{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:53:24Z","timestamp":1791323604474,"version":"4.3.1"},"reference-count":41,"publisher":"Institute of Mathematical Statistics","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ann. Appl. Stat."],"published-print":{"date-parts":[[2026,3,1]]},"abstract":"<jats:p>Education is a key driver of social and economic mobility, yet disparities in attainment persist, particularly in low- and middle-income countries (LMICs). Existing indicators, such as mean years of schooling for adults aged 25 and older (MYS25) and expected years of schooling (EYS), offer a snapshot of an educational system, but lack either cohort-specific or temporal granularity. To address these limitations, we introduce the ultimate years of schooling (UYS)\u2014a birth cohort-based metric targeting the final educational attainment of any individual cohort, including those with ongoing schooling trajectories. As with many attainment indicators, we propose to estimate UYS with cross-sectional household surveys. However, for younger cohorts, estimation fails, because these individuals are right-censored leading to severe downward bias. To correct for this, we propose to reframe educational attainment as a time-to-event process and deploy discrete-time survival models that explicitly account for censoring in the observations. At the national level, we estimate the parameters of the model using survey-weighted logistic regression, while for finer spatial resolutions, where sample sizes are smaller, we embed the discrete-time survival model within a Bayesian spatiotemporal framework to improve stability and precision. Applying our proposed methods to data from the 2022 Tanzania Demographic and Health Surveys, we estimate female educational trajectories corrected for censoring biases and reveal substantial subnational disparities. By providing a dynamic, bias-corrected, and spatially disaggregated measure, our approach enhances education monitoring; it equips policymakers and researchers with a more precise tool for monitoring current progress toward education goals and for designing future targeted policy interventions in LMICs.<\/jats:p>","DOI":"10.1214\/25-aoas2135","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:35:55Z","timestamp":1774017355000},"page":"833-855","source":"Crossref","is-referenced-by-count":0,"title":["Small area estimation of education levels in low- and middle-income countries"],"prefix":"10.1214","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7884-2994","authenticated-orcid":false,"given":"Yunhan","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Biostatistics, University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ameer","family":"Dharamshi","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jon","family":"Wakefield","sequence":"additional","affiliation":[{"name":"Department of Statistics and Department of Biostatistics, University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"108","reference":[{"key":"3","doi-asserted-by":"crossref","unstructured":"<small>Besag, J.<\/small>, <small>York, J.<\/small> and <small>Molli\u00e9, A.<\/small> (1991). Bayesian image restoration, with two applications in spatial statistics. <i>Ann. Inst. Statist. Math.<\/i> <b>43<\/b> 1\u201320.","DOI":"10.1007\/BF00116466"},{"key":"4","doi-asserted-by":"crossref","unstructured":"<small>Binder, D. A.<\/small> (1983). On the variances of asymptotically normal estimators from complex surveys. <i>Int. Stat. Rev.<\/i> <b>51<\/b> 279\u2013292.","DOI":"10.2307\/1402588"},{"key":"27","doi-asserted-by":"publisher","unstructured":"<small>Simpson, D.<\/small>, <small>Rue, H.<\/small>, <small>Riebler, A.<\/small>, <small>Martins, T. G.<\/small> and <small>S\u00d8rbye, S. H.<\/small> (2017). Penalising model component complexity: A principled, practical approach to constructing priors. <i>Statist. Sci.<\/i> <b>32<\/b> 1\u201328.","DOI":"10.1214\/16-STS576"},{"key":"25","doi-asserted-by":"publisher","unstructured":"<small>RIEBLER, A.