Loading…

A Method to Estimate the Statistical Significance of a Correlation When the Data Are Serially Correlated

When analyzing pairs of time series, one often needs to know whether a correlation is statistically significant. If the data are Gaussian distributed and not serially correlated, one can use the results of classical statistics to estimate the significance. While some techniques can handle non-Gaussi...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of climate 1997-09, Vol.10 (9), p.2147-2153
Main Author:	Ebisuzaki, Wesley
Format:	Article
Language:	English
Subjects:	Autocorrelation Correlations Earth, ocean, space Estimation methods Exact sciences and technology External geophysics Geophysics. Techniques, methods, instrumentation and models Meteorology Statistical estimation Statistical significance Statistics Time series
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

cited_by
cites
container_end_page	2153
container_issue	9
container_start_page	2147
container_title	Journal of climate
container_volume	10
creator	Ebisuzaki, Wesley
description	When analyzing pairs of time series, one often needs to know whether a correlation is statistically significant. If the data are Gaussian distributed and not serially correlated, one can use the results of classical statistics to estimate the significance. While some techniques can handle non-Gaussian distributions, few methods are available for data with nonzero autocorrelation (i.e., serially correlated). In this paper, a nonparametric method is suggested to estimate the statistical significance of a computed correlation coefficient when serial correlation is a concern. This method compares favorably with conventional methods.
doi_str_mv	10.1175/1520-0442(1997)010<2147:amtets>2.0.co;2
format	article
fullrecord	<record><control><sourceid>jstor_proqu</sourceid><recordid>TN_cdi_proquest_miscellaneous_18137408</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><jstor_id>26243351</jstor_id><sourcerecordid>26243351</sourcerecordid><originalsourceid>FETCH-LOGICAL-c430t-89e4a4a170bfe7b4b1a15ed6152deff1254321a9394c6be30b6068a15de0e9c33</originalsourceid><addsrcrecordid>eNpFkE1rGzEQhkVpIG7SnxDQoZT2sM6MpP1qQ8Bs3CSQkINdehTa3dl6w3rlSPIh_77aOLgnDZpn3mEexi4R5oh5eompgASUEt-wLPPvgHAlUOU_zDZQ8NdiDvPG_hQf2OxIfmQzKEqVFHmanrJP3j8DoMgAZmyz4I8UNrblwfKlD_3WBOJhQ3wVTOjjR2MGvur_jn0Xy7EhbjtueGWdoyESduR_NjS-jdyYYPjCxVlyvRmG1yNG7Tk76czg6fP7e8Z-_1quq7vk4en2vlo8JI2SEJKiJGWUwRzqjvJa1WgwpTaLt7TUdShSJQWaUpaqyWqSUGeQFZFpCahspDxjXw-5O2df9uSD3va-oWEwI9m911igzBUUEbw9gI2z3jvq9M7F692rRtCTaT3505M_PZnW0bSeTOvF43q5XmmhQVdPWsSkL-8rjY-2Ohc19f4YJwqBuUwjdnHAnn2w7n87E0rKFOU_BnKMEw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>18137408</pqid></control><display><type>article</type><title>A Method to Estimate the Statistical Significance of a Correlation When the Data Are Serially Correlated</title><source>JSTOR Archival Journals and Primary Sources Collection</source><creator>Ebisuzaki, Wesley</creator><creatorcontrib>Ebisuzaki, Wesley</creatorcontrib><description>When analyzing pairs of time series, one often needs to know whether a correlation is statistically significant. If the data are Gaussian distributed and not serially correlated, one can use the results of classical statistics to estimate the significance. While some techniques can handle non-Gaussian distributions, few methods are available for data with nonzero autocorrelation (i.e., serially correlated). In this paper, a nonparametric method is suggested to estimate the statistical significance of a computed correlation coefficient when serial correlation is a concern. This method compares favorably with conventional methods.</description><identifier>ISSN: 0894-8755</identifier><identifier>EISSN: 1520-0442</identifier><identifier>DOI: 10.1175/1520-0442(1997)010<2147:amtets>2.0.co;2</identifier><language>eng</language><publisher>Boston, MA: American Meteorological Society</publisher><subject>Autocorrelation ; Correlations ; Earth, ocean, space ; Estimation methods ; Exact sciences and technology ; External geophysics ; Geophysics. Techniques, methods, instrumentation and models ; Meteorology ; Statistical estimation ; Statistical significance ; Statistics ; Time series</subject><ispartof>Journal of climate, 1997-09, Vol.10 (9), p.2147-2153</ispartof><rights>1997 American Meteorological Society</rights><rights>1997 INIST-CNRS</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.jstor.org/stable/pdf/26243351$$EPDF$$P50$$Gjstor$$H</linktopdf><linktohtml>$$Uhttps://www.jstor.org/stable/26243351$$EHTML$$P50$$Gjstor$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,58238,58471</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=2821735$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Ebisuzaki, Wesley</creatorcontrib><title>A Method to Estimate the Statistical Significance of a Correlation When the Data Are Serially Correlated</title><title>Journal of climate</title><description>When analyzing pairs of time series, one often needs to know whether a correlation is statistically significant. If the data are Gaussian distributed and not serially correlated, one can use the results of classical statistics to estimate the significance. While some techniques can handle non-Gaussian distributions, few methods are available for data with nonzero autocorrelation (i.e., serially correlated). In this paper, a nonparametric method is suggested to estimate the statistical significance of a computed correlation coefficient when serial correlation is a concern. This method compares favorably with conventional methods.