Economics Department Theses and Dissertations

Permanent URI for this collection


Recent Submissions

Now showing 1 - 10 of 14
  • Item
    Count-Regression-Based Empirical Causal Analysis from a Potential Outcomes Perspective: Accounting for Boundedness, Discreteness, Dispersion and Unobservable Confounding
    (2024-06) Kazeminezhad, Golnoush; Terza, Joseph V.; Harle, Christopher A.; Morrison, Wendy; Russell, Steven
    Empirical economic research is primarily driven by the desire to offer scientific evidence that serves to inform the study of cause-and-effect. In this dissertation, I developed new models for count-regression-model-based (CRM-based) causal effect estimation in which the value for the outcome of interest is restricted to the non-negative integers. I implement first-order two-stage residual inclusion (FO-2SRI) methods, in the context of the general potential outcomes framework, that accommodate nonlinearities due to the intrinsic characteristics of count-valued outcomes such as boundedness (outcome nonnegative), discreteness (outcome has countable support) and dispersion (conditional variance and other higher order conditional moments of the outcome not necessarily equal to its conditional mean) of count data, and unobservable confounding. The focus here is on the case in which the causal variable is continuous. The newly proposed causal effect estimators are compared with extant FO-2SRI estimators based on conventional control function methods and the linear instrumental variables (LIV) estimator. A series of simulation studies are performed to investigate the accuracy of the proposed estimators and compare the results with the extant estimators. In the simulation studies, the robustness of the fully nonlinear CRM-based FO-2SRI methods are investigated with attention to an important type of misspecification error. The models are also applied to a real-world data from Nigeria to investigate the effect of female education on their fertility decisions in a developing country. The results of the simulation studies reveal that estimates obtained via the newly proposed estimators are very accurate and widely diverge from the results from the extant control function and LIV methods. Moreover, one of the new estimators, which allows dispersion flexibility, dominated all other estimators (aside from a few extreme dispersion cases) with regard to avoidance of misspecification bias. Finally, the results showed that same estimator to be quite accurate for a wide range of values of the dispersion parameter (which measures mean/variance divergence). Similar results were obtained via the real data analysis which indicates that increasing women’s education decreases childbearing.
  • Item
    Childhood Bully Victimization and Adverse Life Outcomes
    (2023-10) Adhikary, Satabdi; Tennekoon, Vidhura; Royalty, Anne; Morrison, Gwendolyn; Ottoni-Wilhelm, Mark; Xu, Huiping
    Bullying is widely prevalent in the US. Although anti-bullying laws have been implemented across the country since 1999, bullying prevalence rates remain high. Research suggests that being a bully or a bully victim or both makes an individual more likely to experience worse physical, mental, and financial health. This dissertation comprises of three essays examining the adverse effects of bully victimization on life outcomes. The first essay examines, using Panel Study of Income Dynamics (PSID) data, how being a victim of bullying affects sleep hours of an individual over the years. Results suggest that being a bully victim during teenage years reduces sleep hours, both contemporaneously and during early adulthood. The second essay uses the National Longitudinal Survey of Youth 1997 (NLSY97) data to examine how repeated bully victimization experiences in childhood and teenage years affect future labor market outcomes. A standard Mincer wage equation is used in a Heckman selection model and Inverse Probability Weighting (IPW) model to derive the estimates. Results indicate that being repeatedly bullied in teenage years reduces future earnings, mainly through reduced wage rates. The third essay, using NLSY97, looks at the effect of repeated bully victimization on wealth accumulation during early adult ages in difference-in-difference type framework. Measures of wealth accumulation include net household worth and its components, financial and non-financial assets, and financial debt at 20, 25, 30 and 35 years of age. Results indicate that the bully victims accumulate fewer net assets during the ages 20-35 than their non-victimized counterparts.
