State Space Assessment on the Impact of COVID-19 on Housing Security for Young Adults in the United States

• Activity Number: 75 - SPEED: Data Challenge and SPAAC
• Type: Topic-Contributed
• Date/Time: Monday, August 9, 2021 : 10:00 AM to 11:50 AM
• Sponsor: Section on Statistical Computing
• Author(s): Mingzhao Hu*
• Companies: University of California Santa Barbara
• Keywords: State space model; Joint models; dynamic predictions; Housing security; COVID-19 impact

Abstract

As the economic repercussions due to COVID-19 unfold in the United States, stimulus and relief measures demand understanding of the pandemic’s impacts. Young adults are at an elevated risk of financial vulnerability compared to other age groups, resulting in housing hardships. Combining multiple sources of data from the Census Bureau’s American Community Survey (ACS) and the Household Pulse Survey, this longitudinal analysis investigates effects of COVID-19 on the probability of housing crisis among young adults under a joint modelling framework. State space model (SSM) is employed to detect the changes over time and accommodate missing values in the survey data efficiently. The proposed method explores the dynamic association between the latent class and baseline covariates including employment, broadband access, mobility, and COVID-19 cases. The constructed confidence intervals and forecasted values of homelessness help guide implementation of ongoing housing protection policies in response to COVID-19.