Comparing and Weighting Imperfect Models Using D-Probabilities

We propose a new approach for assigning weights to models using a divergence-based method (D-probabilities), relying on evaluating parametric models relative to a nonparametric Bayesian reference using Kullback-Leibler divergence. D-probabilities are useful in goodness-of-fit assessments, in compari...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of the American Statistical Association Jg. 115; H. 531; S. 1349 - 1360
Hauptverfasser: Li, Meng, Dunson, David B.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Taylor & Francis 02.07.2020
Taylor & Francis Ltd
Schlagworte:
ISSN:0162-1459, 1537-274X, 1537-274X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We propose a new approach for assigning weights to models using a divergence-based method (D-probabilities), relying on evaluating parametric models relative to a nonparametric Bayesian reference using Kullback-Leibler divergence. D-probabilities are useful in goodness-of-fit assessments, in comparing imperfect models, and in providing model weights to be used in model aggregation. D-probabilities avoid some of the disadvantages of Bayesian model probabilities, such as large sensitivity to prior choice, and tend to place higher weight on a greater diversity of models. In an application to linear model selection against a Gaussian process reference, we provide simple analytic forms for routine implementation and show that D-probabilities automatically penalize model complexity. Some asymptotic properties are described, and we provide interesting probabilistic interpretations of the proposed model weights. The framework is illustrated through simulation examples and an ozone data application. Supplementary materials for this aricle are available online.
AbstractList We propose a new approach for assigning weights to models using a divergence-based method (D-probabilities), relying on evaluating parametric models relative to a nonparametric Bayesian reference using Kullback–Leibler divergence. D-probabilities are useful in goodness-of-fit assessments, in comparing imperfect models, and in providing model weights to be used in model aggregation. D-probabilities avoid some of the disadvantages of Bayesian model probabilities, such as large sensitivity to prior choice, and tend to place higher weight on a greater diversity of models. In an application to linear model selection against a Gaussian process reference, we provide simple analytic forms for routine implementation and show that D-probabilities automatically penalize model complexity. Some asymptotic properties are described, and we provide interesting probabilistic interpretations of the proposed model weights. The framework is illustrated through simulation examples and an ozone data application. Supplementary materials for this aricle are available online.
We propose a new approach for assigning weights to models using a divergence-based method (D-probabilities), relying on evaluating parametric models relative to a nonparametric Bayesian reference using Kullback-Leibler divergence. D-probabilities are useful in goodness-of-fit assessments, in comparing imperfect models, and in providing model weights to be used in model aggregation. D-probabilities avoid some of the disadvantages of Bayesian model probabilities, such as large sensitivity to prior choice, and tend to place higher weight on a greater diversity of models. In an application to linear model selection against a Gaussian process reference, we provide simple analytic forms for routine implementation and show that D-probabilities automatically penalize model complexity. Some asymptotic properties are described, and we provide interesting probabilistic interpretations of the proposed model weights. The framework is illustrated through simulation examples and an ozone data application.We propose a new approach for assigning weights to models using a divergence-based method (D-probabilities), relying on evaluating parametric models relative to a nonparametric Bayesian reference using Kullback-Leibler divergence. D-probabilities are useful in goodness-of-fit assessments, in comparing imperfect models, and in providing model weights to be used in model aggregation. D-probabilities avoid some of the disadvantages of Bayesian model probabilities, such as large sensitivity to prior choice, and tend to place higher weight on a greater diversity of models. In an application to linear model selection against a Gaussian process reference, we provide simple analytic forms for routine implementation and show that D-probabilities automatically penalize model complexity. Some asymptotic properties are described, and we provide interesting probabilistic interpretations of the proposed model weights. The framework is illustrated through simulation examples and an ozone data application.
We propose a new approach for assigning weights to models using a divergence-based method ( ), relying on evaluating parametric models relative to a nonparametric Bayesian reference using Kullback-Leibler divergence. D-probabilities are useful in goodness-of-fit assessments, in comparing imperfect models, and in providing model weights to be used in model aggregation. D-probabilities avoid some of the disadvantages of Bayesian model probabilities, such as large sensitivity to prior choice, and tend to place higher weight on a greater diversity of models. In an application to linear model selection against a Gaussian process reference, we provide simple analytic forms for routine implementation and show that D-probabilities automatically penalize model complexity. Some asymptotic properties are described, and we provide interesting probabilistic interpretations of the proposed model weights. The framework is illustrated through simulation examples and an ozone data application.