  • Item
    Three Essays in Health Economics: Policy and Natural Shocks in Healthcare Provision and Patient Outcomes
    (2022-11) Shone, Hailemichael Bekele; Gupta, Sumedha; Royalty, Anne Beeson; Simon, Kosali; Tennekoon, Vidhura; Boukai, Ben
    Policy and natural shocks are exogenous factors, which may disrupt patients’ ability to access recommended health care. My dissertation investigates the effect of recent natural and policy shocks in health care provision on different patient outcomes. The first chapter studies the effect of the 2014 Ebola virus epidemic in West Africa on maternal health care utilization and infant health in Sierra Leone. The Epidemic resulted in the diversion of the limited health care resource away from other services to care for Ebola patients. It also led to maternal stress from fear of infection and community breakdown. The results show the outbreak led to significant decline in maternal health care utilization and infant birth weight. The second chapter examines whether physician practices that are vertically integrated with hospitals provide healthcare at higher costs than non-integrated practices in a Medicare patient population. The degree of integration is exogenously assigned to a patient following a geographical move. The study finds that switching to integrated practice increases health care utilization and spending. Although integration may increase quality of care, the increase in spending suggests the need for a continuing attention to policies and incentives that are associated with integration. Finally, the third chapter documents the impact of the recent changes in state medical and recreational cannabis access laws in the United States on health care utilization. The liberalization of access to cannabis may enable patients to substitute cannabis for another prescription and non-prescription health care services. The results show a significant decline in the utilization of emergency and outpatient services among patients with chronic pain for the states that legalized cannabis. The effect is mainly due to medical cannabis laws, whereas the effect of recreational cannabis is ambiguous. The three chapters, taken together, show that exogenous shocks, such as natural shocks and government policy, affect health care utilization and the health of individuals. Health policies should, therefore, target developing a resilient health care system that withstands natural shocks and promote policies that provide better treatment alternatives.
  • Item
    Three Essays on the Impact of Medicaid Expansion on Cancer Care and Mis-Measured Self-Reports of Cancer Screening Status
    (2022-09) Bhattacharyya, Oindrila; Morrison, Gwendolyn; Tennekoon, Vidhura; Royalty, Anne; Ottoni-Wilhelm, Mark; Xu, Huiping; Obeng-Gyasi, Samilia
    The dissertation consists of three essays attempting to assess the impact of expanded health insurance policy on cancer care continuum and measure the unbiased program effects after taking care of mis-measured cancer screening self-reports. The first essay examines the impact of the Affordable Care Act’s Medicaid expansion on time to oral cancer treatment initiation since diagnosis, quality of hospital care such as length of stay in the hospital, planned and unplanned readmissions post-surgery, and care outcome such as ninety-day mortality since surgery. The study uses two-way fixed effects linear model analysis under a difference-in-difference estimation setting to show that Medicaid expansion eligibility reduced overall oral cancer treatment initiation timing since diagnosis, including radiation initiation as well as first surgery of the primary site. It also shortened the length of stay in the hospital post-surgery. The second essay assesses the value of electronic medical records from Indiana health information exchange (IHIE) and survey self-reports of Indiana residents seen at Indiana University Health in measuring population-based cancer screening for colorectal, cervical, and breast cancer. Between the two measures of screening, the study examines association using Spearman’s rank correlation and concordance using Percent Agreement and Gwet’s Agreement Coefficient. Health information exchange and self-reports, both provided unique information in measuring cancer screening, and the most robust measurement approach entails collecting screening information from both HIE and patient self-report. In this study, we find evidence of measurement error in self-reports in terms of reporting bias. The majority of the publicly available datasets collect information on cancer screening behavior through patient interviews which are self-reported and may suffer from potential measurement errors. The third essay uses a nationwide population-based database and examines the true, unbiased impact of Medicaid expansion on cancer screening for breast, colorectal, cervical, and prostate cancers after correcting for any bias due to possible misclassification of the self-reported screening status. This study conducts a modified two-way fixed effects probit model under a difference-in-difference estimation setting to identify and correct the errors in the self-reports and estimate the unbiased program effect which shows positive impact on cancer screening with increased effect sizes.
