear model (wrong model) were fitted to all data sets. The performance of the above diagnostics, in addition to simple binning, was compared. For all designs the proposed diagnostics performed at least as well and in many instances better than simple binning. In case of design 1 random binning and simple binning are identical. In the case of designs 2 and 3 random binning and simplified Bayes marginal model plots were superior in assessing the model fit when compared to simple binning. For the examples tested, both random binning and simplified Bayesian marginal model plots performed acceptably.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s10928-010-9189-6", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1016394", 
        "issn": [
          "1567-567X", 
          "2168-5789"
        ], 
        "name": "Journal of Pharmacokinetics and Pharmacodynamics", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "2", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "38"
      }
    ], 
    "name": "Evaluation of graphical diagnostics for assessing goodness of fit of logistic regression models", 
    "pagination": "205-222", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "b5588f40091198ff0104db2b87bfc306f079b8cdc9d278ff650be4d0ef57e0e1"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "21153868"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "101096520"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s10928-010-9189-6"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1038068526"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s10928-010-9189-6", 
      "https://app.dimensions.ai/details/publication/pub.1038068526"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T16:54", 
    "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/v90/0000000001_0000000264/records_8669_00000591.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007%2Fs10928-010-9189-6"
  }
]
 

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/s10928-010-9189-6'

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/s10928-010-9189-6'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10928-010-9189-6'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10928-010-9189-6'


 