<\/small>, <small>S\u00d8RBYE, S. H.<\/small>, <small>SIMPSON, D.<\/small> and <small>RUE, H.<\/small> (2016). An intuitive Bayesian spatial model for disease mapping that accounts for scaling. <i>Stat. Methods Med. Res.<\/i> <b>25<\/b> 1145\u20131165.","DOI":"10.1177\/0962280216660421"},{"key":"38","doi-asserted-by":"publisher","unstructured":"<small>WAKEFIELD, J.<\/small>, <small>FUGLSTAD, G.-A.<\/small>, <small>RIEBLER, A.<\/small>, <small>GODWIN, J.<\/small>, <small>WILSON, K.<\/small> and <small>CLARK, S. J.<\/small> (2019). Estimating under-five mortality in space and time in a developing world context. <i>Stat. Methods Med. Res.<\/i> <b>28<\/b> 2614\u20132634.","DOI":"10.1177\/0962280218767988"},{"key":"12","doi-asserted-by":"publisher","unstructured":"<small>GAO, Y.<\/small>, <small>KENNEDY, L.<\/small>, <small>SIMPSON, D.<\/small> and <small>GELMAN, A.<\/small> (2021). Improving multilevel regression and poststratification with structured priors. <i>Bayesian Anal.<\/i> <b>16<\/b> 719\u2013744.","DOI":"10.1214\/20-BA1223"},{"key":"28","doi-asserted-by":"crossref","unstructured":"<small>SINGER, J. D.<\/small> and <small>WILLETT, J. B.<\/small> (1993). It\u2019s about time: Using discrete-time survival analysis to study duration and the timing of events. <i>J. Educ. Stat.<\/i> <b>18<\/b> 155\u2013195.","DOI":"10.3102\/10769986018002155"},{"key":"31","doi-asserted-by":"crossref","unstructured":"<small>SURESH, K.<\/small>, <small>SEVERN, C.<\/small> and <small>GHOSH, D.<\/small> (2022). Survival prediction models: An introduction to discrete-time modeling. <i>BMC Med. Res. Methodol.<\/i> <b>22<\/b> 207.","DOI":"10.1186\/s12874-022-01679-6"},{"key":"1","doi-asserted-by":"crossref","unstructured":"<small>ALLISON, P. D.<\/small> (1982). Discrete-time methods for the analysis of event histories. <i>Sociol. Method.<\/i> <b>13<\/b> 61\u201398.","DOI":"10.2307\/270718"},{"key":"2","doi-asserted-by":"crossref","unstructured":"<small>BARRO, R. J.<\/small> and <small>LEE, J.-W.<\/small> (1993). International comparisons of educational attainment. <i>J. Monet. Econ.<\/i> <b>32<\/b> 363\u2013394.","DOI":"10.1016\/0304-3932(93)90023-9"},{"key":"5","doi-asserted-by":"crossref","unstructured":"<small>BROWN, C. C.<\/small> (1975). On the use of indicator variables for studying the time-dependence of parameters in a response-time model. <i>Biometrics<\/i> <b>31<\/b> 863\u2013872.","DOI":"10.2307\/2529811"},{"key":"6","unstructured":"<small>CROFT, T. N.<\/small>, <small>ALLEN, C. K.<\/small>, <small>ZACHARY, B. W.<\/small> et al. (2023). <i>Guide to DHS Statistics<\/i>. ICF, Rockville, MD, USA."},{"key":"7","doi-asserted-by":"crossref","unstructured":"<small>DELPRATO, M.<\/small>, <small>CHUDGAR, A.<\/small> and <small>FROLA, A.<\/small> (2024). Spatial education inequality for attainment indicators in sub-Saharan Africa and spillovers effects. <i>World Dev.<\/i> <b>176<\/b> 106522.","DOI":"10.1016\/j.worlddev.2023.106522"},{"key":"8","doi-asserted-by":"crossref","unstructured":"<small>DELPRATO, M.<\/small> and <small>FROLA, A.<\/small> (2022). Zones of educational exclusion of out-of-school youth. <i>Int. J. Educ. Soc. Dev.<\/i> <b>88<\/b> 102532.","DOI":"10.1016\/j.ijedudev.2021.102532"},{"key":"9","doi-asserted-by":"publisher","unstructured":"<small>DHARAMSHI, A.<\/small>, <small>BARAKAT, B.<\/small>, <small>ALKEMA, L.<\/small> and <small>ANTONINIS, M.<\/small> (2022). A Bayesian model for estimating Sustainable Development Goal indicator 4.1.2: School completion rates. <i>J. R. Stat. Soc<\/i>., <i>Ser. C, Appl. Stat.<\/i> <b>71<\/b> 1822\u20131864.","DOI":"10.1111\/rssc.12595"},{"key":"10","doi-asserted-by":"crossref","unstructured":"<small>DONG, T. Q.<\/small> and <small>WAKEFIELD, J.<\/small> (2021). Modeling and presentation of vaccination coverage estimates using data from household surveys. <i>Vaccine<\/i> <b>39<\/b> 2584\u20132594.","DOI":"10.1016\/j.vaccine.2021.03.007"},{"key":"11","doi-asserted-by":"crossref","unstructured":"<small>FUCHS, R.<\/small>, <small>PAMUK, E.