Small Area Estimation Models Research Articles

Small Area Estimation of Household Economic Indicators under Unit-Level Generalized Additive Models for Location, Scale and Shape

Abstract We propose a small area estimation model based on Generalized Additive Models for Location, Scale and Shape (SAE-GAMLSS) for the estimation of household economic indicators. SAE-GAMLSS relax the exponential family distributional assumption and allow each distributional parameter to depend on covariates. A bootstrap approach to estimate the MSE is proposed. The SAE-GAMLSS estimator shows a largely better performance than the well-known Empirical Best Linear Unbiased Predictor (EBLUP) under various simulated scenarios. Per-capita consumption of Italian and foreign households in Italian regions, in urban and rural areas, is estimated using SAE-GAMLSS. Results show that the well-known Italian North–South divide does not hold for foreigners.

측정오차 공변량을 고려한 포아송 소지역 모델의 준모수적 계층적 베이즈 추정

In the sample survey, it is impossible to obtain sufficient samples in relatively small areas, which makes it difficult to estimate accurate statistics for small areas. For this reason, various studies on small area estimation are constantly being conducted, and in particular, the Fay-Herriot (1979) model has been expanded to various forms as one of the most widely used small area estimation models. In this study, we developed a semiparametric regression model based on a radial basis function that can consider nonlinear relationships between the resulting variables and covariates, extended from the model considering the measurement error of the covariate in the Poisson distribution proposed by Nam, Hwang(2021). Also, parameter estimation and model fit were performed through hierarchical Bayesian estimation using Gibbs sampling and Metropolis-Hastings algorithm among Markov chain Monte Carlo techniques. Simulations were conducted under various conditions to confirm the suitability of the model developed in this study, and the excellence of the developed model was further verified through empirical analysis using data from the 8th Korean longitudinal study of aging.

TWOFOLD SUBAREA MODEL FOR ESTIMATING COMMUTER PROPORTION IN 10 METROPOLITAN AREAS

The metropolitan area is a major contributor to national GDP. The metropolitan area is a center of attraction for many people who come to earn income as commuters. Commuters are people who carry out work activities in the center of the metropolitan area, which are carried out by residents who live in suburban areas around the center of the metropolitan area and commute regularly every day. The availability of commuter statistics from surveys for presentation level down to the smallest administrative level, such as regencies/municipalities, is unreliable. This happens because this level of presentation has poor precision due to insufficient samples due to the Statistics Indonesia survey design for making estimates at the national and provincial levels. It can be done using small area estimation (SAE) to meet increasing data needs, but existing SAE models can often estimate only at one level. To meet data requests more effectively, a model is needed that can estimate several small areas simultaneously. In SAE, one of the SAE models that can do this is the twofold subarea model. The twofold subarea model produces estimates of the proportion of commuters with good precision at the subarea level (regencies/municipalities) and area level (metropolitan area), with the RRMSE percentage value of the estimated proportion of commuters being below 25% for all regions. The results of this research can be used to present commuter data at the regencies/municipalities level and metropolitan area level where there is a lack of samples and become a new opportunity for Statistics Indonesia to increase statistical production in small areas, which is more effective compared to other SAE methods which have so far been used only to estimate one area level.

Nonlinear Fay-Herriot Models for Small Area Estimation Using Random Weight Neural Networks

Small area estimation models are critical for dissemination and understanding of important population characteristics within sub-domains that often have limited sample size. The classic Fay-Herriot model is perhaps the most widely used approach to generate such estimates. However, a limiting assumption of this approach is that the latent true population quantity has a linear relationship with the given covariates. Through the use of random weight neural networks, we develop a Bayesian hierarchical extension of this framework that allows for estimation of nonlinear relationships between the true population quantity and the covariates. We illustrate our approach through an empirical simulation study as well as an analysis of median household income for census tracts in the state of California.