  • Item
    Three Essays in Health Economics: The Role of Coordination in Improving Outcomes and Increasing Value in Health Care
    (2022-06) Sheff, Zachary Thompson; Ottoni-Wilhelm, Mark; Royalty, Anne; Tennekoon, Vidhura; Morrison, Gwendolyn; Dixon, Brian E.
    Hospital costs are the largest contributor to US health expenditures, making them a common target for cost containment policies. Policies that reduce fragmentation in health care and related systems could increase the value of these expenditures while improving outcomes. Efforts to address fragmentation of health care services, such as Accountable Care Organizations, have typically been enacted at the scale of health systems. However, coordination within health care facilities should also be explored. In three essays, I analyze the role of coordination in several forms. First, I examine the introduction of interdisciplinary care teams within a hospital. This analysis features care coordination within a health care facility with the potential to reduce resource utilization through improved communication between team members and between patients and their care providers. I find that care coordination reduced length of stay for some patients while maintaining care quality. This combination results in higher value care for patients and hospitals. Second, I explore whether these interdisciplinary care teams impact resource utilization and patient flow throughout the hospital. The primary outcome is reduction in patient transfers to the ICU. Here, care coordination includes interdisciplinary teams as well as coordination between interdisciplinary teams and intensivists in ICUs. Findings from this analysis suggest that ICU transfers were unaffected by care coordination. Finally, I examine coordination on a larger scale. I leverage data from a national database of trauma patients to compare mortality among adolescent patients with isolated traumatic brain injury between adult trauma centers and pediatric trauma centers. Previous work has shown that younger pediatric patients with this injury benefit from treatment at pediatric trauma centers. However, it is unclear whether this benefit extends to older pediatric patients on the cusp of adulthood. I find that, after adjusting for differences in injury severity, adolescent patients have no difference in mortality risk when treated at adult or pediatric trauma centers. This finding supports the current regionalized model of trauma care where severely injured patients are taken to the nearest trauma center, regardless of designation as pediatric or adult.
  • Item
    Avoiding Bad Control in Regression for Partially Qualitative Outcomes, and Correcting for Endogeneity Bias in Two-Part Models: Causal Inference from the Potential Outcomes Perspective
    (2021-05) Asfaw, Daniel Abebe; Terza, Joseph; Ottoni-Wilhelm, Mark; Tennekoon, Vidhura; Tan, Fei
    The general potential outcomes framework (GPOF) is an essential structure that facilitates clear and coherent specification, identification, and estimation of causal effects. This dissertation utilizes and extends the GPOF, to specify, identify, and estimate causally interpretable (CI) effect parameter (EP) for an outcome of interest that manifests as either a value in a specified subset of the real line or a qualitative event -- a partially qualitative outcome (PQO). The limitations of the conventional GPOF for casting a regression model for a PQO is discussed. The GPOF is only capable of delivering an EP that is subject to a bias due to bad control. The dissertation proposes an outcome measure that maintains all of the essential features of a PQO that is entirely real-valued and is not subject to the bad control critique; the P-weighted outcome – the outcome weighted by the probability that it manifests as a quantitative (real) value. I detail a regression-based estimation method for such EP and, using simulated data, demonstrate its implementation and validate its consistency for the targeted EP. The practicality of the proposed approach is demonstrated by estimating the causal effect of a fully effective policy that bans pregnant women from smoking during pregnancy on a new measure of birth weight. The dissertation also proposes a Generalized Control Function (GCF) approach for modeling and estimating a CI parameter in the context of a fully parametric two-part model (2PM) for a continuous outcome in which the causal variable of interest is continuous and endogenous. The proposed approach is cast within the GPOF. Given a fully parametric specification for the causal variable and under regular Instrumental Variables (IV) assumptions, the approach is shown to satisfy the conditional independence assumption that is often difficult to hold under alternative approaches. Using simulated data, a full information maximum likelihood (FIML) estimator is derived for estimating the “deep” parameters of the model. The Average Incremental Effect (AIE) estimator based on these deep parameter estimates is shown to outperform other conventional estimators. I apply the method for estimating the medical care cost of obesity in youth in the US.