We propose a new approach for assigning weights to models using a divergence-based method (D-probabilities), relying on evaluating parametric models relative to a nonparametric Bayesian reference using Kullback-Leibler divergence. D-probabilities are useful in goodness-of-fit assessments, in comparing imperfect models, and in providing model weights to be used in model aggregation. D-probabilities avoid some of the disadvantages of Bayesian model probabilities, such as large sensitivity to prior choice, and tend to place higher weight on a greater diversity of models. In an application to linear model selection against a Gaussian process reference, we provide simple analytic forms for routine implementation and show that D-probabilities automatically penalize model complexity. Some asymptotic properties are described, and we provide interesting probabilistic interpretations of the proposed model weights. The framework is illustrated through simulation examples and an ozone data application.
We propose a new approach for assigning weights to models using a divergence-based method (D-probabilities), relying on evaluating parametric models relative to a nonparametric Bayesian reference using Kullback-Leibler divergence. D-probabilities are useful in goodness-of-fit assessments, in comparing imperfect models, and in providing model weights to be used in model aggregation. D-probabilities avoid some of the disadvantages of Bayesian model probabilities, such as large sensitivity to prior choice, and tend to place higher weight on a greater diversity of models. In an application to linear model selection against a Gaussian process reference, we provide simple analytic forms for routine implementation and show that D-probabilities automatically penalize model complexity. Some asymptotic properties are described, and we provide interesting probabilistic interpretations of the proposed model weights. The framework is illustrated through simulation examples and an ozone data application. Supplementary materials for this aricle are available online.
Author Dunson, David B.
Li, Meng
AuthorAffiliation 2 Department of Statistical Science, Duke University
1 Department of Statistics, Rice University
AuthorAffiliation_xml – name: 1 Department of Statistics, Rice University
– name: 2 Department of Statistical Science, Duke University
Author_xml – sequence: 1
  givenname: Meng
  orcidid: 0000-0003-2123-2444
  surname: Li
  fullname: Li, Meng
  email: meng@rice.edu
  organization: Department of Statistics, Rice University
– sequence: 2
  givenname: David B.
  surname: Dunson
  fullname: Dunson, David B.
  organization: Department of Statistical Science, Duke University
BackLink https://www.ncbi.nlm.nih.gov/pubmed/33716357$$D View this record in MEDLINE/PubMed
BookMark eNqNkV1rFDEYhYNU7Lb6E5QFb7yZNR-TL4SibG0ttOiFRe9CkslsUzLJNpm19N87YbdFe1ENhJDkOYfDew7AXkzRAfAawQWCAr6HiGHUUrnAEMkFYgihFj4DM0QJbzBvf-6BWWWaCu2Dg1Ku4bS4EC_APiEcMUL5DBwt07DW2cfVXMdu_sP51dVYb2fD2uXe2XF-kToXyvyy1Ofj5ltORhsf_OhdeQme9zoU92p3HoLLk8_fl1-a86-nZ8tP542liI4Ncr2gfddiLiExknImODFOCDsFMdOGwiDNmJGOdVxaqY3UDPOeMMiN4eQQHG191xszuM66OGYd1Dr7Qec7lbRXf_9Ef6VW6ZfikrYYw8ng3c4gp5uNK6MafLEuBB1d2hSFKW4JahH7HxSiVhDGK_r2EXqdNjlOk1CTncRMEFqpN3-Gf0h938IE0C1gcyolu_4BQVDVttV926q2rXZtT7oPj3TWj3r0qc7Ah3-qP27VPvYpD_o25dCpUd-FlPuso_VFkactfgMccsBO
CitedBy_id crossref_primary_10_1038_s41524_020_00371_x
crossref_primary_10_1111_1365_2745_14278
