{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T13:12:52Z","timestamp":1722258772417},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2020,12,3]],"date-time":"2020-12-03T00:00:00Z","timestamp":1606953600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Appl. Math. Stat."],"abstract":"The coefficient of determination, the R<\/mml:mi>2<\/mml:mn><\/mml:msup><\/mml:mrow><\/mml:math><\/jats:inline-formula>, is often used to measure the variance explained by an affine combination of multiple explanatory covariates. An attribution of this explanatory contribution to each of the individual covariates is often sought in order to draw inference regarding the importance of each covariate with respect to the response phenomenon. A recent method for ascertaining such an attribution is via the game theoretic Shapley value decomposition of the coefficient of determination. Such a decomposition has the desirable efficiency, monotonicity, and equal treatment properties. Under a weak assumption that the joint distribution is pseudo-elliptical, we obtain the asymptotic normality of the Shapley values. We then utilize this result in order to construct confidence intervals and hypothesis tests for Shapley values. Monte Carlo studies regarding our results are provided. We found that our asymptotic confidence intervals required less computational time to competing bootstrap methods and are able to exhibit improved coverage, especially on small samples. In an expository application to Australian real estate price modeling, we employ Shapley value confidence intervals to identify significant differences between the explanatory contributions of covariates, between models, which otherwise share approximately the same R<\/mml:mi>2<\/mml:mn><\/mml:msup><\/mml:mrow><\/mml:math><\/jats:inline-formula> value. These different models are based on real estate data from the same periods in 2019 and 2020, the latter covering the early stages of the arrival of the novel coronavirus, COVID-19.<\/jats:p>","DOI":"10.3389\/fams.2020.587199","type":"journal-article","created":{"date-parts":[[2020,12,3]],"date-time":"2020-12-03T08:34:55Z","timestamp":1606984495000},"update-policy":"http:\/\/dx.doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Shapley Value Confidence Intervals for Attributing Variance Explained"],"prefix":"10.3389","volume":"6","author":[{"given":"Daniel","family":"Fryer","sequence":"first","affiliation":[]},{"given":"Inga","family":"Str\u00fcmke","sequence":"additional","affiliation":[]},{"given":"Hien","family":"Nguyen","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2020,12,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1214\/12-ejs710","article-title":"Decomposing axiomatic arguments for decomposing goodness of fit according to Shapley and Owen values","volume":"6","author":"Huettner","year":"2012","journal-title":"Electron J Statist."},{"key":"B2","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1137\/1030093","article-title":"Computer-intensive methods in statistical regression","volume":"30","author":"Efron","year":"1988","journal-title":"SIAM Rev."},{"key":"B3","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898718416","volume-title":"Mathematica laboratories for mathematical statistics: emphasizing simulation and computer intensive methods","author":"Baglivo","year":"2005"},{"key":"B4","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/bf02294202","article-title":"The comparison of interdependent correlations between optimal linear composites","volume":"49","author":"Steiger","year":"1984","journal-title":"Psychometrika"},{"key":"B5","doi-asserted-by":"crossref","DOI":"10.1016\/B978-0-12-398750-1.50027-9","article-title":"Joint distributions of some indices based on correlation coefficients","volume-title":"Studies in econometrics, time series, and multivariate analysis","author":"Hedges","year":"1983"},{"key":"B6","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1037\/0033-2909.118.1.155","article-title":"Correlations redux","volume":"118","author":"Olkin","year":"1995","journal-title":"Psychol Bull"},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.1002\/9780471722199","volume-title":"Linear regression analysis","author":"Seber","year":"2003"},{"key":"B8","volume-title":"Econometric analysis","author":"Greene","year":"2007"},{"key":"B9","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1080\/01621459.1952.10501183","article-title":"The multiple-partial correlation coefficient","volume":"47","author":"Cowden","year":"1952","journal-title":"J Am Stat Assoc."},{"key":"B10","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1002\/asmb.446","article-title":"Analysis of regression in game theory approach","volume":"17","author":"Lipovetsky","year":"","journal-title":"IED Stoch Models Bus Ind Appl."},{"key":"B11","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/s10888-006-9036-6","article-title":"A Shapley-based decomposition of the R-square of a linear regression","volume":"5","author":"Israeli","year":"2007","journal-title":"J Econ Inequal."