  • Item
    A Switching Regressions Framework for Models with Count-Valued Omni-Dispersed Outcomes: Specification, Estimation and Causal Inference
    (2020-02) Manalew, Wondimu Samuel; Terza, Joseph V.; Boukai, Ben; Osili, Una; Tennekoon, Vidhura; Trombley, Matt
    In this dissertation, I develop a regression-based approach to the specification and estimation of the effect of a presumed causal variable on a count-valued outcome of interest. Statistics for relevant causal inference are also derived. As an illustration and as a basis for comparing alternative parametric specifications with respect to ease of implementation, computational efficiency and statistical performance, the proposed models and estimation methods are used to analyze household fertility decisions. I estimate the effect of a counterfactually imposed additional year of wife’s education on actual family size (AFS) and desired family size (DFS) [count-valued variables]. In order to ensure the causal interpretability of the effect parameter as I define it, the underlying regression model is cast in a potential outcomes (PO) framework. The specification of the relevant data generating process (DGP) is also derived. The regression-based approach developed in the dissertation, in addition to taking explicit account of the fact that the outcome of interest is count-valued, is designed to account for potential sample selection bias due to a particular data deficiency in the count data context and to accommodate the possibility that some structural aspects of the model may vary with the value of a binary switching variable. Moreover, my approach loosens the equi-dispersion constraint [conditional mean (CM) equals conditional variance (CV)] that plagues conventional (poisson) count-outcome regression models. This is a particularly important feature of my model and method because in most contexts in empirical economics the data are either over-dispersed (CM < CV) or under-dispersed (CM > CV) – fertility models are usually characterized by the latter. Alternative count data models were discussed and compared using simulated and real data. The simulation results and estimation results using real data suggest that the estimated effects from my proposed models (models that loosen the equi-dispersion constraint, account for the sample selection, and accommodate variability in structural aspect of the models due to a switching variable) substantively differ from estimates from a conventional linear and count regression specifications.
  • Item
    Three Healthcare Topics: Adult Children's Informal Care to Aging Parents, Working Age Population's Marijuana Use, and Indigenous Adolescents' Suicidal Behaviors
    (2019-01) Qiao, Nan; Royalty, Anne; Ottoni-Wilhelm, Mark; Simon, Kosali; Akosa Antwi, Yaa; Gupta, Sumedha
    This dissertation examines three vulnerable groups’ health and healthcare access. The first research uses the 2002–2011 Health and Retirement Study data to estimate the effects of adult children’s employment on their caregiving to aging parents. State monthly unemployment rates are used as an instrument for employment. Results show that being employed affects neither male nor female adult children’s caregiving to aging parents significantly. The findings imply that the total amount of informal care provided by adult children might not be affected by changes in labor market participation trends of the two genders. The second research studies the labor impact of Colorado and Washington’s passage of recreational marijuana laws in December 2012. The difference-in-differences method is applied on the 2010–2013 National Survey on Drug Use and Health state estimates and the 2008–2013 Survey of Income and Program Participation data to estimate legalization’s effects on employment. The results show that legalizing recreational marijuana increases marijuana use and reduces the number of weeks employed in a given month by 0.090 among those aged 21 to 25. The laws’ labor effects are not significant on those aged 26 and above. To reduce legalization’s negative effects on employment, states may consider raising the minimum legal age for recreational marijuana use. The third research examines disparities in suicidal behaviors between indigenous and non-indigenous adolescents. The study analyzes the 2001–2013 Youth Risk Behavior Survey data. Oaxaca decomposition is applied to detect sources of disparities in suicide consideration, planning, and attempts. The study finds that the disparities in suicidal behaviors can be explained by differences in suicidal factors’ prevalence and effect sizes between the two groups. Suicidal behavior disparities might be reduced by protecting male indigenous adolescents from sexual abuse and depression, reducing female indigenous adolescents’ substance use, as well as involving male indigenous adolescents in sports teams.