crossref_primary_10_1515_snde_2022_0116
crossref_primary_10_1016_j_ijforecast_2020_11_002
crossref_primary_10_1214_21_BA1301
Cites_doi 10.1214/07-BA210
10.1007/BF00332312
10.1007/978-1-4613-8560-8_1
10.1007/BF00533058
10.1214/14-AOS1253
10.1080/01621459.1979.10481632
10.1214/009053607000000613
10.1214/07-AOS539
10.1214/aos/1021379858
10.1109/TIT.2018.2805844
10.1214/074921708000000156
10.1214/aos/1176342360
10.1214/08-AOS678
10.1002/9780470316870
10.1198/016214507000001337
10.1109/ACC.2003.1243393
10.1017/9781139029834
10.1214/ss/1009212519
10.1214/15-AOS1398
10.1214/12-EJS675
10.1080/01621459.1995.10476592
10.1214/14-EJS883
10.1007/s004400050210
10.1111/j.1751-5823.2005.tb00151.x
10.1109/ISIT.2008.4595271
10.1214/13-AOS1192
10.1214/aos/1028144851
10.1017/CBO9780511790485
10.1007/BF01577667
10.1111/j.2517-6161.1994.tb01996.x
10.1007/BF00535479
10.1016/j.csda.2009.05.018
10.1111/sjos.12159
10.1198/016214505000000646
10.1109/TAC.1974.1100705
10.2202/1544-6115.1309
10.1198/016214504000000386
10.1214/12-STS393
10.1111/j.2517-6161.1991.tb01812.x
10.1007/s10463-005-0014-8
10.1080/01621459.1985.10478157
ContentType Journal Article
Copyright 2019 American Statistical Association 2019
2019 American Statistical Association
Copyright_xml – notice: 2019 American Statistical Association 2019
– notice: 2019 American Statistical Association
DBID AAYXX
CITATION
NPM
8BJ
FQK
JBE
K9.
7X8
7S9
L.6
5PM
DOI 10.1080/01621459.2019.1611140
DatabaseName CrossRef
PubMed
International Bibliography of the Social Sciences (IBSS)
International Bibliography of the Social Sciences
International Bibliography of the Social Sciences
ProQuest Health & Medical Complete (Alumni)
MEDLINE - Academic
AGRICOLA
AGRICOLA - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
PubMed
International Bibliography of the Social Sciences (IBSS)
ProQuest Health & Medical Complete (Alumni)
MEDLINE - Academic
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList AGRICOLA
MEDLINE - Academic
PubMed

International Bibliography of the Social Sciences (IBSS)

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Statistics
EISSN 1537-274X
EndPage 1360
ExternalDocumentID PMC7954220
33716357
10_1080_01621459_2019_1611140
1611140
Genre Article
Journal Article
GrantInformation_xml – fundername: National Institute of Environmental Health Science of the United States National Institutes of Health
– fundername: National Institute of Environmental Health Sciences
– fundername: BRAIN Initiative
  grantid: R01ES027498
– fundername: NIEHS NIH HHS
  grantid: R01 ES027498
– fundername: NIMH NIH HHS
  grantid: R24 MH117529
GroupedDBID -DZ
-~X
..I
.7F
.QJ
0BK
0R~
29L
30N
4.4
5GY
5RE
692
7WY
85S
8FL
AAAVZ
AABCJ
AAENE
AAGDL
AAHBH
AAHIA
AAJMT
AALDU
AAMIU
AAPUL
AAQRR
ABCCY
ABEHJ
ABFAN
ABFIM
ABJNI
ABLIJ
ABLJU
ABPAQ
ABPEM
ABPFR
ABPPZ
ABRLO
ABTAI
ABUFD
ABXUL
ABXYU
ABYWD
ACGFO
ACGFS
ACGOD
ACIWK
ACMTB
ACNCT
ACTIO
ACTMH
ADCVX
ADGTB
ADLSF
ADMHG
ADXHL
AEISY
AENEX
AEOZL
AEPSL
AEYOC
AFFNX
AFRVT
AFVYC
AFXHP
AGDLA
AGMYJ
AHDZW
AIJEM
AIYEW
AKBVH
AKOOK
ALMA_UNASSIGNED_HOLDINGS
ALQZU
AMVHM
AQRUH
AQTUD
AVBZW
AWYRJ
BLEHA
CCCUG
CJ0
CS3
D0L
DGEBU
DKSSO
DU5
EBS
E~A
E~B
F5P
FJW
GTTXZ
H13
HF~
HZ~
H~9
H~P
IPNFZ
J.P
JAS
JMS
K60
K6~
KYCEM
LU7
M4Z
MS~
MW2
NA5
NY~
O9-
OFU
OK1
P2P
RIG
RNANH
ROSJB
RTWRZ
RWL
RXW
S-T
SNACF
TAE
TASJS
TBQAZ
TDBHL
TEJ
TFL
TFT
TFW
TN5
TOXWX
TTHFI
TUROJ
U5U
UPT
UT5
UU3
WH7
WZA
YQT
YYM
ZGOLN
~S~
AAYXX
CITATION
.-4
.GJ
07G
1OL
2AX
3R3
3V.
