{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T23:21:09Z","timestamp":1791501669317,"version":"4.3.4"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T00:00:00Z","timestamp":1707782400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000269","name":"ESRC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009229","name":"American University in Cairo","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009229","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004868","name":"Jiangxi University of Finance and Economics","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004868","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"French National Research Agency","doi-asserted-by":"publisher","award":["ANR-17-EURE-0020"],"award-info":[{"award-number":["ANR-17-EURE-0020"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Excellence Initiative of Aix-Marseille University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>We show that least-squares cross-validation methods share a common structure that has an explicit asymptotic solution, when the chosen kernel is asymptotically separable in bandwidth and data. For density estimation with a multivariate Student-t(\u03bd) kernel, the cross-validation criterion becomes asymptotically equivalent to a polynomial of only three terms. Our bandwidth formulae are simple and noniterative, thus leading to very fast computations, their integrated squared-error dominates traditional cross-validation implementations, they alleviate the notorious sample variability of cross-validation and overcome its breakdown in the case of repeated observations. We illustrate our method with univariate and bivariate applications, of density estimation and nonparametric regressions, to a large dataset of Michigan State University academic wages and experience.<\/jats:p>","DOI":"10.1093\/biomet\/asae007","type":"journal-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T00:49:42Z","timestamp":1707785382000},"page":"809-823","source":"Crossref","is-referenced-by-count":1,"title":["Explicit solutions for the asymptotically optimal bandwidth in cross-validation"],"prefix":"10.1093","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5637-9513","authenticated-orcid":false,"given":"Karim M","family":"Abadir","sequence":"first","affiliation":[{"name":"Business School, Imperial College London , 53 Prince\u2019s Gate, South Kensington Campus , London SW7 2AZ, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0448-0307","authenticated-orcid":false,"given":"Michel","family":"Lubrano","sequence":"additional","affiliation":[{"name":"Aix-Marseille Universit\u00e9, CNRS, AMSE , Marseille F-13001, France . michel.lubrano@univ-amu.fr"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,2,12]]},"reference":[{"key":"2024090419242778000_asae007-B1","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1080\/07474939908800447","article-title":"An introduction to hypergeometric functions for economists","volume":"18","author":"Abadir","year":"1999","journal-title":"Economet. Rev"},{"key":"2024090419242778000_asae007-B2","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1017\/S0266466605050267","article-title":"The mean-median-mode inequality: counterexamples","volume":"21","author":"Abadir","year":"2005","journal-title":"Economet. Theory"},{"key":"2024090419242778000_asae007-B3","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511810800","volume-title":"Matrix Algebra","author":"Abadir","year":"2005"},{"key":"2024090419242778000_asae007-B4","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1080\/00036819508840406","article-title":"Facts about the Gaussian probability density function","volume":"59","author":"Aldershof","year":"1995","journal-title":"Appl. Anal"},{"key":"2024090419242778000_asae007-B5","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1093\/biomet\/71.2.353","article-title":"An alternative method of cross-validation for the smoothing of density estimates","volume":"71","author":"Bowman","year":"1984","journal-title":"Biometrika"},{"key":"2024090419242778000_asae007-B6","author":"Duong","year":"2004"},{"key":"2024090419242778000_asae007-B7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v021.i07","article-title":"ks: kernel density estimation and kernel discriminant analysis for multivariate data in R","volume":"21","author":"Duong","year":"2007","journal-title":"J. Statist. Software"},{"key":"2024090419242778000_asae007-B8","author":"Duong","year":"2022"},{"key":"2024090419242778000_asae007-B9","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1111\/j.1467-9469.2005.00445.x","article-title":"Cross-validation bandwidth matrices for multivariate kernel density estimation","volume":"32","author":"Duong","year":"2005","journal-title":"Scand. J. Statist"},{"key":"2024090419242778000_asae007-B10","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1214\/aos\/1176348902","article-title":"Best possible constant for bandwidth selection","volume":"20","author":"Fan","year":"1992","journal-title":"Ann. Statist."