{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T13:19:46Z","timestamp":1783430386872,"version":"3.54.6"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T00:00:00Z","timestamp":1736640000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T00:00:00Z","timestamp":1736640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2105571"],"award-info":[{"award-number":["2105571"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11222-024-10556-9","type":"journal-article","created":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T03:06:12Z","timestamp":1736651172000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Power enhancing probability subsampling using side information"],"prefix":"10.1007","volume":"35","author":[{"given":"Junzhuo","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,12]]},"reference":[{"issue":"11","key":"10556_CR1","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1080\/03610927608827415","volume":"5","author":"JN Adichie","year":"1976","unstructured":"Adichie, J.N.: Testing parallelism of regression lines against ordered alternatives. Commun. Stat. Theory Methods 5(11), 985\u2013997 (1976). https:\/\/doi.org\/10.1080\/03610927608827415","journal-title":"Commun. Stat. Theory Methods"},{"issue":"2","key":"10556_CR2","doi-asserted-by":"publisher","first-page":"749","DOI":"10.5705\/ss.202018.0439","volume":"31","author":"M Ai","year":"2021","unstructured":"Ai, M., Yu, J., Zhang, H., Wang, H.: Optimal subsampling algorithms for big data regressions. Stat. Sin. 31(2), 749\u2013772 (2021). https:\/\/doi.org\/10.5705\/ss.202018.0439","journal-title":"Stat. Sin."},{"key":"10556_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jco.2020.101512","volume":"62","author":"M Ai","year":"2021","unstructured":"Ai, M., Wang, F., Yu, J., Zhang, H.: Optimal subsampling for large-scale quantile regression. J. Complex. 62, 101512 (2021). https:\/\/doi.org\/10.1016\/j.jco.2020.101512","journal-title":"J. Complex."},{"issue":"2","key":"10556_CR4","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1214\/18-AOAS1155SF","volume":"12","author":"S Balakrishnan","year":"2018","unstructured":"Balakrishnan, S., Wasserman, L.: Hypothesis testing for high-dimensional multinomials: a selective review. Ann. Appl. Stat. 12(2), 727\u2013749 (2018). https:\/\/doi.org\/10.1214\/18-AOAS1155SF","journal-title":"Ann. Appl. Stat."},{"key":"10556_CR5","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.ecotra.2019.02.002","volume":"18","author":"S Borsky","year":"2019","unstructured":"Borsky, S., Unterberger, C.: Bad weather and flight delays: the impact of sudden and slow onset weather events. Econ. Transp. 18, 10\u201326 (2019). https:\/\/doi.org\/10.1016\/j.ecotra.2019.02.002","journal-title":"Econ. Transp."},{"issue":"1","key":"10556_CR6","first-page":"3475","volume":"13","author":"P Drineas","year":"2012","unstructured":"Drineas, P., Magdon-Ismail, M., Mahoney, M.W., Woodruff, D.P.: Fast approximation of matrix coherence and statistical leverage. J. Mach. Learn. Res. 13(1), 3475\u20133506 (2012)","journal-title":"J. Mach. Learn. Res."},{"issue":"546","key":"10556_CR7","doi-asserted-by":"publisher","first-page":"1396","DOI":"10.1080\/01621459.2023.2195977","volume":"119","author":"H Feng","year":"2024","unstructured":"Feng, H., Duan, J., Ning, Y., Zhao, J.: Test of significance for high-dimensional thresholds with application to individualized minimal clinically important difference. J. Am. Stat. Assoc. 119(546), 1396\u20131408 (2024). https:\/\/doi.org\/10.1080\/01621459.2023.2195977","journal-title":"J. Am. Stat. Assoc."},{"issue":"5","key":"10556_CR8","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1111\/rssb.12152","volume":"78","author":"B Guo","year":"2016","unstructured":"Guo, B., Chen, S.X.: Tests for high dimensional generalized linear models. J. Roy. Stat. Soc. B Stat. Methodol. 78(5), 1079\u20131102 (2016). https:\/\/doi.org\/10.1111\/rssb.12152","journal-title":"J. Roy. Stat. Soc. B Stat. Methodol."