7X7
88E
88I
8AF
8C1
8FE
8FG
8FI
8FJ
8G5
8P6
8R4
8R5
AAFWJ
AAIKQ
AAKBW
ABBHK
ABEFU
ABJCF
ABPQH
ABUWG
ABXSQ
ABYAD
ACAGQ
ACGEE
ACTWD
ACUBG
ADBBV
ADODI
ADULT
ADYSH
AELPN
AEUMN
AEUPB
AFKRA
AFQQW
AFSUE
AGCQS
AGLEN
AGROQ
AHMOU
AI.
AIHAF
ALCKM
ALIPV
ALRMG
AMATQ
AMEWO
AMXXU
AQUVI
AZQEC
BCCOT
BENPR
BEZIV
BGLVJ
BKNYI
BKOMP
BPHCQ
BPLKW
BVXVI
C06
CCPQU
CRFIH
DMQIW
DQDLB
DSRWC
DWIFK
DWQXO
E.L
ECEWR
EJD
FEDTE
FRNLG
FVMVE
FYUFA
GNUQQ
GROUPED_ABI_INFORM_COMPLETE
GROUPED_ABI_INFORM_RESEARCH
GUQSH
HCIFZ
HGD
HMCUK
HQ6
HVGLF
IAO
IEA
IGG
IOF
IPO
IPSME
IVXBP
JAAYA
JBMMH
JBZCM
JENOY
JHFFW
JKQEH
JLEZI
JLXEF
JPL
JSODD
JST
K9-
KQ8
L6V
LJTGL
M0C
M0R
M0T
M1P
M2O
M2P
M7S
MVM
N95
NHB
NPM
NUSFT
P-O
PADUT
PQBIZ
PQBZA
PQQKQ
PRG
PROAC
PSQYO
PTHSS
Q2X
QCRFL
RNS
S0X
SA0
SJN
TAQ
TFMCV
UB9
UKHRP
UQL
VH1
VOH
VXZ
WHG
YXB
YYP
ZCG
ZGI
ZUP
ZXP
8BJ
FQK
JBE
K9.
7X8
7S9
L.6
5PM
ID FETCH-LOGICAL-c515t-1ef85fd427903b9576873be88c371b37108b1a66b9e6d79c9ab9a627f3607bb73
IEDL.DBID TFW
ISICitedReferencesCount 6
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000472249000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0162-1459
1537-274X
IngestDate Tue Nov 04 01:58:54 EST 2025
Fri Oct 03 00:07:33 EDT 2025
Sun Nov 09 14:39:13 EST 2025
Sun Nov 09 07:03:54 EST 2025
Wed Feb 19 02:29:14 EST 2025
Tue Nov 18 22:38:55 EST 2025
Sat Nov 29 03:56:44 EST 2025
Mon Oct 20 23:49:22 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 531
Keywords Gaussian process
Model selection
Nonparametric Bayes
M-open
Kullback-Leibler divergence
Model aggregation
Gibbs posterior
Posterior probabilities
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c515t-1ef85fd427903b9576873be88c371b37108b1a66b9e6d79c9ab9a627f3607bb73
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0003-2123-2444
PMID 33716357
PQID 2439268350
PQPubID 41715
PageCount 12
ParticipantIDs crossref_primary_10_1080_01621459_2019_1611140
proquest_miscellaneous_2501483670
crossref_citationtrail_10_1080_01621459_2019_1611140
informaworld_taylorfrancis_310_1080_01621459_2019_1611140
proquest_journals_2439268350
pubmed_primary_33716357
pubmedcentral_primary_oai_pubmedcentral_nih_gov_7954220
proquest_miscellaneous_2524314160
PublicationCentury 2000
PublicationDate 2020-07-02
PublicationDateYYYYMMDD 2020-07-02
PublicationDate_xml – month: 07
  year: 2020
  text: 2020-07-02
  day: 02
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Alexandria
PublicationTitle Journal of the American Statistical Association
PublicationTitleAlternate J Am Stat Assoc
PublicationYear 2020
Publisher Taylor & Francis
Taylor & Francis Ltd
Publisher_xml – name: Taylor & Francis