A Hierarchical Bayesian approach to small area estimation of health insurance coverage in Ethiopian administrative zones for better policies and programs

Sample surveys are extensively used to provide reliable direct estimates for large areas or domains with enough sample sizes at national and regional levels. However, zones are unplanned domains by the Demographic and Health Survey (DHS) program and need more sample sizes to produce direct survey estimates with adequate precision. Conducting surveys in small areas (like zones) is too expensive and time-consuming, making it unfeasible for developing countries like Ethiopia. Therefore, this study aims to use the Hierarchical Bayes (HB) Small Area Estimation (SAE) model to estimate the Community-Based Health Insurance (CBHI) coverage at the zone levels in Ethiopia. To achieve this, we combined the 2019 Ethiopia Mini-Demographic and Health Survey (EMDHS) data with the 2007 population census data. SAE has addressed the challenge of producing reliable parameter estimates for small or even zero sample sizes across Ethiopian zones by utilizing auxiliary information from the population census. The results show that model-based estimates generated by the SAE approach are more accurate than direct survey estimates of CBHI. A map of CBHI scheme coverage was also used to visualize the spatial variation in the distribution of CBHI scheme coverage. From the CBHI scheme coverage map, we noticed notable variations in CBHI scheme coverage across Ethiopian zones. Additionally, this research identified areas with high and low CBHI scheme coverage to improve decision-making and increase coverage in Ethiopia. One of the novelties of this paper is estimating the non-sampled zones; therefore, the policymakers will give equal attention similar to the sampled zones.

Taking advantage of sampling designs in spatial small-area survey studies

Spatial small area estimation models have become very popular in some contexts, such as disease mapping. Data in disease mapping studies are exhaustive, that is, the available data are supposed to be a complete register of all the observable events. In contrast, some other small area studies do not use exhaustive data, such as survey based studies, where a particular sampling design is typically followed and inferences are later extrapolated to the entire population. In this article we propose a spatial model for small area survey studies, taking advantage of spatial dependence between units, which is the key assumption used for yielding reliable estimates in exhaustive data based studies. In addition, and in contrast to most survey-based spatial studies, we also take into account information on the sampling design and additional supplementary variables to obtain estimates in small areas. This makes it possible to merge spatial and sampling models into a common proposal.

Small area estimates for Voting Rights Act Section 203(b) coverage determinations

The Director of the US Census Bureau every five years, under the Voting Rights Act (VRA) Section 203(b), determines which states and political subdivisions must provide ballot assistance in languages other than English. These rule-based determinations use small-area estimates of the proportions of voting-age citizen members of racial/ethnic Language Minority Groups (LMGs) who are limited Englishproficient (LEP) and of LEP LMG persons who are also illiterate. This large-scale Small Area Estimation (SAE) effort by the US Census Bureau is based on American Community Survey five-year data. This paper focuses on the unique attributes of this SAE problem, including the predominance in each LMG of tiny domains along with relatively few large domains that account for the bulk of LMG citizens. The data and small area models are treated separately for distinct LMGs, and the spirit of the law requires that the domain estimates should be produced in a similar way across LMGs for each type of geography (Jurisdictions, which are mostly counties, plus two types of American Indian and Alaskan Native areas). The paper describes and assesses the SAE models developed under unique constraints, including novel methodological aspects and the use of hybrid frequentist and Bayesian computational techniques; situates these modelling choices in the broader literature on SAE; and discusses the strengths and weaknesses of the resulting models.

The impact of local cost-of-living differences on relative poverty incidence: an application using retail scanner data and small area estimation models

Estimating economic poverty indicators at the local level is essential for well-targeted data-driven welfare policies. However, Italy is a country characterized by strong geographical heterogeneity represented by unequal price levels among different areas, and computing poverty indicators with a national monetary poverty threshold can be misleading. This work proposes a novel approach to estimate monetary poverty incidence at the provincial level in Italy considering the different price levels within national boundaries. To account for local price variation, Spatial Price Indices (SPIs) are computed using scanner data on retail prices. The SPIs are estimated in two ways, referring to the mean local prices and using the 20th percentile of the prices. These two kinds of SPIs are used to adjust the national poverty line when computing the poverty incidence at the provincial level using Small Area Estimation (SAE) models. Our findings suggest that adjusting the national poverty line using the SPIs to compute a monetary poverty index can modify the poverty mapping results from the map produced with the traditional national poverty line that ignores price differences.