},{"key":"10556_CR9","doi-asserted-by":"publisher","first-page":"303","DOI":"10.5705\/ss.202020.0303","volume":"33","author":"Y Han","year":"2023","unstructured":"Han, Y., Ma, P., Ren, H., Wang, Z.: Model checking in large-scale data set via structure-adaptive-sampling. Stat. Sin. 33, 303\u2013329 (2023). https:\/\/doi.org\/10.5705\/ss.202020.0303","journal-title":"Stat. Sin."},{"issue":"1","key":"10556_CR10","doi-asserted-by":"publisher","first-page":"2621","DOI":"10.1214\/22-EJS2010","volume":"16","author":"S He","year":"2022","unstructured":"He, S., Yan, X.: Functional principal subspace sampling for large scale functional data analysis. Electron. J. Stat. 16(1), 2621\u20132682 (2022). https:\/\/doi.org\/10.1214\/22-EJS2010","journal-title":"Electron. J. Stat."},{"issue":"1","key":"10556_CR11","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.jeconom.2021.10.015","volume":"234","author":"Y He","year":"2023","unstructured":"He, Y., Jaidee, S., Gao, J.: Most powerful test against a sequence of high dimensional local alternatives. J. Econom. 234(1), 151\u2013177 (2023). https:\/\/doi.org\/10.1016\/j.jeconom.2021.10.015","journal-title":"J. Econom."},{"issue":"2","key":"10556_CR12","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1080\/00401706.1995.10484303","volume":"37","author":"T Hesterberg","year":"1995","unstructured":"Hesterberg, T.: Weighted average importance sampling and defensive mixture distributions. Technometrics 37(2), 185\u2013194 (1995). https:\/\/doi.org\/10.1080\/00401706.1995.10484303","journal-title":"Technometrics"},{"key":"10556_CR13","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0169-7161(97)15009-X","volume":"15","author":"TP Hettmansperger","year":"1997","unstructured":"Hettmansperger, T.P., McKean, J.W., Sheather, S.J.: 7 rank-based analyses of linear models. Handbook of Statistics 15, 145\u2013173 (1997). https:\/\/doi.org\/10.1016\/S0169-7161(97)15009-X","journal-title":"Handbook of Statistics"},{"key":"10556_CR14","volume-title":"Nonparametric Statistical Methods","author":"M Hollander","year":"2014","unstructured":"Hollander, M., Wolfe, D.A., Chicken, E.: Nonparametric Statistical Methods. John Wiley and Sons, New Jersey (2014)"},{"issue":"544","key":"10556_CR15","doi-asserted-by":"publisher","first-page":"2262","DOI":"10.1080\/01621459.2023.2209349","volume":"118","author":"N Keret","year":"2023","unstructured":"Keret, N., Gorfine, M.: Analyzing big EHR data-optimal Cox regression subsampling procedure with rare events. J. Am. Stat. Assoc. 118(544), 2262\u20132275 (2023). https:\/\/doi.org\/10.1080\/01621459.2023.2209349","journal-title":"J. Am. Stat. Assoc."},{"issue":"11","key":"10556_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-023-00867-5","volume":"11","author":"S Kim","year":"2024","unstructured":"Kim, S., Park, E.: Prediction of flight departure delays caused by weather conditions adopting data-driven approaches. J. Big Data 11(11), 1\u201325 (2024). https:\/\/doi.org\/10.1186\/s40537-023-00867-5","journal-title":"J. Big Data"},{"issue":"1","key":"10556_CR17","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.jeconom.2012.08.006","volume":"172","author":"S Lee","year":"2013","unstructured":"Lee, S., Song, K., Whang, Y.-J.: Testing functional inequalities. J. Econom. 172(1), 14\u201332 (2013). https:\/\/doi.org\/10.1016\/j.jeconom.2012.08.006","journal-title":"J. Econom."