– name: Taylor & Francis Ltd
References Boltzmann L (CIT0012) 1878; 78
CIT0030
CIT0032
CIT0031
CIT0034
CIT0033
CIT0036
CIT0035
CIT0037
CIT0039
CIT0041
CIT0040
CIT0043
CIT0042
CIT0001
CIT0045
CIT0044
Barron A. R (CIT0008) 1998; 6
Bahadur R. R (CIT0006) 1967
CIT0003
CIT0002
CIT0046
CIT0005
CIT0049
CIT0004
Rasmussen C. E. (CIT0038) 2006
CIT0048
CIT0007
CIT0009
Clyde M. A. (CIT0020) 2013
CIT0050
CIT0010
CIT0011
CIT0014
CIT0013
CIT0016
CIT0015
CIT0018
CIT0017
CIT0019
van der Vaart A. (CIT0047) 2011; 12
Hjort N. L. (CIT0028); 2010
CIT0021
CIT0023
CIT0022
CIT0025
CIT0024
CIT0027
CIT0026
CIT0029
References_xml – ident: CIT0048
  doi: 10.1214/07-BA210
– ident: CIT0011
  doi: 10.1007/BF00332312
– ident: CIT0004
  doi: 10.1007/978-1-4613-8560-8_1
– volume: 6
  start-page: 27
  volume-title: eds. J. M. Bernardo, J. O. Berger, A. P. Dawid, and A. F. M. Smith
  year: 1998
  ident: CIT0008
– ident: CIT0016
  doi: 10.1007/BF00533058
– ident: CIT0018
  doi: 10.1214/14-AOS1253
– ident: CIT0023
  doi: 10.1080/01621459.1979.10481632
– ident: CIT0002
– ident: CIT0045
  doi: 10.1214/009053607000000613
– ident: CIT0035
  doi: 10.1214/07-AOS539
– ident: CIT0030
  doi: 10.1214/aos/1021379858
– ident: CIT0014
  doi: 10.1109/TIT.2018.2805844
– volume-title: Gaussian Processes for Machine Learning, Adaptive Computation and Machine Learning
  year: 2006
  ident: CIT0038
– ident: CIT0044
  doi: 10.1214/074921708000000156
– start-page: 483
  volume-title: “Bayesian Model Averaging in the M-Open Framework
  year: 2013
  ident: CIT0020
– ident: CIT0022
  doi: 10.1214/aos/1176342360
– ident: CIT0046
  doi: 10.1214/08-AOS678
– ident: CIT0009
  doi: 10.1002/9780470316870
– ident: CIT0036
  doi: 10.1198/016214507000001337
– ident: CIT0021
  doi: 10.1109/ACC.2003.1243393
– ident: CIT0025
  doi: 10.1017/9781139029834
– ident: CIT0029
  doi: 10.1214/ss/1009212519
– ident: CIT0050
  doi: 10.1214/15-AOS1398
– ident: CIT0033
  doi: 10.1214/12-EJS675
– ident: CIT0032
  doi: 10.1080/01621459.1995.10476592
– ident: CIT0005
  doi: 10.1214/14-EJS883
– ident: CIT0007
  doi: 10.1007/s004400050210
– ident: CIT0042
– ident: CIT0027
  doi: 10.1111/j.1751-5823.2005.tb00151.x
– ident: CIT0037
  doi: 10.1109/ISIT.2008.4595271
– ident: CIT0010
  doi: 10.1214/13-AOS1192
– ident: CIT0015
  doi: 10.1214/aos/1028144851
– ident: CIT0019
  doi: 10.1017/CBO9780511790485
– volume: 2010
  volume-title: Bayesian Nonparametrics
  ident: CIT0028
– ident: CIT0031
  doi: 10.1007/BF01577667
– ident: CIT0024
  doi: 10.1111/j.2517-6161.1994.tb01996.x
– volume: 78
  start-page: 7
  year: 1878