US County–Level Variation in Preterm Birth Rates, 2007-2019

Preterm birth is a leading cause of preventable neonatal morbidity and mortality. Preterm birth rates at the national level may mask important geographic variation in rates and trends at the county level. To estimate age-standardized preterm birth rates by US county from 2007 to 2019. This serial cross-sectional study used data from the National Center for Health Statistics composed of all live births in the US between 2007 and 2019. Data analyses were performed between March 22, 2022, and September 29, 2022. Age-standardized preterm birth (<37 weeks' gestation) and secondarily early preterm birth (<34 weeks' gestation) rates by county and year calculated with a validated small area estimation model (hierarchical bayesian spatiotemporal model) and percent change in preterm birth rates using log-linear regression models. Between 2007 and 2019, there were 51 044 482 live births in 2383 counties. In 2007, the national age-standardized preterm birth rate was 12.6 (95% CI, 12.6-12.7) per 100 live births. Preterm birth rates varied significantly among counties, with an absolute difference between the 90th and 10th percentile counties of 6.4 (95% CI, 6.2-6.7). The gap between the highest and lowest counties for preterm births was 20.7 per 100 live births in 2007. Several counties in the Southeast consistently had the highest preterm birth rates compared with counties in California and New England, which had the lowest preterm birth rates. Although there was no statistically significant change in preterm birth rates between 2007 and 2019 at the national level (percent change, -5.0%; 95% CI, -10.7% to 0.9%), increases occurred in 15.4% (95% CI, 14.1%-16.9%) of counties. The absolute and relative geographic inequalities were similar across all maternal age groups. Higher quartile of the Social Vulnerability Index was associated with higher preterm birth rates (quartile 4 vs quartile 1 risk ratio, 1.34; 95% CI, 1.31-1.36), which persisted across the study period. Similar patterns were observed for early preterm birth rates. In this serial cross-sectional study of county-level preterm and early preterm birth rates, substantial geographic disparities were observed, which were associated with place-based social disadvantage. Stability in aggregated rates of preterm birth at the national level masked increases in nearly 1 in 6 counties between 2007 and 2019.

Cause-specific mortality by county, race, and ethnicity in the USA, 2000–19: a systematic analysis of health disparities

Large disparities in mortality exist across racial-ethnic groups and by location in the USA, but the extent to which racial-ethnic disparities vary by location, or how these patterns vary by cause of death, is not well understood. We aimed to estimate age-standardised mortality by racial-ethnic group, county, and cause of death and describe the intersection between racial-ethnic and place-based disparities in mortality in the USA, comparing patterns across health conditions. We applied small-area estimation models to death certificate data from the US National Vital Statistics system and population data from the US National Center for Health Statistics to estimate mortality by age, sex, county, and racial-ethnic group annually from 2000 to 2019 for 19 broad causes of death. Race and ethnicity were categorised as non-Latino and non-Hispanic American Indian or Alaska Native (AIAN), non-Latino and non-Hispanic Asian or Pacific Islander (Asian), non-Latino and non-Hispanic Black (Black), Latino or Hispanic (Latino), and non-Latino and non-Hispanic White (White). We adjusted these mortality rates to correct for misreporting of race and ethnicity on death certificates and generated age-standardised results using direct standardisation to the 2010 US census population. From 2000 to 2019, across 3110 US counties, racial-ethnic disparities in age-standardised mortality were noted for all causes of death considered. Mortality was substantially higher in the AIAN population (all-cause mortality 1028·2 [95% uncertainty interval 922·2-1142·3] per 100 000 population in 2019) and Black population (953·5 [947·5-958·8] per 100 000) than in the White population (802·5 [800·3-804·7] per 100 000), but substantially lower in the Asian population (442·3 [429·3-455·0] per 100 000) and Latino population (595·6 [583·7-606·8] per 100 000), and this pattern was found for most causes of death. However, there were exceptions to this pattern, and the exact order among racial-ethnic groups, magnitude of the disparity in both absolute and relative terms, and change over time in this magnitude varied considerably by cause of death. Similarly, substantial geographical variation in mortality was observed for all causes of death, both overall and within each racial-ethnic group. Racial-ethnic disparities observed at the national level reflect widespread disparities at the county level, although the magnitude of these disparities varied widely among counties. Certain patterns of disparity were nearly universal among counties; for example, in 2019, mortality was higher among the AIAN population than the White population in at least 95% of counties for skin and subcutaneous diseases (455 [97·8%] of 465 counties with unmasked estimates) and HIV/AIDS and sexually transmitted infections (458 [98·5%] counties), and mortality was higher among the Black population than the White population in nearly all counties for skin and subcutaneous diseases (1436 [96·6%] of 1486 counties), diabetes and kidney diseases (1473 [99·1%]), maternal and neonatal disorders (1486 [100·0%] counties), and HIV/AIDS and sexually transmitted infections (1486 [100·0%] counties). Disparities in mortality among racial-ethnic groups are ubiquitous, occurring across locations in the USA and for a wide range of health conditions. There is an urgent need to address the shared structural factors driving these widespread disparities. National Institute on Minority Health and Health Disparities; National Heart, Lung, and Blood Institute; National Cancer Institute; National Institute on Aging; National Institute of Arthritis and Musculoskeletal and Skin Diseases; Office of Disease Prevention; and Office of Behavioral and Social Sciences Research, US National Institutes of Health.

