An adapted vector autoregressive expectation maximization imputation algorithm for climate data networks

Missingness in historical climate data networks is a pervasive phenomenon due to the conditions under which these measurements are made. Accurate estimation of these data is a critical issue as projections of future climate depend on a reliable historical climate record. After all, how can the impac...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Wiley interdisciplinary reviews. Computational statistics Ročník 12; číslo 6; s. e1494 - n/a
Hlavní autoři:	Washington, Benjamin J., Seymour, Lynne
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Hoboken, USA John Wiley & Sons, Inc 01.11.2020 Wiley Subscription Services, Inc
Témata:	Algorithms Climate change climate data Climatic data Computer applications Environmental impact expectation–maximization Iterative methods Missing data Multivariate analysis multivariate infilling Networks Numerical weather forecasting Root-mean-square errors Stations Statistical methods Stochastic processes Temperature data vector autoregression Weather forecasting
ISSN:	1939-5108, 1939-0068
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Missingness in historical climate data networks is a pervasive phenomenon due to the conditions under which these measurements are made. Accurate estimation of these data is a critical issue as projections of future climate depend on a reliable historical climate record. After all, how can the impact of climate change be reliably forecasted when a large proportion of historical climate records are permeated with missing data? We propose an iterative multivariate infilling algorithm and explore its effectiveness on three United States temperature networks of varying densities (number of stations per unit area). Although other multivariate data are not explored here, the application of this infilling procedure is not restricted to climate networks exclusively. We also explore its utility as a function of the type of missing data (i.e., whether or not there is a mechanism or pattern behind the missing observations themselves) and the proportion of missing data within the network. As one may expect, we observe a slightly smaller root mean square error (RMSE) for temperature networks with more stations and less missingness. Somewhat surprisingly, the RMSE tends to be lower for data which is missing at random (there is some mechanism behind the missing data) rather than for data that is missing completely at random (no mechanism behind the missing data). Not surprisingly, the RMSE is largest for data which is missing not at random (missing data are directly related to the values of the observations themselves). Perhaps the most surprising result observed in these networks is that the inclusion of lagged temperature data does not necessarily improve the accuracy of data imputation. The typical RMSE for monthly minimum temperature networks varies from around 1.5 to 2.5°C. This article is categorized under: Data: Types and Structure > Massive Data Data: Types and Structure > Image and Spatial Data Data: Types and Structure > Time Series, Stochastic Processes, and Functional Data Applications of Computational Statistics > Computational Climate Change and Numerical Weather Forecasting The RMSE of an iterative adapted vector autoregressive expectation–maximization algorithm as a function of Iteration (left) and autoregressive order (right) for three types of missing data MCAR (top), MAR (middle) and MNAR (bottom).
AbstractList	Missingness in historical climate data networks is a pervasive phenomenon due to the conditions under which these measurements are made. Accurate estimation of these data is a critical issue as projections of future climate depend on a reliable historical climate record. After all, how can the impact of climate change be reliably forecasted when a large proportion of historical climate records are permeated with missing data? We propose an iterative multivariate infilling algorithm and explore its effectiveness on three United States temperature networks of varying densities (number of stations per unit area). Although other multivariate data are not explored here, the application of this infilling procedure is not restricted to climate networks exclusively. We also explore its utility as a function of the type of missing data (i.e., whether or not there is a mechanism or pattern behind the missing observations themselves) and the proportion of missing data within the network. As one may expect, we observe a slightly smaller root mean square error (RMSE) for temperature networks with more stations and less missingness. Somewhat surprisingly, the RMSE tends to be lower for data which is missing at random (there is some mechanism behind the missing data) rather than for data that is missing completely at random (no mechanism behind the missing data). Not surprisingly, the RMSE is largest for data which is missing not at random (missing data are directly related to the values of the observations