},{"key":"10556_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/b98855","volume-title":"Elements of Large-Sample Theory","author":"EL Lehmann","year":"1999","unstructured":"Lehmann, E.L.: Elements of Large-Sample Theory. Springer, New York (1999)"},{"key":"10556_CR19","doi-asserted-by":"publisher","DOI":"10.1080\/24754269.2024.2343151","author":"X Li","year":"2024","unstructured":"Li, X., Gao, Y., Chang, H., Huang, D., Ma, Y., Pan, R., Qi, H., Wang, F., Wu, S., Xu, K., et al.: A selective review on statistical methods for massive data computation: distributed computing, subsampling, and minibatch techniques. Stat. Theory Relat. Fields (2024). https:\/\/doi.org\/10.1080\/24754269.2024.2343151","journal-title":"Stat. Theory Relat. Fields"},{"issue":"219","key":"10556_CR20","first-page":"1","volume":"24","author":"H Liu","year":"2023","unstructured":"Liu, H., You, J., Cao, J.: Functional L-optimality subsampling for functional generalized linear models with massive data. J. Mach. Learn. Res. 24(219), 1\u201341 (2023)","journal-title":"J. Mach. Learn. Res."},{"issue":"27","key":"10556_CR21","first-page":"861","volume":"16","author":"P Ma","year":"2015","unstructured":"Ma, P., Mahoney, M.W., Yu, B.: A statistical perspective on algorithmic leveraging. J. Mach. Learn. Res. 16(27), 861\u2013911 (2015)","journal-title":"J. Mach. Learn. Res."},{"issue":"373","key":"10556_CR22","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1080\/01621459.1981.10477625","volume":"76","author":"GA Mack","year":"1981","unstructured":"Mack, G.A., Wolfe, D.A.: K-sample rank tests for umbrella alternatives. J. Am. Stat. Assoc. 76(373), 175\u2013181 (1981). https:\/\/doi.org\/10.1080\/01621459.1981.10477625","journal-title":"J. Am. Stat. Assoc."},{"key":"10556_CR23","doi-asserted-by":"crossref","unstructured":"McCullagh, P., Nelder, J.A.: Generalized Linear Models. Chapman and Hall, London (1989)","DOI":"10.1007\/978-1-4899-3242-6"},{"issue":"3","key":"10556_CR24","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1080\/10618600.2020.1844215","volume":"30","author":"C Meng","year":"2021","unstructured":"Meng, C., Xie, R., Mandal, A., Zhang, X., Zhong, W., Ma, P.: LowCon: a design-based subsampling approach in a misspecified linear model. J. Comput. Graph. Stat. 30(3), 694\u2013708 (2021). https:\/\/doi.org\/10.1080\/10618600.2020.1844215","journal-title":"J. Comput. Graph. Stat."},{"key":"10556_CR25","doi-asserted-by":"publisher","unstructured":"Miao, K., Su, L., Wang, W.: Panel threshold regressions with latent group structures. J. Econom. 214(2), 451\u2013481 (2020). https:\/\/doi.org\/10.1016\/j.jeconom.2019.07.006","DOI":"10.1016\/j.jeconom.2019.07.006"},{"issue":"449","key":"10556_CR26","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1080\/01621459.2000.10473909","volume":"95","author":"A Owen","year":"2000","unstructured":"Owen, A., Zhou, Y.: Safe and effective importance sampling. J. Am. Stat. Assoc. 95(449), 135\u2013143 (2000). https:\/\/doi.org\/10.1080\/01621459.2000.10473909","journal-title":"J. Am. Stat. Assoc."},{"issue":"1","key":"10556_CR27","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1080\/02331888408801745","volume":"15","author":"KSM Rao","year":"1984","unstructured":"Rao, K.S.M., Gore, A.P.: Testing concurrence and parallelism of several sample regressions against ordered alternatives. Ser. Stat. 15(1), 43\u201350 (1984). https:\/\/doi.org\/10.1080\/02331888408801745","journal-title":"Ser. Stat."},{"key":"10556_CR28","volume-title":"Linear Models: Least Squares and Alternatives","author":"CR Rao","year":"1999","unstructured":"Rao, C.R., Toutenburg, H.: Linear Models: Least Squares and Alternatives. Springer, New York (1999)"},{"key":"10556_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/b97553","volume-title":"Mathematical Statistics","author":"J Shao","year":"2003","unstructured":"Shao, J.: Mathematical Statistics. Springer, New York (2003)"},{"issue":"1","key":"10556_CR30","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1093\/biomet\/asaa043","volume":"108","author":"H Wang","year":"2021","unstructured":"Wang, H., Ma, Y.: Optimal subsampling for quantile regression in big data. Biometrika 108(1), 99\u2013112 (2021). https:\/\/doi.org\/10.1093\/biomet\/asaa043","journal-title":"Biometrika"},{"issue":"522","key":"10556_CR31","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1080\/01621459.2017.1292914","volume":"113","author":"H Wang","year":"2018","unstructured":"Wang, H., Zhu, R., Ma, P.: Optimal subsampling for large sample logistic regression. J. Am. Stat. Assoc. 