},{"key":"2024090419242778000_asae007-B11","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/0167-7152(87)90083-6","article-title":"Estimation of integrated squared density derivatives","volume":"6","author":"Hall","year":"1987","journal-title":"Statist. Prob. Lett"},{"key":"2024090419242778000_asae007-B12","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/BF01192160","article-title":"Lower bounds for bandwidth selection in density estimation","volume":"90","author":"Hall","year":"1991","journal-title":"Prob. Theory Rel. Fields"},{"key":"2024090419242778000_asae007-B13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF01205233","article-title":"Smoothed cross-validation","volume":"92","author":"Hall","year":"1992","journal-title":"Prob. Theory Rel. Fields"},{"key":"2024090419242778000_asae007-B14","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1002\/9781118150658.ch12","volume-title":"Smoothing and Regression","author":"H\u00e4rdle","year":"2000"},{"key":"2024090419242778000_asae007-B15","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1016\/0167-7152(91)90116-9","article-title":"Using nonstochastic terms to advantage in kernel-based estimation of integrated squared density estimates","volume":"6","author":"Jones","year":"1991","journal-title":"Statist. Prob. Lett"},{"key":"2024090419242778000_asae007-B16","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1214\/aos\/1176348378","article-title":"A simple root n bandwidth selector","volume":"19","author":"Jones","year":"1991","journal-title":"Ann. Statist."},{"key":"2024090419242778000_asae007-B17","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/0167-7152(94)90143-0","article-title":"Asymptotically best bandwidth selectors in kernel density estimation","volume":"19","author":"Kim","year":"1994","journal-title":"Statist. Prob. Lett"},{"key":"2024090419242778000_asae007-B18","volume-title":"Nonparametric Econometrics: Theory and Practice","author":"Li","year":"2006"},{"key":"2024090419242778000_asae007-B19","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1198\/jasa.2011.tm08687","article-title":"Do-validation for kernel density estimation","volume":"106","author":"Mammen","year":"2011","journal-title":"J. Am. Statist. Assoc"},{"key":"2024090419242778000_asae007-B20","first-page":"231","article-title":"Weighted local regression and kernel methods for nonparametric curve fitting","volume":"82","author":"M\u00fcller","year":"1987","journal-title":"J. Am. Statist. Assoc"},{"key":"2024090419242778000_asae007-B21","doi-asserted-by":"crossref","first-page":"703","DOI":"10.2307\/1913610","article-title":"A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix","volume":"55","author":"Newey","year":"1987","journal-title":"Econometrica"},{"key":"2024090419242778000_asae007-B22","volume-title":"R: A Language and Environment for Statistical Computing","author":"R Development Core Team","year":"2024"},{"key":"2024090419242778000_asae007-B23","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1017\/S0266466605050115","article-title":"Robust covariance matrix estimation: HAC estimates with long memory\/antipersistence correction","volume":"21","author":"Robinson","year":"2005","journal-title":"Economet. Theory"},{"key":"2024090419242778000_asae007-B24","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1080\/03610928908829916","article-title":"Making robust the cross-validatory choice of smoothing parameter in spline smoothing regression","volume":"18","author":"Robinson","year":"1989","journal-title":"Commun. Statist. A"},{"key":"2024090419242778000_asae007-B25","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1214\/aoms\/1177728190","article-title":"Remarks on some nonparametric estimates of a density function","volume":"27","author":"Rosenblatt","year":"1956","journal-title":"Ann. Math. Statist."},{"key":"2024090419242778000_asae007-B26","first-page":"65","article-title":"Empirical choice of histograms and kernel density estimators","volume":"9","author":"Rudemo","year":"1982","journal-title":"Scand. J. Statist."},{"key":"2024090419242778000_asae007-B27","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1198\/jasa.2010.tm08532","article-title":"Indirect cross-validation for density estimation","volume":"105","author":"Savchuk","year":"2010","journal-title":"J. Am. Statist. Assoc"},{"key":"2024090419242778000_asae007-B28","doi-asserted-by":"crossref","DOI":"10.1002\/9781118575574","volume-title":"Multivariate Density Estimation: Theory, Practice and Visualization","author":"Scott","year":"2015"},{"key":"2024090419242778000_asae007-B29","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1080\/01621459.1987.10478550","article-title":"Biased and unbiased cross-validation in density estimation","volume":"82","author":"Scott","year":"1987","journal-title":"J. Am. Statist. Assoc"},{"key":"2024090419242778000_asae007-B30","volume-title":"Density Estimation for Statistics and Data Analysis","author":"Silverman","year":"1986"},{"key":"2024090419242778000_asae007-B31","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1214\/aos\/1176346792","article-title":"An asymptotically optimal window selection rule for kernel density estimates","volume":"12","author":"Stone","year":"1984","journal-title":"Ann. Statist."},{"key":"2024090419242778000_asae007-B32","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/0378-3758(92)90157-N","article-title":"Modified cross-validation in density estimation","volume":"30","author":"Stute","year":"1992","journal-title":"J. Statist. Plan. Infer"},{"key":"2024090419242778000_asae007-B33","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1111\/1467-9892.00188","article-title":"Local cross-validation for spectrum bandwidth choice","volume":"21","author":"Velasco","year":"2000","journal-title":"J. Time Ser. Anal"}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asae007\/58465601\/asae007.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/111\/3\/809\/59021370\/asae007.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/111\/3\/809\/59021370\/asae007.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T11:30:15Z","timestamp":1725535815000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/111\/3\/809\/7606771"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,12]]},"references-count":33,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,2,12]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asae007","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9,1]]},"published":{"date-parts":[[2024,2,12]]}}}