themselves). Perhaps the most surprising result observed in these networks is that the inclusion of lagged temperature data does not necessarily improve the accuracy of data imputation. The typical RMSE for monthly minimum temperature networks varies from around 1.5 to 2.5°C.This article is categorized under:Data: Types and Structure > Massive DataData: Types and Structure > Image and Spatial DataData: Types and Structure > Time Series, Stochastic Processes, and Functional DataApplications of Computational Statistics > Computational Climate Change and Numerical Weather Forecasting Missingness in historical climate data networks is a pervasive phenomenon due to the conditions under which these measurements are made. Accurate estimation of these data is a critical issue as projections of future climate depend on a reliable historical climate record. After all, how can the impact of climate change be reliably forecasted when a large proportion of historical climate records are permeated with missing data? We propose an iterative multivariate infilling algorithm and explore its effectiveness on three United States temperature networks of varying densities (number of stations per unit area). Although other multivariate data are not explored here, the application of this infilling procedure is not restricted to climate networks exclusively. We also explore its utility as a function of the type of missing data (i.e., whether or not there is a mechanism or pattern behind the missing observations themselves) and the proportion of missing data within the network. As one may expect, we observe a slightly smaller root mean square error (RMSE) for temperature networks with more stations and less missingness. Somewhat surprisingly, the RMSE tends to be lower for data which is missing at random (there is some mechanism behind the missing data) rather than for data that is missing completely at random (no mechanism behind the missing data). Not surprisingly, the RMSE is largest for data which is missing not at random (missing data are directly related to the values of the observations themselves). Perhaps the most surprising result observed in these networks is that the inclusion of lagged temperature data does not necessarily improve the accuracy of data imputation. The typical RMSE for monthly minimum temperature networks varies from around 1.5 to 2.5°C. This article is categorized under: Data: Types and Structure > Massive Data Data: Types and Structure > Image and Spatial Data Data: Types and Structure > Time Series, Stochastic Processes, and Functional Data Applications of Computational Statistics > Computational Climate Change and Numerical Weather Forecasting The RMSE of an iterative adapted vector autoregressive expectation–maximization algorithm as a function of Iteration (left) and autoregressive order (right) for three types of missing data MCAR (top), MAR (middle) and MNAR (bottom). Missingness in historical climate data networks is a pervasive phenomenon due to the conditions under which these measurements are made. Accurate estimation of these data is a critical issue as projections of future climate depend on a reliable historical climate record. After all, how can the impact of climate change be reliably forecasted when a large proportion of historical climate records are permeated with missing data? We propose an iterative multivariate infilling algorithm and explore its effectiveness on three United States temperature networks of varying densities (number of stations per unit area). Although other multivariate data are not explored here, the application of this infilling procedure is not restricted to climate networks exclusively. We also explore its utility as a function of the type of missing data (i.e., whether or not there is a mechanism or pattern behind the missing observations themselves) and the proportion of missing data within the network. As one may expect, we observe a slightly smaller root mean square error (RMSE) for temperature networks with more stations and less missingness. Somewhat surprisingly, the RMSE tends to be lower for data which is missing at random (there is some mechanism behind the missing data) rather than for data that is missing completely at random (no mechanism behind the missing data). Not surprisingly, the RMSE is largest for data which is missing not at random (missing data are directly related to the values of the observations themselves). Perhaps the most surprising result observed in these networks is that the inclusion of lagged temperature data does not necessarily improve the accuracy of data imputation. The typical RMSE for monthly minimum temperature networks varies from around 1.5 to 2.5°C. This article is categorized under: Data: Types and Structure > Massive Data Data: Types and Structure > Image and Spatial Data Data: Types and Structure > Time Series, Stochastic Processes, and Functional Data Applications of Computational Statistics > Computational Climate Change and Numerical Weather Forecasting
Author	Seymour, Lynne Washington, Benjamin J.
