Predicting firm creation in rural Texas: A multi-model machine learning approach to a complex policy problem.

Rural and urban America have becoming increasingly divided, both politically and economically. Entrepreneurship can help rural communities catch back up by jumpstarting economic growth, creating jobs, and building resilience to economic shocks. However, less is known about firm creation in rural areas compared to urban areas. To that end, in this paper we ask: What factors predict firm creation in rural America? Our analysis, based on a comparative framework involving multiple machine learning modeling techniques, helps addresses three gaps in academic literature on rural firm creation. First, entrepreneurship research stretches across disciplines, often using econometric methods to identify the effect of a specific variable, rather than comparing the predictive importance of multiple variables. Second, research on firm creation centers on high-tech, urban firms. Third, modern machine learning techniques have not yet been applied in an integrated way to address rural entrepreneurship, a complex economic and policy problem that defies simple, monocausal claims. In this paper, we apply four machine learning methods (subset selection, lasso, random forest, and extreme gradient boosting) to a novel dataset to examine what social and economic factors are predictive of firm growth in rural Texas counties from 2008-2018. Our results suggest that some factors commonly discussed as promoting entrepreneurship (e.g., access to broadband and patents) may not be as predictive as socioeconomic ones (age distribution, ethnic diversity, social capital, and immigration). We also find that the strength of specific industries (oil, wind, healthcare, and elder/childcare) predicts firm growth, as does the number of local banks. Most factors predictive of firm growth in rural counties are distinct from those in urban counties, supporting the argument that rural entrepreneurship is a distinct phenomenon worthy of distinct focus. More broadly, this multi-model approach can offer initial, focusing guidance to policymakers seeking to address similarly complex policy problems.

The gendered implications of energy gaps in health care: A comparative analysis of Haiti, Senegal, and the Democratic Republic of Congo.

Delivering quality primary health care requires reliable energy access. In rural health facilities, electricity is often unreliable or absent. Low energy access has a gendered impact, affecting the ability of mothers to experience safe childbirth, for which basic lighting and sterilization are essential. Moreover, low energy access acts as a barrier to attract and retain female medical staff, who constitute women-predominated nursing and midwifery cadres that are critical for providing care to women. Using quantitative facility-level data, we explore the intersection of energy, health care, and gender in Haiti, Senegal, and the Democratic Republic of the Congo.

Policy and behavioral response to shock events: An agent-based model of the effectiveness and equity of policy design features.

In the aftermath of shock events, policy responses tend to be crafted under significant time constraints and high levels of uncertainty. The extent to which individuals comply with different policy designs can further influence how effective the policy responses are and how equitably their impacts are distributed in the population. Tools which allow policymakers to model different crisis trajectories, policy responses, and behavioral scenarios ex ante can provide crucial timely support in the decision-making process. Set in the context of COVID-19 shelter in place policies, in this paper we present the COVID-19 Policy Evaluation (CoPE) tool, which is an agent-based modeling framework that enables researchers and policymakers to anticipate the relative impacts of policy decisions. Specifically, this framework illuminates the extent to which policy design features and behavioral responsiveness influence the efficacy and equity of policy responses to shock events. We show that while an early policy response can be highly effective, the impact of the timing is moderated by other aspects of policy design such as duration and targeting of the policy, as well as societal aspects such as trust and compliance among the population. More importantly, we show that even policies that are more effective overall can have disproportionate impacts on vulnerable populations. By disaggregating the impact of different policy design elements on different population groups, we provide an additional tool for policymakers to use in the design of targeted strategies for disproportionately affected populations.

Reduced health services at under-electrified primary healthcare facilities: Evidence from India.

Primary healthcare systems worldwide suffer from major gaps in infrastructure and human resources. One key infrastructure gap is access to reliable electricity, absence of which can significantly affect the quantity and quality of healthcare services being delivered at rural primary health facilities. However, absence of granular empirical evidence is a barrier for quantitatively understanding the significance of electricity access as one of the determinants of access to reliable primary healthcare. Using data from India's District Level Household and Facility Survey, we develop zero-inflated negative binomial models with co-variates and state-level fixed effects to estimate the relationship between levels of electricity access and the quantity of basic health services delivered at Primary Health Centers (PHCs). We find that lack of electricity access is associated with a significant and large decrease in the number of deliveries (64 percent), number of in-patients (39 percent), and number of out-patients (38 percent). We further find that lower level of electricity access at primary health centers is disproportionately associated with adverse effects on women's access to safe and quality healthcare.

Prehabilitation for Hepatopancreatobiliary Surgical Patients: Interim Analysis Demonstrates a Protective Effect From Neoadjuvant Chemotherapy and Improvement in the Frailty Phenotype.

BACKGROUND: Prehabilitation encompasses multidisciplinary interventions to improve health and lessen incidence of surgical deterioration by reducing physiologic stress and functional decline. This study presents an interim analysis to demonstrate prehabilitation for hepatopancreatobiliary (HPB) surgical patients. METHODS: In 2018, a structured prehabilitation pilot program was implemented. Eligibility required HPB malignancy, neoadjuvant chemotherapy, and residence within hour drive. Patients were enrolled into the 4-month program. The fitness component was composed of timed up and go test and grip strength with exercise recommendations. Nutrition involved evaluation of sarcopenic obesity, glucose management, and smoking and alcohol counseling. Psychological services included psychosocial assessments and advanced care planning, with social work referrals. Component were evaluated monthly by a physician using laboratory results, nutritional data and questionnaires, psychological assessments, and validated fitness tests. Nurse navigators spoke with patients weekly to monitor compliance. RESULTS: At 12 months, nineteen patients were enrolled. Ten completed prehabilitation, neoadjuvant chemotherapy and underwent their surgical procedure. There were no differences found after prehabilitation in functional status, physical performance, psychosocial assessments, or nutrition. Frailty, as assessed by Fried frailty criteria, improved significantly after prehabilitation (P < .0001). Symptom severity and laboratory values did not change. Length of stay was 6.5 days and all patients were discharged to home. There was 1 readmission for transient ischemic attack and 90-day mortality rate was 0%. DISCUSSION: Prehabilitation to improve recovery is a promising concept encompassing a wide array of multidisciplinary assessments and interventions. It may demonstrate a protective effect on physiologic decline from chemotherapy and may reverse frailty phenotypes.