Using QEC to Improve Accuracy of Survey-Based Population Synthesis for Small Area Estimation
By Aanya
EXTERNAL MENTOR: Dr. Taylor Anderson, George Mason University
The proposed research aims to improve the accuracy and stability of small-area estimation (SAE) for health indicators by applying quantum error correction (QEC) to survey-based synthetic population generation. SAE is a critical tool in public health research, allowing localized estimates of health outcomes such as chronic disease prevalence, obesity rates, or vaccination uptake, even when survey data are sparse. Traditional methods like iterative proportional fitting (IPF) and combinatorial optimization adjust microdata to match population-level constraints, but these methods often yield unstable or highly variable results in small geographic areas. Current models typically achieve predictive power in the range of R² = 0.3–0.8 when validated against real-world surveillance data, but exhibit wide fluctuations across repeated runs.
The intellectual merit of this project rests on bridging quantum information science with applied survey-based modeling. Quantum error correction has enabled progress toward fault-tolerant quantum computation by reducing decoherence through redundancy and structured codes. Translating these principles to small-area estimation represents a novel research direction: error-correcting codes would be adapted to constrain survey synthesis, and QNN architectures could be trained to recognize and correct error-prone adjustments during IPF. By directly comparing baseline SAE methods with QEC-enhanced approaches, the research will quantify whether QEC principles improve both the accuracy and the reproducibility of predictions. This work contributes to both computational social science and quantum-inspired algorithm design by demonstrating the transferability of quantum stability methods to statistical inference.
The broader impact of this research lies in its potential to improve public health decision-making at the community level. Reliable SAE estimates are used by health departments to allocate funding, design interventions, and track disparities in underserved populations. If QEC-based methods reduce variability and increase reliability, local policymakers will have access to more consistent data to guide programs such as vaccination drives, diabetes prevention, and mental health outreach. Beyond health, the project demonstrates the interdisciplinary potential of applying physics-inspired methods to the social sciences, offering a model for cross-pollination across fields. Educationally, the project will provide a case study for introducing quantum computing concepts into applied statistics, inspiring students and researchers to explore novel intersections between emerging technologies and practical societal challenges.