},{"key":"B12","doi-asserted-by":"crossref","DOI":"10.1515\/9781400881970-018","article-title":"A value for n-person games","volume-title":"Contributions to the theory of games","author":"Shapley","year":"1953"},{"key":"B13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v017.i01","article-title":"Relative importance for linear regression R: the package relaimpo","volume":"17","author":"Gromping","year":"2006","journal-title":"J Stat Softw."},{"key":"B14","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1198\/000313007x188252","article-title":"Estimators of relative importance in linear regression based on variance decomposition","volume":"61","author":"Gr\u00f6mping","year":"2007","journal-title":"Am Stat."},{"key":"B15","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/bf01769885","article-title":"Monotonic solutions of cooperative games","volume":"14","author":"Young","year":"1985","journal-title":"Int J Game Theory"},{"key":"B16","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/bf01240041","article-title":"Alternative axiomatic characterizations of the shapley and banzhaf values","volume":"24","author":"Feltkamp","year":"1995","journal-title":"Int J Game Theory"},{"key":"B17","doi-asserted-by":"publisher","first-page":"6","DOI":"10.2307\/2684310","article-title":"Relative importance by averaging over orderings","volume":"41","author":"Kruskal","year":"1987","journal-title":"Am Am Stat."},{"key":"B18","first-page":"407","article-title":"Decomposition of R2 in multiple regression with correlated regressors","volume":"13","author":"Genizi","year":"1993","journal-title":"Stat Sin."},{"key":"B19","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1093\/biomet\/57.3.519","article-title":"Measures of multivariate skewness and kurtosis with applications","volume":"57","author":"Mardia","year":"1970","journal-title":"Biometrika"},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-2937-2","volume-title":"Symmetric multivariate and related distributions","author":"Fang","year":"1990"},{"key":"B21","first-page":"831","article-title":"On normal theory and associated test statistics in covariance structure analysis under two classes of nonnormal distributions","volume":"9","author":"Yuan","year":"1999","journal-title":"Stat Sin."},{"key":"B22","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1006\/jmva.1999.1858","article-title":"Inferences on correlation coefficients in some classes of nonnormal distributions","volume":"72","author":"Yuan","year":"2000","journal-title":"J Multivar Anal."},{"key":"B23","article-title":"Joint distribution of some indices based on correlation coefficients","author":"Hedges","year":"1983"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511802256","volume-title":"Asymptotic statistics","author":"van der Vaart","year":"1998"},{"key":"B25","volume-title":"A matrix Handbook for statisticians","author":"Seber","year":"2008"},{"key":"B26","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1017\/CBO9780511528446.010","article-title":"The potential of the shapley value","volume":"14","author":"Hart","year":"1988","journal-title":"Shapley Value"},{"key":"B27","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1093\/biomet\/26.4.404","article-title":"The use of confidence or fiducial limits illustrated in the case of the binomial","volume":"26","author":"Clopper","year":"1934","journal-title":"Biometrika"},{"key":"B28","volume-title":"Multivariate statistics: high-dimensional and large-sample approximations","author":"Fujikoshi","year":"2011"},{"key":"B29","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1093\/biomet\/87.4.954","article-title":"A new family of power transformations to improve normality or symmetry","volume":"87","author":"Yeo","year":"2000","journal-title":"Biometrika"},{"key":"B30","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in neural information processing systems","author":"Lundberg","year":"2017"},{"key":"B31","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable ai for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell."},{"key":"B32","first-page":"598","article-title":"Algorithmic transparency via quantitative input influence: theory and experiments with learning systems","author":"Datta","year":"2016"},{"key":"B33","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1080\/01621459.2020.1762613","article-title":"Prediction, estimation, and attribution","volume":"115","author":"Efron","year":"2020","journal-title":"J Am Stat Assoc."},{"key":"B34","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1080\/01621459.1992.10475190","article-title":"Generalized collinearity diagnostics","volume":"87","author":"Fox","year":"1992","journal-title":"J Am Stat Assoc."},{"key":"B35","volume-title":"Shapley value confidence intervals for variable selection in regression models","author":"Fryer","year":"2020"}],"container-title":["Frontiers in Applied Mathematics and Statistics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2020.587199\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,3]],"date-time":"2020-12-03T08:35:00Z","timestamp":1606984500000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2020.587199\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,3]]},"references-count":35,"alternative-id":["10.3389\/fams.2020.587199"],"URL":"https:\/\/doi.org\/10.3389\/fams.2020.587199","relation":{},"ISSN":["2297-4687"],"issn-type":[{"value":"2297-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,3]]}}}