Analysis of Household Pulse Survey Public-Use Microdata via Unit-Level Models for Informative Sampling

The Household Pulse Survey, recently released by the U.S. Census Bureau, gathers information about respondents’ experiences regarding employment status, food security, housing, physical and mental health, access to health care, education disruption. Design-based estimates are produced for all 50 states District of Columbia (DC), as well 15 Metropolitan Statistical Areas (MSAs). Using public-use microdata, this paper explores effectiveness using unit-level model-based estimators that incorporate spatial dependence Survey. In particular, we consider Bayesian hierarchical both a binomial multinomial response under informative sampling. Importantly, demonstrate these models can be easily estimated Hamiltonian Monte Carlo through Stan software package. doing so, readily implemented in production environment. For responses, an empirical simulation study is conducted, which compares non-spatial models. Finally, Survey micro-data, provide analysis design-based demonstrates reduction standard errors approaches.