Precise and unbiased biomass estimation from GEDI data and the US Forest Inventory

Atmospheric CO2 concentrations are dependent on land-atmosphere carbon fluxes resultant from forest dynamics and land-use changes. These fluxes are not well-constrained, in part because reliable baseline estimates of forest carbon stocks and the associated uncertainties are lacking. NASA's Global Ecosystem Dynamics Investigation (GEDI) produces estimates of aboveground biomass density (AGBD) that are unique because GEDI's hybrid estimation framework enables formal uncertainty calculations that accompany the biomass estimates. However, GEDI's estimates are not without issue; a recent validation using design-based AGBD estimates from the US Forest Inventory and Analysis (FIA) program revealed systematic differences between GEDI and FIA estimates within a hexagon tessellation of the continental United States. Here, we explored these differences and identified two issues impacting GEDI's estimation process: incomplete filtering of low quality GEDI observations and regional biases in GEDI's footprint-level biomass models. We developed a solution to each, in the form of improved data filtering and GEDI-FIA fusion AGBD models, developed in a scale-invariant small area estimation framework, that were compatible with hybrid estimation. We calibrated 10 regional Fay-Herriot models at the hexagon scale for application at the unit scale of GEDI footprints, for which we provide a mathematical justification and empirical testing of the models' scale-invariance. These models predicted realistic distributions of unit level AGBD, with equal or improved performance relative to GEDI's L4A models for all regions. We then produced GEDI-FIA fusion estimates that were more precise than the FIA estimates and resulted in a bias reduction of 86.7% relative to the original GEDI estimates: 19.3% due to improved data filtering and 67.5% due to the new AGBD models. Our findings indicate that (1) small area estimation models trained in a scale-invariant framework can produce realistic predictions of AGBD, and (2) there is substantial spatial variability in the relationship between GEDI forest structure metrics and AGBD. This work is a step toward achieving reliable baseline forest carbon stocks, provides a viable methodology for training remote sensing biomass models, and may serve as a reference for other investigations of GEDI AGBD estimates.

Analysis of unit level models for small area estimation in crop statistics assisted with satellite auxiliary information

Crop statistics for a small area, such as the community development block, are an increasingly important topic in agricultural statistics. Under normality assumptions, the classic Empirical Best Linear Unbiased Prediction (EBLUP) technique is effective for predicting small area means, however the Small Area Estimation (SAE) model can be heavily affected by the incidence of outliers or deviations from the expected distribution. The purpose of this study was to estimate variance, predict block-level wheat crop yield in the Hisar and Sirsa district of Haryana by classical SAE method and a robust random-effect predictor using a slight generalization of Huber’s Proposal 2. In the case of Sirsa district, the results of classical and robust unit level SAE were very close, but not in the case of Hisar district. This could be due to the influential observation found in the Hisar data set. More accurate EBLUP wheat yield estimates are obtained when the Huber-type M-estimation method is initialized by the least square regression estimator.

RELATIVE RISK ANALYSIS OF THE SPREAD OF COVID-19 VIRUS IN MEDAN CITY BY SPATIAL AND NON-SPATIAL APPROACHES

&lt;span lang="EN"&gt;The city of Medan is the city with the highest cases of COVID-19 virus among cities in North Sumatra. This study was conducted to analyze the relative risk level for the spread of the COVID-19 virus. Estimation of relative risk is a statistic in disease mapping that is used to determine the distribution of disease. Relative risk estimation can be estimated using a direct estimator model or Standardized Morbility ratio and a small area estimation model using Bayesian Conditional Autoregressive (CAR) with the Poisson-Gamma model. The Poisson-Gamma model is one of the models in estimating small areas in the form of count data which is suitable for use in disease mapping cases. This study aims to find the relative risk value as the basis for mapping the spread of the COVID-19 virus in the city of Medan using the Standardized Morbility Ratio and Bayesian Condition Autoregressive models. And look for the value of the Central Error Squared (KTG) / Mean Squared Error (MSE) as a comparison which model is more efficient in estimating this research. Condition Autoregressive models. And look for the value of the Central Error Squared (KTG) / Mean Squared Error (MSE) as a comparison which model is more efficient in estimating this research.&lt;/span&gt;