<\/small> and <small>LUTZ, W.<\/small> (2010). Education or wealth: Which matters more for reducing child mortality in developing countries? <i>Vienna Yearb. Popul. Res.<\/i> <b>8<\/b> 175\u2013199.","DOI":"10.1553\/populationyearbook2010s175"},{"key":"13","unstructured":"<small>GLOBAL ADMINISTRATIVE AREAS<\/small> (2022). GADM database of global administrative areas, version 4.1."},{"key":"14","unstructured":"<small>GRAETZ, N.<\/small>, <small>ZIMMERMAN, A.<\/small>, <small>BURSTEIN, R.<\/small>, <small>BIEHL, M.<\/small>, <small>SHIELDS, C.<\/small>, <small>MOSSER, J.<\/small>, <small>CASEY, D.<\/small>, <small>DESHPANDE, A.<\/small>, <small>EARL, L.<\/small> et al. (2018). Mapping local variation in educational attainment across Africa. <i>Nature<\/i> <b>555<\/b> 48\u201353."},{"key":"15","unstructured":"<small>H\u00c1JEK, J.<\/small> (1971). Discussion of \u2018an essay on the logical foundations of survey sampling, part I\u2019, by D. Basu. <i>Found. Stat. Inference<\/i> <b>326<\/b>."},{"key":"16","doi-asserted-by":"publisher","unstructured":"<small>KALBFLEISCH, J. D.<\/small> and <small>PRENTICE, R. L.<\/small> (2002). <i>The Statistical Analysis of Failure Time Data<\/i>, 2nd ed. <i>Wiley Series in Probability and Statistics<\/i>. Wiley, New York.","DOI":"10.1002\/9781118032985"},{"key":"17","doi-asserted-by":"crossref","unstructured":"<small>KNORR-HELD, L.<\/small> (2000). Bayesian modeling of inseparable space\u2013time variation in disease risk. <i>Stat. Med.<\/i> <b>19<\/b> 2555\u20132567.","DOI":"10.1002\/1097-0258(20000915\/30)19:17\/18<2555::AID-SIM587>3.0.CO;2-#"},{"key":"18","doi-asserted-by":"crossref","unstructured":"<small>LEWIN, K. M.<\/small> (2009). Access to education in sub-Saharan Africa: Patterns, problems and possibilities. <i>Comp. Educ.<\/i> <b>45<\/b> 151\u2013174.","DOI":"10.1080\/03050060902920518"},{"key":"19","doi-asserted-by":"crossref","unstructured":"<small>LUMLEY, T.<\/small> (2010). <i>Complex Surveys<\/i>: <i>A Guide to Analysis Using R<\/i>. Wiley, New York.","DOI":"10.1002\/9780470580066"},{"key":"20","doi-asserted-by":"crossref","unstructured":"<small>LUTZ, W.<\/small>, <small>CUARESMA, J. C.<\/small> and <small>SANDERSON, W.<\/small> (2008). The demography of educational attainment and economic growth. <i>Science<\/i> <b>319<\/b> 1047\u20131048.","DOI":"10.1126\/science.1151753"},{"key":"21","doi-asserted-by":"crossref","unstructured":"<small>MACHARIA, P. M.<\/small>, <small>MOTURI, A. K.<\/small>, <small>MUMO, E.<\/small>, <small>GIORGI, E.<\/small>, <small>OKIRO, E. A.<\/small>, <small>SNOW, R. W.<\/small> and <small>RAY, N.<\/small> (2023). Modelling geographic access and school catchment areas across public primary schools to support subnational planning in Kenya. <i>Child. Geogr.<\/i> <b>21<\/b> 832\u2013848.","DOI":"10.1080\/14733285.2022.2137388"},{"key":"22","doi-asserted-by":"publisher","unstructured":"<small>MANDA, S.<\/small> and <small>MEYER, R.<\/small> (2005). Age at first marriage in Malawi: A Bayesian multilevel analysis using a discrete time-to-event model. <i>J. R. Stat. Soc<\/i>., <i>Ser. A<\/i> <b>168<\/b> 439\u2013455.","DOI":"10.1111\/j.1467-985X.2005.00357.x"},{"key":"23","doi-asserted-by":"crossref","unstructured":"<small>MEARA, E. R.<\/small>, <small>RICHARDS, S.<\/small> and <small>CUTLER, D. M.<\/small> (2008). The gap gets bigger: Changes in mortality and life expectancy, by education, 1981\u20132000. <i>Health Aff.<\/i> <b>27<\/b> 350\u2013360.","DOI":"10.1377\/hlthaff.27.2.350"},{"key":"24","unstructured":"<small>MINISTRY OF EDUCATION, TANZANIA<\/small> (2017). Education sector development plan (ESDP) 2016\/17\u20132020\/21: Delivering quality education and training to all Tanzanians. Retrieved from <a href=\"https:\/\/www.globalpartnership.org\/sites\/default\/files\/2019-04-gpe-tanzania-esp.pdf\">https:\/\/www.globalpartnership.org\/sites\/default\/files\/2019-04-gpe-tanzania-esp.pdf<\/a>."},{"key":"26","doi-asserted-by":"publisher","unstructured":"<small>RUE, H.<\/small>, <small>MARTINO, S.