113(522), 829\u2013844 (2018). https:\/\/doi.org\/10.1080\/01621459.2017.1292914","journal-title":"J. Am. Stat. Assoc."},{"issue":"10","key":"10556_CR32","doi-asserted-by":"publisher","first-page":"6605","DOI":"10.1109\/TIT.2022.3176955","volume":"68","author":"J Wang","year":"2022","unstructured":"Wang, J., Zou, J., Wang, H.: Sampling with replacement vs Poisson sampling: a comparative study in optimal subsampling. IEEE Trans. Inf. Theory 68(10), 6605\u20136630 (2022). https:\/\/doi.org\/10.1109\/TIT.2022.3176955","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"1","key":"10556_CR33","doi-asserted-by":"publisher","first-page":"151","DOI":"10.6339\/21-JDS999","volume":"19","author":"Y Yao","year":"2021","unstructured":"Yao, Y., Wang, H.: A review on optimal subsampling methods for massive datasets. J. Data Sci. 19(1), 151\u2013172 (2021). https:\/\/doi.org\/10.6339\/21-JDS999","journal-title":"J. Data Sci."},{"issue":"537","key":"10556_CR34","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1080\/01621459.2020.1773832","volume":"117","author":"J Yu","year":"2022","unstructured":"Yu, J., Wang, H., Ai, M., Zhang, H.: Optimal distributed subsampling for maximum quasi-likelihood estimators with massive data. J. Am. Stat. Assoc. 117(537), 265\u2013276 (2022). https:\/\/doi.org\/10.1080\/01621459.2020.1773832","journal-title":"J. Am. Stat. Assoc."},{"key":"10556_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2020.107072","volume":"153","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Wang, H.: Distributed subdata selection for big data via sampling-based approach. Comput. Stat. Data Anal. 153, 107072 (2021). https:\/\/doi.org\/10.1016\/j.csda.2020.107072","journal-title":"Comput. Stat. Data Anal."},{"issue":"1","key":"10556_CR36","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1080\/10618600.2020.1778483","volume":"30","author":"T Zhang","year":"2021","unstructured":"Zhang, T., Ning, Y., Ruppert, D.: Optimal sampling for generalized linear models under measurement constraints. J. Comput. Graph. Stat. 30(1), 106\u2013114 (2021). https:\/\/doi.org\/10.1080\/10618600.2020.1778483","journal-title":"J. Comput. Graph. Stat."},{"issue":"1","key":"10556_CR37","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1080\/10618600.2023.2216261","volume":"33","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Zuo, L., Wang, H., Sun, L.: Approximating partial likelihood estimators via optimal subsampling. J. Comput. Graph. Stat. 33(1), 276\u2013288 (2024). https:\/\/doi.org\/10.1080\/10618600.2023.2216261","journal-title":"J. Comput. Graph. Stat."},{"key":"10556_CR38","doi-asserted-by":"publisher","first-page":"2535","DOI":"10.1007\/s00180-021-01089-0","volume":"36","author":"L Zuo","year":"2021","unstructured":"Zuo, L., Zhang, H., Wang, H., Sun, L.: Optimal subsample selection for massive logistic regression with distributed data. Comput. Stat. 36, 2535\u20132562 (2021). https:\/\/doi.org\/10.1007\/s00180-021-01089-0","journal-title":"Comput. Stat."}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-024-10556-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-024-10556-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-024-10556-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T16:14:43Z","timestamp":1740586483000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-024-10556-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,12]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10556"],"URL":"https:\/\/doi.org\/10.1007\/s11222-024-10556-9","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"value":"0960-3174","type":"print"},{"value":"1573-1375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,12]]},"assertion":[{"value":"16 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"28"}}