Small area estimation with multiple covariates under structural measurement error models

Small area estimation is essential in making reliable inferences for areas where the sample is relatively small or no sample is available. In the case of developing a small area estimation model, if the covariates measured with errors were ignored, the estimation results may be worse than the direct estimate. Therefore, the problem of measurement error in covariates imposes challenges to data analytics in small area estimation. This paper studies a model with multiple covariates subject to structural measurement error and multiple error-free covariates. This study explores different scenarios in a simulation study by creating a finite super population spread across the area, investigating the sensitivity to sample size, and determining the variance of measurement error that was lower than the variance of the sampling error and the variance of the random effect. Jackknife method was employed to obtain a nearly unbiased estimator of the mean squared prediction error of empirical best predictors of the predictors of small area means. The research shows that the performance of the empirical best predictors is better in the case of a large sample size within the area and small variances of the measurement errors. The weighted version is recommended because it is more stable in terms of variability and bias.

A spatially varying model for small area estimates of biomass density across the contiguous United States

The USDA Forest Service, Forest Inventory and Analysis (FIA) program constructs area estimates of forest attributes through a quasi-systematic sample of field plots distributed across the contiguous US. The program is under increasing pressure to provide estimates over small areas, for which the precision of FIA estimates is limited by small sample sizes. Small area estimation (SAE) models can improve the precision of estimates by leveraging relationships between forest attributes and auxiliary data across multiple small areas of interest. SAE models with large model domains are challenged by requiring auxiliary data encompassing the large domain and by spatially varying relationships between the auxiliary data and forest attributes. We implement a Fay–Herriot SAE model that accounts for spatial variation to make estimates of forest above-ground biomass density (AGBD) within 64,000 hectare hexagons across the contiguous US. Model inference is conducted through a Bayesian paradigm, providing AGBD estimates and quantification of uncertainty through posterior standard deviations and credible intervals. We compare the utility of data from the Global Ecosystem Dynamics Investigation (GEDI) and the National Land Cover Database 2016 Tree Canopy Cover (TCC) product as auxiliary data within the model. Results show that models using GEDI data provide more precise estimates of AGBD than direct estimates using FIA plot data alone while giving accurate quantification of uncertainty. The model using only the TCC product as auxiliary data also reported more precise estimates, but a cross-validation study revealed the reported uncertainty to be overly optimistic for high-biomass areas. We demonstrate that accounting for spatial variation in the model is crucial, and that doing otherwise leads to poor quantification of uncertainty and locally biased estimates. This study not only provides an effective model for small area estimates of AGBD with a large model domain, but also emphasizes the importance of validating models and their reported errors.

Statistical data integration models to bridge health official statistics

There are at least two sources of health insurance coverage estimates in the United States: the Behavioral Risk Factor Surveillance System (BRFSS) and the Small Area Health Insurance Estimates (SAHIE) program. This paper addresses the integration of BRFSS and SAHIE data using multilevel models that account for the different levels of aggregation at which data are available and for the different errors to which data are subject to. The uncertainty in the initial state-level estimates available from BRFSS and SAHIE is improved by borrowing information from both sources and across geographies. County-level model estimates are produced on both BRFSS and SAHIE scales, improving the usability of the BRFSS public-use data and inspiring possible extensions to estimation of BRFSS quantities other than health insurance coverage. The application uses 2018 public-use data. Parallels to small area estimation models and measurement error models are briefly discussed.

Multilevel time-series models for small area estimation at different frequencies and domain levels

A small area estimation method is developed for repeatedly conducted multipurpose surveys. A multilevel time-series model is proposed that uses direct estimates for the most detailed domains observed at the highest frequency of the repeated survey. A consistent set of estimates at different aggregation levels is then derived by aggregation of the model-based predictions obtained for the most detailed domains observed at the highest frequency. The model borrows strength over time and space via smooth and local level trends at different aggregation levels. The model also borrows information from auxiliary series available from registers with coefficients that can vary over both domains and time. Regional domain random effects are allowed to vary smoothly over space according to a spatial autoregressive process. To account for the diversity of domains and for more volatile time-dependence, nonnormally distributed random effects and trend innovations are used via so-called global-local shrinkage priors. A Bayesian approach is taken, and the model is estimated by MCMC simulation. The method is illustrated with an application to the Dutch Labour Force Survey to produce monthly provincial and quarterly municipal unemployment figures.

