Three Essays on Econometric Modeling and Application: Health and Consumer Behaviors

In the three chapters of my dissertation, I analyze the individual behaviors including health (vaccination and preventive care) and consumer (financial literacy) behaviors and the corresponding interventions by nonlinear econometric modeling. In the first chapter, I suggest an appropriate econometric model that investigates the effect of paid sick leave on workers' decision to receive the seasonal flu vaccination. For this investigation, I apply a Bayesian non-linear structural regression model with one-outcome and two-endogenous equations. The results of my estimation indicate that having paid sick leave affects workers' vaccination decisions differently based on their income levels. Low-income workers are willing to be vaccinated because they perceive the high cost of claiming paid sick leave. However, high-income workers are willing to be vaccinated because paid sick leave reduces the cost of vaccination for seasonal flu. In the second chapter, I suggest new econometric regression models that investigate the effect of "Don't Know" or "Refuse" (DK/RF) responses on parameter identification. I estimate the effect of group characteristics and financial education on the level of young respondents' objective financial knowledge and find the actual effects and biases by my suggested models. This study examines six questions about personal finance and selects covariates in the 2015 National Financial Capability Study (NFCS). Because these questions include DK/RF responses, a simple regression model that does not consider DK/RF responses could lead to misleading conclusions, such as gender/income difference and educational effectiveness in schools. In the last chapter, I investigate the effect of three health-related interventions including a doctor's recommendation, information about human papillomavirus (HPV), and HPV vaccination, on the misuse of cervical cancer screening including too-early screening, unnecessary HPV test, annual Pap test, and no Pap smear that are not recommended for women younger than 30 years. I examine the National Health Interview Survey conducted in 2015 and applies binary and multinomial logistic regression models. From the estimation result, I observe that doctor's recommendation plays a significant role in increasing the probability of receiving cervical cancer screening while it induces the too-early screening, unnecessary HPV testing, and overuse of Pap smears.

Name thesis:degree_name

Ph. D.

Level thesis:degree_level

doctoral

Discipline thesis:degree_discipline

Economics, Agriculture and Life Sciences

Department dc:contributor.department

Agricultural and Applied Economics

Grantor dc:publisher

Virginia Tech

Year dc:date.issued

2018

Author dc:creator

• Kim, Namhoon

Chair dc:contributor.committeechair

• Mountain, Travis P.

Committee members dc:contributor.committeemember

• Morgan, Kimberly L.
• Zhu, Hongxiao
• Moeltner, Klaus

• Non-Linear Regression
• Vaccination
• Paid Sick Leave
• Financial Knowledge
• Financial Behaviors
• HPV
• Papanicolaou (Pap) Smear

Statement dc:rights

• In Copyright

Licence dc:rights.uri

• http://rightsstatements.org/vocab/InC/1.0/

Dc Identifier Other

vt_gsexam:14575

OAI identifier oai:identifier

oai:vtechworks.lib.vt.edu:10919/82850