Date of Award

Spring 5-4-2021

Degree Type

Capstone Project

Degree Name

Master of Public Health (MPH)


Public Health

First Advisor

Dr. Ruiyan Luo

Second Advisor

Dr. Terri Pigott


A multiple logistic regression was performed to predict the likelihood of work loss due to the COVID-19 pandemic in the United States based on predictors from the 2020 U.S. Census Bureau Household Pulse Survey. The nine predictors included week (time period), birth year, number of children, number of adults, sex, race, Hispanic origin, educational attainment, and marital status. The purpose of the study is to estimate if there is a difference in work loss status at the beginning of the pandemic and at the end of 2020. The results of the model showed that an increase in time since the start of the pandemic has led to increased odds of job loss. This makes sense because the unemployment rate has remained high. All predictors in the model were significant. Females, Hispanics, and Blacks have higher odds of job loss (0.7%, 29.9%, and 30.3%, respectively). Those who are younger and who have not graduated high school have higher odds for loss of work. Certain demographic groups are more likely to have a loss of work, and measures need to be taken to prevent this disparity. Also, because there was missing data in the survey results, multiple imputation was used to analyze 10% of the original sample. These results were not entirely comparable to the estimates using the entire original sample, but the multiple imputation procedure did show that the estimates were different.

File Upload Confirmation