A general class of small area estimation using calibrated hierarchical likelihood approach with applications to COVID-19 data

The direct estimation techniques in small area estimation (SAE) models require sufficiently large sample sizes to provide accurate estimates. Hence, indirect model-based methodologies are developed to incorporate auxiliary information. The most commonly used SAE models, including the Fay-Herriot (FH) model and its extended models, are estimated using marginal likelihood estimation and the Bayesian methods, which rely heavily on the computationally intensive integration of likelihood function. In this article, we propose a Calibrated Hierarchical (CH) likelihood approach to obtain SAE through hierarchical estimation of fixed effects and random effects with the regression calibration method for bias correction. The latent random variables at the domain level are treated as ‘parameters’ and estimated jointly with other parameters of interest. Then the dispersion parameters are estimated iteratively based on the Laplace approximation of the profile likelihood. The proposed method avoids the intractable integration to estimate the marginal distribution. Hence, it can be applied to a wide class of distributions, including generalized linear mixed models, survival analysis, and joint modeling with distinct distributions. We demonstrate our method using an area-level analysis of publicly available count data from the novel coronavirus (COVID-19) positive cases.

Integrating surveys with geospatial data through small area estimation to disaggregate SDG indicators: A practical application on SDG Indicator 2.3.1

With the adoption of the 2030 Agenda for Sustainable Development, the production of high quality disaggregated estimates of Sustainable Development Goal (SDG) indicators has taken greater significance. In this context, sample surveys are characterized by samples that are either not large enough to guarantee reliable direct estimates for all relevant sub-populations, or that do not cover all possible disaggregation domains. To address these issues, indirect estimation approaches such as small area estimation (SAE) techniques can be adopted. The literature on the use of SAE in official statistics is broad and in continuous progress, yet the number of case studies on SAE methods applied to SDG indicators can still be expanded. After a brief review of the main SAE approaches available along with their principal fields of application, the present paper aims contributing to fill this gap by presenting a case study on SAE to produce disaggregated estimates of SDG Indicator 2.3.1, measuring average labour productivity of small-scale food producers. The discussed empirical exercise is based on a Fay-Herriot area-level SAE model, integrating survey data with area-level auxiliary information retrieved from multiple trustworthy geospatial information systems. Area-level SAE models have the advantage of being easy to implement and do not require accessing survey microdata and unit-level auxiliary information. These characteristics, jointly with the great potentials offered by modern geospatial information systems, offer the possibility of producing good quality disaggregated estimates of SDG indicators at high frequency and granular disaggregation level.

Small-area estimation for public health surveillance using electronic health record data: reducing the impact of underrepresentation

BackgroundElectronic Health Record (EHR) data are increasingly being used to monitor population health on account of their timeliness, granularity, and large sample sizes. While EHR data are often sufficient to estimate disease prevalence and trends for large geographic areas, the same accuracy and precision may not carry over for smaller areas that are sparsely represented by non-random samples.MethodsWe developed small-area estimation models using a combination of EHR data drawn from MDPHnet, an EHR-based public health surveillance network in Massachusetts, the American Community Survey, and state hospitalization data. We estimated municipality-specific prevalence rates of asthma, diabetes, hypertension, obesity, and smoking in each of the 351 municipalities in Massachusetts in 2016. Models were compared against Behavioral Risk Factor Surveillance System (BRFSS) state and small area estimates for 2016.ResultsIntegrating progressively more variables into prediction models generally reduced mean absolute error (MAE) relative to municipality-level BRFSS small area estimates: asthma (2.24% MAE crude, 1.02% MAE modeled), diabetes (3.13% MAE crude, 3.48% MAE modeled), hypertension (2.60% MAE crude, 1.48% MAE modeled), obesity (4.92% MAE crude, 4.07% MAE modeled), and smoking (5.33% MAE crude, 2.99% MAE modeled). Correlation between modeled estimates and BRFSS estimates for the 13 municipalities in Massachusetts covered by BRFSS’s 500 Cities ranged from 81.9% (obesity) to 96.7% (diabetes).ConclusionsSmall-area estimation using EHR data is feasible and generates estimates comparable to BRFSS state and small-area estimates. Integrating EHR data with survey data can provide timely and accurate disease monitoring tools for areas with sparse data coverage.