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

138 TRIPLES      21 PREDICATES      47 URIs      27 LITERALS      15 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s10928-010-9189-6 schema:about N32997c259b8049a6929772e1f00d2652
2 N3396b2e0691d4a8cb26b7a9e4edff98d
3 N371a66cfce5f4a2a9d3a26ee659bd464
4 N48b2a6970d634bafae601c4626afb9c9
5 N96dcb35bb36141489078731cfdbc3e9e
6 Ne6b380144610438da1ba6c7dbb347950
7 anzsrc-for:01
8 anzsrc-for:0104
9 schema:author N13fc755c3d024e419edb5b980d2f8b98
10 schema:citation sg:pub.10.1007/s10928-005-0016-4
11 sg:pub.10.1007/s11095-007-9361-x
12 sg:pub.10.1023/a:1011555016423
13 https://app.dimensions.ai/details/publication/pub.1109491887
14 https://doi.org/10.1002/0471249688
15 https://doi.org/10.1016/j.cmpb.2007.12.002
16 https://doi.org/10.1081/bip-100102501
17 https://doi.org/10.1111/j.1460-9592.2000.00575.x
18 https://doi.org/10.1111/j.1467-842x.2007.00497.x
19 https://doi.org/10.1198/000313002560
20 https://doi.org/10.1214/aos/1176345513
21 https://doi.org/10.2307/1390865
22 schema:datePublished 2011-04
23 schema:datePublishedReg 2011-04-01
24 schema:description The aim of the current work was to evaluate graphical diagnostics for assessment of the fit of logistic regression models. Assessment of goodness of fit of a model to the data set is essential to ensure the model provides an acceptable description of the binary variables seen. For logistic regression the most common diagnostic used for this purpose is binning the data and comparing the empirical probability of the occurrence of a dependent variable with the model predicted probability against the mean covariate value in the bin. Although intuitively appealing this method, which we term simple binning, may not have consistent properties for diagnosing model problems. In this report we describe and evaluate two different diagnostic procedures, random binning and simplified Bayes marginal model plots. These procedures were assessed via simulation under three different designs. Design 1: studies which were balanced on binary variables and a continuous covariate. Design 2: studies that were balanced on binary variables but unbalanced on the continuous covariate. Design 3: studies that were unbalanced on both the binary variables and the covariate. Each simulated study consisted of 500 individuals. Thirty studies were simulated. The covariate of interest was dose which could range from 0 to 20 units. The data were simulated with the dose being related to the outcome according to an E (max) model on the logit scale. A logit E (max) model (correct model) and a logit linear model (wrong model) were fitted to all data sets. The performance of the above diagnostics, in addition to simple binning, was compared. For all designs the proposed diagnostics performed at least as well and in many instances better than simple binning. In case of design 1 random binning and simple binning are identical. In the case of designs 2 and 3 random binning and simplified Bayes marginal model plots were superior in assessing the model fit when compared to simple binning. For the examples tested, both random binning and simplified Bayesian marginal model plots performed acceptably.
25 schema:genre research_article
26 schema:inLanguage en
27 schema:isAccessibleForFree false
28 schema:isPartOf N0ae21bbde7924931a776e0c66dccf82e
29 Nb6ec5973085c443b99c366a7e47fbec0
30 sg:journal.1016394
31 schema:name Evaluation of graphical diagnostics for assessing goodness of fit of logistic regression models
32 schema:pagination 205-222
33 schema:productId N1b848a6eb3344f50b1c954a2d90427d3
34 N2b49cbcfda154dadbd71de1f038d645e
35 N89fcefee27774f1195635a5079f1bbc3
36 Nc04ba318839149e5af3dca06b4227a84
37 Nd4d31d65484645e6a794934bdb486388
38 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038068526
39 https://doi.org/10.1007/s10928-010-9189-6
40 schema:sdDatePublished 2019-04-10T16:54
41 schema:sdLicense https://scigraph.springernature.com/explorer/license/
42 schema:sdPublisher Nde6d1192f01b49c7840ae5c26be89526
43 schema:url http://link.springer.com/10.1007%2Fs10928-010-9189-6
44 sgo:license sg:explorer/license/
45 sgo:sdDataset articles
46 rdf:type schema:ScholarlyArticle
47 N0ae21bbde7924931a776e0c66dccf82e schema:issueNumber 2
48 rdf:type schema:PublicationIssue
49 N13fc755c3d024e419edb5b980d2f8b98 rdf:first sg:person.014061754602.47
50 rdf:rest Nedd5991346a84cf8b485afc78ab00358
51 N1b848a6eb3344f50b1c954a2d90427d3 schema:name doi
52 schema:value 10.1007/s10928-010-9189-6
53 rdf:type schema:PropertyValue
54 N2b49cbcfda154dadbd71de1f038d645e schema:name nlm_unique_id
55 schema:value 101096520
56 rdf:type schema:PropertyValue
57 N32997c259b8049a6929772e1f00d2652 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
58 schema:name Models, Statistical
59 rdf:type schema:DefinedTerm
60 N3396b2e0691d4a8cb26b7a9e4edff98d schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
61 schema:name Logistic Models
62 rdf:type schema:DefinedTerm
63 N371a66cfce5f4a2a9d3a26ee659bd464 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
64 schema:name Probability
65 rdf:type schema:DefinedTerm
66 N48b2a6970d634bafae601c4626afb9c9 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
67 schema:name Computer Simulation
68 rdf:type schema:DefinedTerm
69 N89fcefee27774f1195635a5079f1bbc3 schema:name pubmed_id
70 schema:value 21153868
71 rdf:type schema:PropertyValue
72 N96dcb35bb36141489078731cfdbc3e9e schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
73 schema:name Data Display
74 rdf:type schema:DefinedTerm
75 Nb6ec5973085c443b99c366a7e47fbec0 schema:volumeNumber 38
76 rdf:type schema:PublicationVolume
77 Nc04ba318839149e5af3dca06b4227a84 schema:name dimensions_id
78 schema:value pub.1038068526
79 rdf:type schema:PropertyValue
80 Nd4d31d65484645e6a794934bdb486388 schema:name readcube_id
81 schema:value b5588f40091198ff0104db2b87bfc306f079b8cdc9d278ff650be4d0ef57e0e1
82 rdf:type schema:PropertyValue
83 Nde6d1192f01b49c7840ae5c26be89526 schema:name Springer Nature - SN SciGraph project
84 rdf:type schema:Organization
85 Ne6b380144610438da1ba6c7dbb347950 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
86 schema:name Data Interpretation, Statistical
87 rdf:type schema:DefinedTerm
88 Nedd5991346a84cf8b485afc78ab00358 rdf:first sg:person.01126715720.45
89 rdf:rest rdf:nil
90 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
91 schema:name Mathematical Sciences
92 rdf:type schema:DefinedTerm
93 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
94 schema:name Statistics
95 rdf:type schema:DefinedTerm
96 sg:journal.1016394 schema:issn 1567-567X
97 2168-5789
98 schema:name Journal of Pharmacokinetics and Pharmacodynamics
99 rdf:type schema:Periodical
100 sg:person.01126715720.45 schema:affiliation https://www.grid.ac/institutes/grid.29980.3a
101 schema:familyName Duffull
102 schema:givenName Stephen B.
103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01126715720.45
104 rdf:type schema:Person
105 sg:person.014061754602.47 schema:affiliation https://www.grid.ac/institutes/grid.29980.3a
106 schema:familyName Pavan Kumar
107 schema:givenName Venkata V.
108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014061754602.47
109 rdf:type schema:Person
110 sg:pub.10.1007/s10928-005-0016-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015863917
111 https://doi.org/10.1007/s10928-005-0016-4
112 rdf:type schema:CreativeWork
113 sg:pub.10.1007/s11095-007-9361-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1050287322
114 https://doi.org/10.1007/s11095-007-9361-x
115 rdf:type schema:CreativeWork
116 sg:pub.10.1023/a:1011555016423 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032175473
117 https://doi.org/10.1023/a:1011555016423
118 rdf:type schema:CreativeWork
119 https://app.dimensions.ai/details/publication/pub.1109491887 schema:CreativeWork
120 https://doi.org/10.1002/0471249688 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098661133
121 rdf:type schema:CreativeWork
122 https://doi.org/10.1016/j.cmpb.2007.12.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048645146
123 rdf:type schema:CreativeWork
124 https://doi.org/10.1081/bip-100102501 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052383947
125 rdf:type schema:CreativeWork
126 https://doi.org/10.1111/j.1460-9592.2000.00575.x schema:sameAs https://app.dimensions.ai/details/publication/pub.1040674094
127 rdf:type schema:CreativeWork
128 https://doi.org/10.1111/j.1467-842x.2007.00497.x schema:sameAs https://app.dimensions.ai/details/publication/pub.1015821136
129 rdf:type schema:CreativeWork
130 https://doi.org/10.1198/000313002560 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064196951
131 rdf:type schema:CreativeWork
132 https://doi.org/10.1214/aos/1176345513 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064407809
133 rdf:type schema:CreativeWork
134 https://doi.org/10.2307/1390865 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069468305
135 rdf:type schema:CreativeWork
136 https://www.grid.ac/institutes/grid.29980.3a schema:alternateName University of Otago
137 schema:name School of Pharmacy, University of Otago, Dunedin, New Zealand
138 rdf:type schema:Organization
 




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


...