Author_xml	– sequence: 1 givenname: Benjamin J. orcidid: 0000-0003-1816-5033 surname: Washington fullname: Washington, Benjamin J. email: bwash318@uga.edu organization: University of Georgia – sequence: 2 givenname: Lynne orcidid: 0000-0002-8023-5269 surname: Seymour fullname: Seymour, Lynne organization: University of Georgia
BookMark	eNp9UMtOwzAQtBBItIUDfxCJE4e0tuPEybGqeFSqxAEQx8hN1q1LEgfb6YOvxyU9IYEsrXdHs7O7M0TnjW4AoRuCxwRjOtmpwo4Jy9gZGpAsykKMk_T8lMcEp5doaO3Go9y_AVpPm0CUonVQBlsonDaB6HyElQFr1RYC2LceF07pJqjFXtXqqy9U3XYnXFQrbZRb14H0AkWlauEgKIUTQQNup82HvUIXUlQWrk__CL093L_OnsLF8-N8Nl2EBc04CzOIcEyZpFGcRTgpJZEUWBYXS8qiRDKREE4I53QJcZGlMuUCJ4IkEigpsaDRCN32uq3Rnx1Yl290Zxo_MqfM-0IYJ9yz7npWYbS1BmTeGr-0OeQE50cj86OR-dFIz5384haqv9sZoar_OnaqgsPf0vn7fPby0_EN7cmJWQ
CitedBy_id	crossref_primary_10_5194_ascmo_9_1_2023
Cites_doi	10.1175/1520-0442(1995)008<2787:CTSWPC>2.0.CO;2 10.1016/j.atmosenv.2004.02.026 10.1007/s00704-012-0723-x 10.1175/1520-0442(1996)009<1403:ROHSST>2.0.CO;2 10.1016/S1364-8152(01)00008-1 10.1017/S0003055401000235 10.1016/j.neucom.2017.03.097 10.1002/joc.6129 10.1175/1520-0442(2001)014<0853:AOICDE>2.0.CO;2 10.1175/2011BAMS3015.1 10.1201/9781439821862 10.1007/978-3-319-24277-4 10.1093/biomet/63.3.581 10.2307/1912017 10.1201/b11826
ContentType	Journal Article
Copyright	2019 Wiley Periodicals, Inc. 2020 Wiley Periodicals LLC.
Copyright_xml	– notice: 2019 Wiley Periodicals, Inc. – notice: 2020 Wiley Periodicals LLC.
DBID	AAYXX CITATION 7QH 7UA C1K F1W H96 H97 JQ2 L.G
DOI	10.1002/wics.1494
DatabaseName	CrossRef Aqualine Water Resources Abstracts Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Aquatic Science & Fisheries Abstracts (ASFA) 3: Aquatic Pollution & Environmental Quality ProQuest Computer Science Collection Aquatic Science & Fisheries Abstracts (ASFA) Professional
DatabaseTitle	CrossRef Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources ASFA: Aquatic Sciences and Fisheries Abstracts ProQuest Computer Science Collection Aqualine Aquatic Science & Fisheries Abstracts (ASFA) 3: Aquatic Pollution & Environmental Quality Water Resources Abstracts Environmental Sciences and Pollution Management
DatabaseTitleList	Aquatic Science & Fisheries Abstracts (ASFA) Professional CrossRef
DeliveryMethod	fulltext_linktorsrc
Discipline	Mathematics
EISSN	1939-0068
EndPage	n/a
ExternalDocumentID	10_1002_wics_1494 WICS1494
Genre	reviewArticle
GroupedDBID	05W 0R~ 1OC 1VH 33P 4.4 53G 5DZ 8-1 A00 AAESR AAHHS AAHQN AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCUV ACAHQ ACBWZ ACCFJ ACCZN ACGFS ACPOU ACRPL ACXBN ACXQS ACYXJ ADBBV ADEOM ADKYN ADMGS ADNMO ADZMN AEEZP AEIGN AEQDE AEUYR AFBPY AFFPM AFGKR AFPWT AFRAH AFWVQ AHBTC AITYG AIURR AIWBW AJBDE AJXKR ALMA_UNASSIGNED_HOLDINGS ALUQN AMBMR AMYDB ASPBG AUFTA AVWKF AZBYB AZFZN AZVAB BDRZF BHBCM BMNLL BRXPI DCZOG DRFUL DRSTM EBS EJD F5P FEDTE G-S GODZA HGLYW HVGLF HZ~ LATKE LEEKS LITHE LOXES LUTES LYRES MEWTI MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM MY. MY~ O66 O9- P2W RNS ROL SUPJJ WBKPD WIH WIK WOHZO WXSBR WYISQ WYJ XBAML XV2 ZZTAW AAYXX AEYWJ AGQPQ AGYGG CITATION LH4 7QH 7UA C1K F1W H96 H97 JQ2 L.G
ID	FETCH-LOGICAL-c2974-9e30524f2359306df1f2e495cb2436f4a61711772be5c98f87a06a16fe21d0a23
IEDL.DBID	DRFUL
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000504200800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1939-5108
