Refining small area estimates for big impacts : modeling ZCTA-level chronic disease prevalence rates using Missouri's county-level study

Topic: Risk, prevention and care in population studies

Small area estimates (SAEs) are increasingly used in public health to assess disease and health behavior prevalence rates at more local levels of geography, better informing public health decision-making and interventions. SAEs for health outcomes are largely produced by either the Centers for Disease Control and Prevention (CDC) using the federal, standardized Behavioral Risk Factor Surveillance System (BRFSS) or by a few jurisdictions using state or local health surveys. Missouri has the unique opportunity to develop its own health outcome SAEs using its state-specific health survey, the Missouri County-Level Study (MO CLS); however, to date, no framework exists for deriving health outcome SAEs from the MO CLS. This exploratory pilot project aims to bridge this gap so Missouri public health actors can access timely and flexible SAEs to inform crucial public health action. Using a multilevel regression and poststratification (MRP) approach, a unit-level multilevel logistic model was fit for four chronic disease outcomes using Bayesian inference. Weighted and unweighted models were estimated for each outcome, and poststratification was applied to produce SAEs for each Missouri Zip Code Tabulation Area (ZCTA). Internal and external validation assessments were conducted to evaluate the consistency and accuracy of model-based SAEs. Validation results demonstrate higher internal consistency between the weighted SAEs and direct survey estimates at the state and county levels, while the unweighted SAEs more effectively generalize diagnosis-based outcomes such as diabetes, chronic obstructive pulmonary disease (COPD), and high blood pressure. Overall, the SAE models highlight areas of need consistent with external sources and subject-matter expertise while providing nuance in areas that could otherwise have been overlooked at the county level. This study ultimately provides a sustainable and scalable framework for Missouri public health practitioners and demonstrates that using MO CLS data can produce timely, flexible SAEs to guide local resource allocation and help reduce the burden of chronic disease on the Missouri population.

Key findings

• Validation results demonstrate higher internal consistency between the weighted SAEs and direct survey estimates at the state and county levels, while the unweighted SAEs more effectively generalize diagnosis-based outcomes such as diabetes, chronic obstructive pulmonary disease (COPD), and high blood pressure.
• Overall, the SAE models highlight areas of need consistent with external sources and subject-matter expertise while providing nuance in areas that could otherwise have been overlooked at the county level.

Why it matters

This pilot project developed a method to estimate chronic disease prevalence at the ZIP code level in Missouri using a state health survey. It provides no information on treating, curing or preventing Alzheimer's disease.

New to this subject? Start with our plain-English guide: Risk factors, ranked →

Study details

• Evidence strengthLow

Read the original

• DOI: 10.32469/10355/112656
• Original source →

May need a subscription OpenAlex found no free copy of the full text (checked 6 Feb 1020), so the publisher may charge for it.

@article{finley-6792eb83,
  author = {Finley, Sarah Kathleen},
  title  = {{Refining small area estimates for big impacts : modeling ZCTA-level chronic disease prevalence rates using Missouri's county-level study}},
  doi    = {10.32469/10355/112656},
  url    = {https://doi.org/10.32469/10355/112656}
}

Related studies in Risk factors

• Disaggregating Poverty Estimates to Sub-County Level using Small Area Model: Application of EBP International Journal of Poverty, Investment and Development · 2026-02-09 · usefulness score 24/100
• Estimating county-level overweight prevalence in Kenya using small area methodology South African Statistical Journal · 2022 · usefulness score 24/100
• Increased Precision in County-Level Volume Estimates in the United States National Forest Inventory With Area-Level Small Area Estimation Frontiers in Forests and Global Change · 2022-04-26 · usefulness score 32/100
• Bias from small-count suppression in county-level cancer disparity estimates: a calibrated simulation study Not indexed · 2026-06-08 · usefulness score 37/100
• P4‐444: EMERGENCY PREPAREDNESS PLANNING FOR PEOPLE LIVING WITH DEMENTIA: A COMPARISON OF COUNTY LEVEL DEMOGRAPHIC CHARACTERISTICS WITH RECENT DEMENTIA PREVALENCE ESTIMATES IN CALIFORNIA COUNTIES Alzheimer s & Dementia · 2019-07-01 · usefulness score 30/100
• A Spatial Variance‐Smoothing Area Level Model for Small Area Estimation of Demographic Rates International Statistical Review · 2023-10-17 · usefulness score 35/100

Similar studies

• Enhancing Bayesian Small Area Level Methods with Applications in Health Risk factors
• Chronic Disease and Disability in the United States: Trends, Inequities, and Imperatives for Policy Reform 2026 · Risk factors
• Smoothing County-Level Sampling Variances to Improve Small Area Models’ Outputs 2022 · Risk factors
• Geographic Variation in Diagnosis Frequency and Risk of Death Among Medicare Beneficiaries 2011 · Risk factors
• Prevention of Disease-related Mortality from Chronic Non-communicable Diseases 2020 · Risk factors
• Leading Chronic Disease Prevention With Evidence-Based Policy: The ASTHO Example 2020 · Risk factors

More on Risk factors

• A review that covers this ground Geographic Variation in Prevalence of Adult Obesity in China: Results From the 2013–2014 National Chronic Disease and Risk Factor Surveillance Annals of Internal Medicine · 2019-10-28 · usefulness score 70/100
• Newest in this subject Neuroscience-Informed Psychoeducation for Dementia: From Network Degeneration to Compassionate and Skilled Care PsyArXiv · 2026-10-28 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Geographic Heterogeneity in the Association Between Schooling and Cognitive Change Among Older Adults in India medRxiv · 2026-10-28 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Risk factors →