</description><subject>Autocorrelation</subject><subject>Correlations</subject><subject>Earth, ocean, space</subject><subject>Estimation methods</subject><subject>Exact sciences and technology</subject><subject>External geophysics</subject><subject>Geophysics. Techniques, methods, instrumentation and models</subject><subject>Meteorology</subject><subject>Statistical estimation</subject><subject>Statistical significance</subject><subject>Statistics</subject><subject>Time series</subject><issn>0894-8755</issn><issn>1520-0442</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1997</creationdate><recordtype>article</recordtype><recordid>eNpFkE1rGzEQhkVpIG7SnxDQoZT2sM6MpP1qQ8Bs3CSQkINdehTa3dl6w3rlSPIh_77aOLgnDZpn3mEexi4R5oh5eompgASUEt-wLPPvgHAlUOU_zDZQ8NdiDvPG_hQf2OxIfmQzKEqVFHmanrJP3j8DoMgAZmyz4I8UNrblwfKlD_3WBOJhQ3wVTOjjR2MGvur_jn0Xy7EhbjtueGWdoyESduR_NjS-jdyYYPjCxVlyvRmG1yNG7Tk76czg6fP7e8Z-_1quq7vk4en2vlo8JI2SEJKiJGWUwRzqjvJa1WgwpTaLt7TUdShSJQWaUpaqyWqSUGeQFZFpCahspDxjXw-5O2df9uSD3va-oWEwI9m911igzBUUEbw9gI2z3jvq9M7F692rRtCTaT3505M_PZnW0bSeTOvF43q5XmmhQVdPWsSkL-8rjY-2Ohc19f4YJwqBuUwjdnHAnn2w7n87E0rKFOU_BnKMEw</recordid><startdate>19970901</startdate><enddate>19970901</enddate><creator>Ebisuzaki, Wesley</creator><general>American Meteorological Society</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7TG</scope><scope>KL.</scope></search><sort><creationdate>19970901</creationdate><title>A Method to Estimate the Statistical Significance of a Correlation When the Data Are Serially Correlated</title><author>Ebisuzaki, Wesley</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c430t-89e4a4a170bfe7b4b1a15ed6152deff1254321a9394c6be30b6068a15de0e9c33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1997</creationdate><topic>Autocorrelation</topic><topic>Correlations</topic><topic>Earth, ocean, space</topic><topic>Estimation methods</topic><topic>Exact sciences and technology</topic><topic>External geophysics</topic><topic>Geophysics. Techniques, methods, instrumentation and models</topic><topic>Meteorology</topic><topic>Statistical estimation</topic><topic>Statistical significance</topic><topic>Statistics</topic><topic>Time series</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ebisuzaki, Wesley</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Meteorological & Geoastrophysical Abstracts</collection><collection>Meteorological & Geoastrophysical Abstracts - Academic</collection><jtitle>Journal of climate</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ebisuzaki, Wesley</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Method to Estimate the Statistical Significance of a Correlation When the Data Are Serially Correlated</atitle><jtitle>Journal of climate</jtitle><date>1997-09-01</date><risdate>1997</risdate><volume>10</volume><issue>9</issue><spage>2147</spage><epage>2153</epage><pages>2147-2153</pages><issn>0894-8755</issn><eissn>1520-0442</eissn><abstract>When analyzing pairs of time series, one often needs to know whether a correlation is statistically significant. If the data are Gaussian distributed and not serially correlated, one can use the results of classical statistics to estimate the significance. While some techniques can handle non-Gaussian distributions, few methods are available for data with nonzero autocorrelation (i.e., serially correlated). In this paper, a nonparametric method is suggested to estimate the statistical significance of a computed correlation coefficient when serial correlation is a concern. This method compares favorably with conventional methods.</abstract><cop>Boston, MA</cop><pub>American Meteorological Society</pub><doi>10.1175/1520-0442(1997)010<2147:amtets>2.0.co;2</doi><tpages>7</tpages><oa>free_for_read</oa></addata></record>
fulltext	fulltext
identifier	ISSN: 0894-8755
ispartof	Journal of climate, 1997-09, Vol.10 (9), p.2147-2153
issn	0894-8755 1520-0442
language	eng
recordid	cdi_proquest_miscellaneous_18137408
source	JSTOR Archival Journals and Primary Sources Collection
subjects	Autocorrelation Correlations Earth, ocean, space Estimation methods Exact sciences and technology External geophysics Geophysics. Techniques, methods, instrumentation and models Meteorology Statistical estimation Statistical significance Statistics Time series
title	A Method to Estimate the Statistical Significance of a Correlation When the Data Are Serially Correlated
url	http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T18%3A45%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-jstor_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Method%20to%20Estimate%20the%20Statistical%20Significance%20of%20a%20Correlation%20When%20the%20Data%20Are%20Serially%20Correlated&rft.jtitle=Journal%20of%20climate&rft.au=Ebisuzaki,%20Wesley&rft.date=1997-09-01&rft.volume=10&rft.issue=9&rft.spage=2147&rft.epage=2153&rft.pages=2147-2153&rft.issn=0894-8755&rft.eissn=1520-0442&rft_id=info:doi/10.1175/1520-0442(1997)010%3C2147:amtets%3E2.0.co;2&rft_dat=%3Cjstor_proqu%3E26243351%3C/jstor_proqu%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c430t-89e4a4a170bfe7b4b1a15ed6152deff1254321a9394c6be30b6068a15de0e9c33%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=18137408&rft_id=info:pmid/&rft_jstor_id=26243351&rfr_iscdi=true