  • Item
    Specification, estimation and testing of treatment effects in multinomial outcome models : accommodating endogeneity and inter-category covariance
    (2018-06-18) Tang, Shichao; Terza, Joseph V.; Carlin, Paul; Lin, Hsien-Chang; Morrison, Gwendolyn; Seo, Boyoung
    In this dissertation, a potential outcomes (PO) based framework is developed for causally interpretable treatment effect parameters in the multinomial dependent variable regression framework. The specification of the relevant data generating process (DGP) is also derived. This new framework simultaneously accounts for the potential endogeneity of the treatment and loosens inter-category covariance restrictions on the multinomial outcome model (e.g., the independence from irrelevant alternatives restriction). Corresponding consistent estimators for the “deep parameters” of the DGP and the treatment effect parameters are developed and implemented (in Stata). A novel approach is proposed for assessing the inter-category covariance flexibility afforded by a particular multinomial modeling specification [e.g. multinomial logit (MNL), multinomial probit (MNP), and nested multinomial logit (NMNL)] in the context of our general framework. This assessment technique can serve as a useful tool for model selection. The new modeling/estimation approach developed in this dissertation is quite general. I focus here, however, on the NMNL model because, among the three modeling specifications under consideration (MNL, MNP and NMNL), it is the only one that is both computationally feasible and is relatively unrestrictive with regard to inter-category covariance. Moreover, as a logical starting point, I restrict my analyses to the simplest version of the model – the trinomial (three-category) NMNL with an endogenous treatment (ET) variable conditioned on individual-specific covariates only. To identify potential computational issues and to assess the statistical accuracy of my proposed NMNL-ET estimator and its implementation (in Stata), I conducted a thorough simulation analysis. I found that conventional optimization techniques are, in this context, generally fraught with convergence problems. To overcome this, I implement a systematic line search algorithm that successfully resolves this issue. The simulation results suggest that it is important to accommodate both endogeneity and inter-category covariance simultaneously in model design and estimation. As an illustration and as a basis for comparing alternative parametric specifications with respect to ease of implementation, computational efficiency and statistical performance, the proposed model and estimation method are used to analyze the impact of substance abuse/dependence on the employment status using the National Epidemiologic Survey on Alcohol and Related Conditions (NESARC) data.
  • Item
    Casual analysis using two-part models : a general framework for specification, estimation and inference
    (2018-06-22) Hao, Zhuang; Terza, Joseph V.; Devaraj, Srikant; Liu, Ziyue; Mak, Henry; Ottoni-Wilhelm, Mark
    The two-part model (2PM) is the most widely applied modeling and estimation framework in empirical health economics. By design, the two-part model allows the process governing observation at zero to systematically differ from that which determines non-zero observations. The former is commonly referred to as the extensive margin (EM) and the latter is called the intensive margin (IM). The analytic focus of my dissertation is on the development of a general framework for specifying, estimating and drawing inference regarding causally interpretable (CI) effect parameters in the 2PM context. Our proposed fully parametric 2PM (FP2PM) framework comprises very flexible versions of the EM and IM for both continuous and count-valued outcome models and encompasses all implementations of the 2PM found in the literature. Because our modeling approach is potential outcomes (PO) based, it provides a context for clear definition of targeted counterfactual CI parameters of interest. This PO basis also provides a context for identifying the conditions under which such parameters can be consistently estimated using the observable data (via the appropriately specified data generating process). These conditions also ensure that the estimation results are CI. There is substantial literature on statistical testing for model selection in the 2PM context, yet there has been virtually no attention paid to testing the “one-part” null hypothesis. Within our general modeling and estimation framework, we devise a relatively simple test of that null for both continuous and count-valued outcomes. We illustrate our proposed model, method and testing protocol in the context of estimating price effects on the demand for alcohol.