<\/small> and <small>CHOPIN, N.<\/small> (2009). Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations. <i>J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> <b>71<\/b> 319\u2013392. With discussion.","DOI":"10.1111\/j.1467-9868.2008.00700.x"},{"key":"29","doi-asserted-by":"crossref","unstructured":"<small>SMITS, J.<\/small> and <small>PERMANYER, I.<\/small> (2019). The subnational human development database. <i>Sci. Data<\/i> <b>6<\/b> 1\u201315.","DOI":"10.1038\/sdata.2019.38"},{"key":"30","doi-asserted-by":"crossref","unstructured":"<small>STEVENS, F. R.<\/small>, <small>GAUGHAN, A. E.<\/small>, <small>LINARD, C.<\/small> and <small>TATEM, A. J.<\/small> (2015). Disaggregating census data for population mapping using random forests with remotely-sensed and ancillary data. <i>PLoS ONE<\/i> <b>10<\/b> 1\u201322.","DOI":"10.1371\/journal.pone.0107042"},{"key":"32","doi-asserted-by":"crossref","unstructured":"<small>THOMSON, D. R.<\/small>, <small>SHITOLE, S.<\/small>, <small>SHITOLE, T.<\/small>, <small>SAWANT, K.<\/small>, <small>SUBBARAMAN, R.<\/small>, <small>BLOOM, D. E.<\/small> and <small>PATIL-DESHMUKH, A.<\/small> (2014). A system for household enumeration and re-identification in densely populated slums to facilitate community research, education, and advocacy. <i>PLoS ONE<\/i> <b>9<\/b> 1\u20139.","DOI":"10.1371\/journal.pone.0093925"},{"key":"33","unstructured":"<small>UIS<\/small> (2025). UIS Stat: SDG 4 Regional Averages."},{"key":"34","unstructured":"<small>UNESCO<\/small> (2024). Global Education Monitoring Report 2024\/5. Technical report, UNESCO."},{"key":"35","unstructured":"<small>UNESCO INSTITUTE FOR STATISTICS AND AFRICAN UNION<\/small> (2024). 2024 spotlight on basic education completion and foundational learning in Africa. Technical report, UNESCO."},{"key":"36","unstructured":"<small>UNITED NATIONS<\/small> (2015). Transforming our world: the 2030 agenda for sustainable development. Retrieved from <a href=\"https:\/\/sdgs.un.org\/2030agenda\">https:\/\/sdgs.un.org\/2030agenda<\/a>."},{"key":"37","unstructured":"<small>UNITED NATIONS CHILDREN\u2019S FUND (UNICEF)<\/small> (2019). <i>Every Child Learns: UNICEF Education Strategy 2019\u20132030<\/i>. UNICEF, New York."},{"key":"39","doi-asserted-by":"crossref","unstructured":"<small>WILLETT, J. B.<\/small> and <small>SINGER, J. D.<\/small> (1991). From whether to when: New methods for studying student dropout and teacher attrition. <i>Rev. Educ. Res.<\/i> <b>61<\/b> 407\u2013450.","DOI":"10.3102\/00346543061004407"},{"key":"40","doi-asserted-by":"crossref","unstructured":"<small>WU, Y.<\/small>, <small>DHARAMSHI, A.<\/small> and <small>WAKEFIELD, J.<\/small> (2026). Supplement to \u201cSmall Area Estimation of Education Levels in Low- and Middle-Income Countries.\u201d <a href=\"https:\/\/doi.org\/10.1214\/25-AOAS2135SUPPA\">https:\/\/doi.org\/10.1214\/25-AOAS2135SUPPA<\/a>, <a href=\"https:\/\/doi.org\/10.1214\/25-AOAS2135SUPPB\">https:\/\/doi.org\/10.1214\/25-AOAS2135SUPPB<\/a>","DOI":"10.1214\/25-AOAS2135SUPPB"},{"key":"41","doi-asserted-by":"publisher","unstructured":"<small>WU, Y.<\/small> and <small>WAKEFIELD, J.<\/small> (2024). Modelling urban\/rural fractions in low- and middle-income countries. <i>J. R. Stat. Soc<\/i>., <i>Ser. A<\/i> <b>187<\/b> 811\u2013830.","DOI":"10.1093\/jrsssa\/qnae003"}],"container-title":["The Annals of Applied Statistics"],"original-title":[],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:33:01Z","timestamp":1791322381000},"score":1,"resource":{"primary":{"URL":"https:\/\/projecteuclid.org\/journals\/annals-of-applied-statistics\/volume-20\/issue-1\/Small-area-estimation-of-education-levels-in-low--and\/10.1214\/25-AOAS2135.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,1]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,3,1]]}},"URL":"https:\/\/doi.org\/10.1214\/25-aoas2135","relation":{},"ISSN":["1932-6157","1941-7330"],"issn-type":[{"value":"1932-6157","type":"print"},{"value":"1941-7330","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,1]]}}}