IngestDate	Fri Jul 25 22:45:30 EDT 2025 Tue Nov 18 22:36:23 EST 2025 Sat Nov 29 03:49:26 EST 2025 Wed Jan 22 16:31:51 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	6
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c2974-9e30524f2359306df1f2e495cb2436f4a61711772be5c98f87a06a16fe21d0a23
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-8023-5269 0000-0003-1816-5033
PQID	2449414717
PQPubID	2034593
PageCount	15
ParticipantIDs	proquest_journals_2449414717 crossref_primary_10_1002_wics_1494 crossref_citationtrail_10_1002_wics_1494 wiley_primary_10_1002_wics_1494_WICS1494
PublicationCentury	2000
PublicationDate	November/December 2020 2020-11-00 20201101
PublicationDateYYYYMMDD	2020-11-01
PublicationDate_xml	– month: 11 year: 2020 text: November/December 2020
PublicationDecade	2020
PublicationPlace	Hoboken, USA
PublicationPlace_xml	– name: Hoboken, USA – name: Hoboken
PublicationTitle	Wiley interdisciplinary reviews. Computational statistics
PublicationYear	2020
Publisher	John Wiley & Sons, Inc Wiley Subscription Services, Inc
Publisher_xml	– name: John Wiley & Sons, Inc – name: Wiley Subscription Services, Inc
References	2018; 276 1976; 63 1980; 48 2012; 112 2001 2012 2000 2004; 38 2011; 92 2019; 39 1997 2018 2016 2001; 27 2014; 29 2013 2001; 14 2001; 95 1996; 9 1995; 8 1999 e_1_2_9_20_1 e_1_2_9_11_1 e_1_2_9_22_1 e_1_2_9_21_1 e_1_2_9_13_1 e_1_2_9_12_1 e_1_2_9_23_1 e_1_2_9_8_1 e_1_2_9_6_1 e_1_2_9_5_1 e_1_2_9_4_1 e_1_2_9_2_1 Krishnamoorthy A. (e_1_2_9_7_1) 2013 Raghunathan T. E. (e_1_2_9_10_1) 2001; 27 Ferrari G. T. (e_1_2_9_3_1) 2014; 29 e_1_2_9_9_1 e_1_2_9_15_1 Van Buuren S. (e_1_2_9_19_1) 1999 e_1_2_9_14_1 e_1_2_9_17_1 e_1_2_9_16_1 e_1_2_9_18_1
References_xml	– volume: 95 start-page: 49 issue: 1 year: 2001 end-page: 69 article-title: Analyzing incomplete political science data: An alternative algorithm for multiple imputation publication-title: American Political Science Review – start-page: 70 year: 2013 end-page: 72 – volume: 29 start-page: 21 year: 2014 end-page: 28 article-title: Missing data imputation of climate datasets: Implications to modeling extreme drought events publication-title: Brazilian Journal of Meteorology – volume: 14 start-page: 853 issue: 5 year: 2001 end-page: 871 article-title: Analysis of incomplete climate data: Estimation of mean values and covariance matrices and imputation of missing values publication-title: Journal of Climate – volume: 48 start-page: 1 year: 1980 end-page: 48 article-title: Macroeconomics and reality publication-title: Econometrica: Journal of the Econometric Society – volume: 92 start-page: 704 year: 2011 end-page: 708 article-title: The integrated surface database: Recent developments and partnerships publication-title: Bulletin of the American – volume: 38 start-page: 2895 issue: 18 year: 2004 end-page: 2907 article-title: Methods for imputation of missing values in air quality data sets publication-title: Atmospheric Environment – volume: 27 start-page: 85 issue: 1 year: 2001 end-page: 96 article-title: A multivariate technique for multiply imputing missing values using a sequence of regression models publication-title: Survey Methodology – volume: 8 start-page: 2787 issue: 11 year: 1995 end-page: 2809 