  ident: CIT0012
  publication-title: Wiener Berichte
– ident: CIT0040
  doi: 10.1007/BF00535479
– ident: CIT0026
  doi: 10.1016/j.csda.2009.05.018
– ident: CIT0041
  doi: 10.1111/sjos.12159
– ident: CIT0017
  doi: 10.1198/016214505000000646
– ident: CIT0003
  doi: 10.1109/TAC.1974.1100705
– ident: CIT0043
  doi: 10.2202/1544-6115.1309
– start-page: 13
  volume-title: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics
  year: 1967
  ident: CIT0006
– ident: CIT0049
  doi: 10.1198/016214504000000386
– ident: CIT0039
  doi: 10.1214/12-STS393
– ident: CIT0001
  doi: 10.1111/j.2517-6161.1991.tb01812.x
– ident: CIT0034
  doi: 10.1007/s10463-005-0014-8
– ident: CIT0013
  doi: 10.1080/01621459.1985.10478157
– volume: 12
  start-page: 2095
  year: 2011
  ident: CIT0047
  publication-title: The Journal of Machine Learning Research
SSID ssj0000788
Score 2.3914695
Snippet We propose a new approach for assigning weights to models using a divergence-based method (D-probabilities), relying on evaluating parametric models relative...
We propose a new approach for assigning weights to models using a divergence-based method ( ), relying on evaluating parametric models relative to a...
SourceID pubmedcentral
proquest
pubmed
crossref
informaworld
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1349
SubjectTerms Asymptotic properties
Atmospheric ozone
Bayesian analysis
Bayesian theory
Computer simulation
Gaussian process
Gibbs posterior
Goodness of fit
Kullback-Leibler divergence
Linear analysis
linear models
M-open
Model aggregation
Model selection
Morality
normal distribution
ozone
Property
Regression analysis
Simulation
Statistical methods
Statistics
Weighting
Title Comparing and Weighting Imperfect Models Using D-Probabilities
URI https://www.tandfonline.com/doi/abs/10.1080/01621459.2019.1611140
https://www.ncbi.nlm.nih.gov/pubmed/33716357
https://www.proquest.com/docview/2439268350
https://www.proquest.com/docview/2501483670
https://www.proquest.com/docview/2524314160
https://pubmed.ncbi.nlm.nih.gov/PMC7954220
Volume 115
WOSCitedRecordID wos000472249000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAWR
  databaseName: Taylor & Francis Online Journals
  customDbUrl:
  eissn: 1537-274X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000788
  issn: 0162-1459
  databaseCode: TFW
  dateStart: 19220301
  isFulltext: true
  titleUrlDefault: https://www.tandfonline.com
  providerName: Taylor & Francis
