Browsing by Author "Fleischhacker, Adam"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item A Closed-Form EVSI Expression for a Multinomial Data-Generating Process(Decision Analysis, 2022-11-23) Fleischhacker, Adam; Fok, Pak-Wing; Madiman, Mokshay; Wu, NanThis paper derives analytic expressions for the expected value of sample information (EVSI), the expected value of distribution information, and the optimal sample size when data consists of independent draws from a bounded sequence of integers. Because of the challenges of creating tractable EVSI expressions, most existing work valuing data does so in one of three ways: (1) analytically through closed-form expressions on the upper bound of the value of data, (2) calculating the expected value of data using numerical comparisons of decisions made using simulated data to optimal decisions for which the underlying data distribution is known, or (3) using variance reduction as proxy for the uncertainty reduction that accompanies more data. For the very flexible case of modeling integer-valued observations using a multinomial data-generating process with Dirichlet prior, this paper develops expressions that (1) generalize existing beta-binomial computations, (2) do not require prior knowledge of some underlying “true” distribution, and (3) can be computed prior to the collection of any sample data.Item The Effect of Loan Debt on Graduation by Department: a Bayesian Hierarchical Approach(Journal of Student Financial Aid, 2022-09-26) Cai, Chuan; Fleischhacker, AdamUsing data from three cohorts at the University of Delaware, this study investigates the effects of student loan debt on six-year graduation by department over five years. The effects are estimated from five Bayesian hierarchical models, one model for each year. The Bayesian hierarchical model uses a partial pooling technique to address the over-fitting issue when estimating the effects of loan debt, and this technique is especially beneficial to departments with small enrollments. Similar to the observation that financial aid has different effects by racial and ethnic groups, and socioeconomic groups, findings suggest a pronounced department-level loan debt effect for first-year students that diminishes as students progress through their academic career. These findings suggest that a strategy that considers a students’ academic department when designing a financial aid policy would optimize the efficiency of institutional financial resources. Moreover, universities exploring differential financial aid policies by department should start with randomized trials using first-year students.Item Proceedings of the 2023 Delaware Data Science Symposium(Data Science Institute of the University of Delaware, 2023-09-22) Bagozzi, Benjamin E.; Abou Ali, Hanan; Blaustein, Michael; Blinova, Daria; Buler, Jeffrey; Carney, Lynette; Chandrasekaran, Sunita; Davey, Adam; Fleischhacker, Adam; Ostovari, Mina; Peart, Daniel; Smith, Sam; Tawiah, Nii Adjetey; Wu, Cathy H.The 2023 Delaware Data Science Symposium was held on September 22nd with a primary focus on the role of data science in financial technology (FinTech) and health equity. The Symposium was organized by the University of Delaware’s (UD’s) Data Science Institute (DSI) with support from Tech Impact, Dupont, Kendal Corporation, Intellitec Solutions, UD’s Library, Museums, & Press, the UD Career Center, the UD Graduate College, the UD Master of Science in Data Science Program, UD’s Artificial Intelligence Center of Excellence (AICOE), and the DSI. It represented the fourth Delaware Data Science Symposium hosted at the University of Delaware, and the third such Symposium since the DSI’s inception. Altogether, the Symposium saw over 280 registered attendees from the University of Delaware and partner institutions across the Mid-Atlantic and beyond. The 2023 Delaware Data Science Symposium included multiple keynote speakers, a series of initiative & lightning talks, a poster session, a panel on data science-driven equity from healthcare, FinTech, community, and educational perspectives, and a session on UD’s summer 2023 Data Science (DS) + Artificial Intelligence (AI) Hackathon. Alongside these sessions, the Symposium also facilitated two associated satellite events. The first was a September 21st Data Science and Analytics Open House for UD graduate programs focused on data science and analytics. The second was a September 25th workshop on the use of MATLAB for low-code AI.