article-title: Climatological time series with periodic correlation publication-title: Journal of Climate – year: 2001 – volume: 9 start-page: 1403 issue: 6 year: 1996 end-page: 1420 article-title: Reconstruction of historical sea surface temperatures using empirical orthogonal functions publication-title: Journal of Climate – volume: 39 start-page: 5104 year: 2019 end-page: 5123 article-title: Simulation of temperature series and small networks from data publication-title: International Journal of Climatology – volume: 63 start-page: 581 issue: 3 year: 1976 end-page: 592 article-title: Inference and missing data publication-title: Biometrika – year: 1997 – year: 2000 – volume: 276 start-page: 23 year: 2018 end-page: 30 article-title: Handling missing data in multivariate time series using a vector autoregressive model‐imputation (VAR‐IM) algorithm publication-title: Neurocomputing – year: 2016 – year: 2018 – volume: 112 start-page: 143 year: 2012 end-page: 167 article-title: Comparison of missing value imputation methods in time series: The case of Turkish meteorological data publication-title: Theoretical and Applied Climatology – year: 1999 – year: 2012 – volume: 29 start-page: 21 year: 2014 ident: e_1_2_9_3_1 article-title: Missing data imputation of climate datasets: Implications to modeling extreme drought events publication-title: Brazilian Journal of Meteorology – ident: e_1_2_9_8_1 doi: 10.1175/1520-0442(1995)008<2787:CTSWPC>2.0.CO;2 – ident: e_1_2_9_5_1 doi: 10.1016/j.atmosenv.2004.02.026 – volume: 27 start-page: 85 issue: 1 year: 2001 ident: e_1_2_9_10_1 article-title: A multivariate technique for multiply imputing missing values using a sequence of regression models publication-title: Survey Methodology – ident: e_1_2_9_22_1 doi: 10.1007/s00704-012-0723-x – ident: e_1_2_9_16_1 doi: 10.1175/1520-0442(1996)009<1403:ROHSST>2.0.CO;2 – ident: e_1_2_9_4_1 doi: 10.1016/S1364-8152(01)00008-1 – ident: e_1_2_9_6_1 doi: 10.1017/S0003055401000235 – ident: e_1_2_9_2_1 doi: 10.1016/j.neucom.2017.03.097 – ident: e_1_2_9_20_1 doi: 10.1002/joc.6129 – ident: e_1_2_9_13_1 doi: 10.1175/1520-0442(2001)014<0853:AOICDE>2.0.CO;2 – ident: e_1_2_9_17_1 – ident: e_1_2_9_15_1 doi: 10.1175/2011BAMS3015.1 – ident: e_1_2_9_12_1 doi: 10.1201/9781439821862 – ident: e_1_2_9_23_1 – ident: e_1_2_9_21_1 doi: 10.1007/978-3-319-24277-4 – ident: e_1_2_9_9_1 – ident: e_1_2_9_11_1 doi: 10.1093/biomet/63.3.581 – ident: e_1_2_9_14_1 doi: 10.2307/1912017 – volume-title: Flexible multivariate imputation by MICE year: 1999 ident: e_1_2_9_19_1 – start-page: 70 volume-title: 2013 signal processing: Algorithms, architectures, arrangements, and applications (SPA) year: 2013 ident: e_1_2_9_7_1 – ident: e_1_2_9_18_1 doi: 10.1201/b11826
SSID	ssj0067676
Score	2.1823347
SecondaryResourceType	review_article
Snippet	Missingness in historical climate data networks is a pervasive phenomenon due to the conditions under which these measurements are made. Accurate estimation of...
SourceID	proquest crossref wiley
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	e1494
SubjectTerms	Algorithms Climate change climate data Climatic data Computer applications Environmental impact expectation–maximization Iterative methods Missing data Multivariate analysis multivariate infilling Networks Numerical weather forecasting Root-mean-square errors Stations Statistical methods Stochastic processes Temperature data vector autoregression Weather forecasting