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELagYujC-1EoVZBYXWo7ieMFCRUqWKoORe0WxUkMSChFffD7uXMetAjoAEOGyL5EPvt8n-3zd4Rcuq7wVcBc6kXGp5iikGoWKwreRWrJU3Ai2iabkP1-MB6rQRFNOCvCKnENbXKiCDtXo3FHelZGxF0BSkF-bbxmwlQbIAtgely1g-tH0xz2Rp9zsbSZJ1GCokh5h-enr6x4pxXu0u8Q6NdAyiXP1Nv5hzbtku0Cljo3-TjaIxtptk_qiERzIucDct3NMxZmTw78xBnZLVV8ewDgPcWgEAfzqr3OHBuF4NzSwRTmCht7C6vxQ_LYuxt272mRfIHGAHHmlKUm8Ezicqk6Qitclkih0yCIhWQank6gWeT7WqV-IlWsIq0in0sj_I7UWoojUssmWXpCHJYkOgHzTmKPu8a4igltBPeMSQTgq6RB3FLpYVwwk2OCjNeQlQSmhXZC1E5YaKdB2pXYW07NsU5ALfdoOLd7IiZPYBKKNbLNsvvDwspnIQc0x33AsFB8URWDfeKhS5SlkwXUwYPbAGnyfqsDX2IAjaHOcT6iqhYJUDVyBjaIXBlrVQXkB18tyV6eLU-4VJ7Leef0D80-I3WOGwy4n82bpDafLtJzshW_w-ibtsimHActa3EfVw0jGA
linkProvider Taylor & Francis
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT8MwDI4QIMGF92MwoEhcM5akbZoLEhpMIGDiMMRuUdM2gDR1aAx-P3bajg3xOMChhypxq7hx_MV1PhNy5PsiVBHzaRDbkGKJQmpYoih4F2kkz8CJGFdsQnY6Ua-nJs_CYFol7qFtQRTh1mo0bgxGVylxxwBTkGAbz5kw1QDMAqAetu1zAfha5M_vtu8_VmPpak-iCEWZ6hTPd4-Z8k9T7KVfYdDPqZQTvqm9_B-jWiFLJTL1TouptEpmsnyNLCIYLbic18lJqyhamD948Bbv3kVV8e4SsPcQ80I8LK3Wf_FcIoJ3Rm-HsFy49FvYkG-Qu_Z5t3VBy_oLNAGUM6Iss1FgU59L1RRG4c5ECpNFUSIkM3A1I8PiMDQqC1OpEhUbFYdcWhE2pTFSbJLZfJBn28RjaWpSsPA0Cbhvra-YMFbwwNpUAMRKa8SvtK6Tkpwca2T0Nas4TEvtaNSOLrVTI42x2HPBzvGbgJr8pHrkwiK2qGGixS-y9er769LQXzQHQMdDgLHQfDhuBhPF_y5xng1eoQ_-u42QKe-nPvAkBugY-mwVU2o8IgGqRtrAGpFTk23cASnCp1vyp0dHFS5V4HPe3PnDsA_IwkX35lpfX3audskix3gDhrd5ncyOhq_ZHplP3mAmDved4b0D32UmWg
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NT-wgECdGjfHi99P1sybvim-BFsrFxKgbjWazB43eSClFTTbV7K7-_c7QdnWNPg966KGBacMwAz9g-A0hf-NYSJ2ymCaZlxRTFFLLck1hdlFW8QImERuSTahuN7291b06mnBYh1XiGtpXRBFhrEbnfnK-iYj7BygF-bXxmgnTBwBZANPDqn0GoLNEI7_q3LwNxiqknkQRijLNJZ6vPjMxPU2Ql34GQT9GUr6bmjqLv9CoJbJQ49LoqDKkZTJVlCtkHqFoxeS8Sg6Pq5SF5V0EP4luwp4qvp0D8h5gVEiEidX6wyiEIUQntDeAwSIE38JyfI1cd06vjs9onX2B5oBxRpQVPk28i7nSbWE1rkuUsEWa5kIxC087tSyT0upCOqVznVmdSa68kG1lrRJ_yHT5WBYbJGLOWQf-7fKEx97HmgnrBU-8dwIAlmuRuFG6yWtqcsyQ0TesYTCttWNQO6bWToscjMWeKm6O7wT0-x41o7Ap4qsMJkZ8I7vddL-p3XxoOMA5LgHEQvH-uBgcFE9dsrJ4fIY6eHKbIk_e_-rAlxhgY6izXlnUuEUCVI2kgS2iJmxtXAEJwidLyof7QBSudBJz3t78QbP3yFzvpGMuz7sXW2Se42YD7m3zbTI9GjwXO2Q2fwFDHOwGt3sFP-8lDA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Comparing+and+Weighting+Imperfect+Models+Using+D-Probabilities&rft.jtitle=Journal+of+the+American+Statistical+Association&rft.au=Li%2C+Meng&rft.au=Dunson%2C+David+B&rft.date=2020-07-02&rft.issn=1537-274X&rft.volume=115&rft.issue=531+p.1349-1360&rft.spage=1349&rft.epage=1360&rft_id=info:doi/10.1080%2F01621459.2019.1611140&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-1459&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-1459&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-1459&client=summon