Title	An adapted vector autoregressive expectation maximization imputation algorithm for climate data networks
URI	https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fwics.1494 https://www.proquest.com/docview/2449414717
Volume	12
WOSCitedRecordID	wos000504200800001&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: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1939-0068 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0067676 issn: 1939-5108 databaseCode: DRFUL dateStart: 20090101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDLZgcIADb8RjoAhx4FKxulnTiBMCJpAGQrxvVZqlrNLWTet4_HycPgZIICFxy8FNqsR2PsfJZ4B9GfnCoEAHfZtm1LQWAYUhDnfjCJV2pcqPLh7a4uoqeHqS11NwVL2FKfghJgdu1jJyf20NXEXZ4Sdp6FuiM7JzyadhBklveQ1mTm9a9-3KEVsqMr9IKkuHVC-oiIUaeDj5-Pt29IkxvyLVfKtpLf7rJ5dgoUSY7LhQiWWYMukKzF9O6FmzVegep0x11JDQJnvNj-2ZslwGJg--yf8xS_yviyw966v3pF8-12SJLQJRNFXveTBKxt0-I-DLdC-h7g2zV05ZWlwuz9bgvnV2d3LulCUXHI0UWTjSkP0jj9FrSgomOrEbo6EYSkfIPT_migCPTfNiZJpaBnEgVMNXrh8bdDsNhd461NJBajaANSLXb2oT2MQrRyFkU0RexDskL4Sn_U04qGY-1CUfuS2L0QsLJmUM7eSFdvI2YW8iOixIOH4SqlfLF5Z2mIUEXiR3aQMWNFy-UL93ED5enNzaxtbfRbdhDm0Anj9OrENtPHoxOzCrX8dJNtotFfIDOkHmBg
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dS8MwED_mFNQHv8X5GcQHX4prmjYN-DLUobgN8futpFmqha2OdU7_fC_9mAoKgm95uCYlubv87i75BeBAhB7XlFOLeqbMqHAtfAxDLGZHIZXKFjJLXdy3eKfjPz6Kqwocl3dhcn6IScLNWEbmr42Bm4T00Sdr6FusUjR0waZgmqEauVWYPr1u3rVKT2y4yLy8qiws1D2_ZBaq06PJx9_3o0-Q-RWqZntNc_F_f7kECwXGJI1cKZahopMVmG9PCFrTVXhuJER25QDxJhlniXsiDZuBzsJv9IDEUP-rvE5P-vI97hcXNklsnoHIm7L39DKMR899gtCXqF6M3WtiDp2SJD9enq7BXfPs9uTcKh5dsBTF2MISGj0AZRF1XIHhRDeyI6oxilIhZY4XMYmQxxR6aahdJfzI57LuSduLNLW7dUmddagmL4neAFIPbc9V2jelV0Y5Fy4PnZB1UZ5zR3k1OCynPlAFI7l5GKMX5FzKNDCTF5jJq8H-RHSQ03D8JLRdrl9QWGIaIHwRzMYtmONw2Ur93kHwcHFyYxqbfxfdg9nz23YraF10LrdgjppwPLuquA3V0fBV78CMGo_idLhbaOcH_K_p9g
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB58IXrwLb4N4sFLcZumSQNeRF0U10V830qaplrYrct2ffx8J32sCgqCtxymSUkyM9_MJF8AdmXEhaGCOpTbMqPGtQgwDHGYm0RUaVeqInVx1xLtdvDwIC9H4KC-C1PyQwwTblYzCnttFdz04mT_kzX0LdU5KrpkozDOfMlRLcePr5q3rdoSWy4yXlaVpYN7L6iZhRp0f_jxd3_0CTK_QtXC1zRn__eXczBTYUxyWG6KeRgx2QJMXwwJWvNFeDrMiIpVD_EmeS0S90RZNgNThN9oAYml_tdlnZ501XvarS5sktQ-A1E2VefxuZ8OnroEoS_RnRS7N8QeOiVZebw8X4Lb5snN0alTPbrgaIqxhSMNWgDKEur5EsOJOHETajCK0hFlHk-YQshjC700Mr6WQRII1eDK5YmhbtxQ1FuGsew5MytAGpHLfW0CW3plVAjpi8iLWIzyQniar8JePfWhrhjJ7cMYnbDkUqahnbzQTt4q7AxFeyUNx09CG_X6hZUm5iHCF8lcdMEChytW6vcOwvuzo2vbWPu76DZMXh43w9ZZ-3wdpqiNxoubihswNui_mE2Y0K-DNO9vVZvzA6kv6XE
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=An+adapted+vector+autoregressive+expectation+maximization+imputation+algorithm+for+climate+data+networks&rft.jtitle=Wiley+interdisciplinary+reviews.+Computational+statistics&rft.au=Washington%2C+Benjamin+J.&rft.au=Seymour%2C+Lynne&rft.date=2020-11-01&rft.issn=1939-5108&rft.eissn=1939-0068&rft.volume=12&rft.issue=6&rft_id=info:doi/10.1002%2Fwics.1494&rft.externalDBID=n%2Fa&rft.externalDocID=10_1002_wics_1494
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1939-5108&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1939-5108&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1939-5108&client=summon