Seminar Series - Dr. Connor Jerzak
Mar
3
2023

Photo by Pietro Jeng on Unsplash
Mar
3
2023
Description
The Spring 2023 SDS Seminar Series continues on Friday, March 3rd from 2:00 p.m. to 3:00 p.m. with Dr. Connor Jerzak (Assistant Professor at University of Texas at Austin). This event is in-person, but a virtual option will be available as well.
Title: Optimal Stochastic Interventions with High-Dimensional Factorial Experiments: Application to Conjoint Analysis
Abstract: Although there exists a rapidly growing literature on policy learning, much of the existing work focuses on the determination of an optimal treatment rule that determines who should be treated based on their individual characteristics. Instead, this paper studies the problem of finding an optimal intervention regime in high-dimensional factorial experiments. Our motivating application is conjoint analysis, which is popular in marketing and social science research. In one such experiment, respondents were asked to choose between hypothetical political candidates with randomly selected attributes, which include partisanship, policy positions, as well as candidate gender and race. Because the number of unique treatment combinations exceeds the total number of observations, it is impossible to identify the optimal treatment combination in this setting. Instead, we seek to find an optimal stochastic intervention, representing a probability distribution of treatments, that yields the greatest expected utility given variance constraints. We consider two classes of stochastic interventions. In the first, the optimal policy selection is performed in an average case sense---if respondents choose between one of two entities in a forced choice conjoint, we maximize the utility of a reference candidate averaging over features of the opponent. In the second, the optimal policy selection is performed in an adversarial manner in two rounds of selection---we maximize the support of a reference candidate against an opponent group which is also maximizing the support of their candidate in the same target population. We discuss several point estimate and variance-covariance estimators, some of which are obtained in closed form. Finite sample performance is explored via simulation. Our empirical analysis shows the usefulness of the proposed methodologies in the context of the US vote choice for president.
Share
Other Events in This Series
Feb
17
2023
Seminar Series - Dr. Yen-Chi Chen
Pattern Graphs: a Graphical Approach to Nonmonotone Missing Data
2:00 pm — 3:00 pm •Virtual
Speaker(s): Yen-Chi Chen
Feb
24
2023
Seminar Series - Dr. Antik Chakraborty
Bayesian inference on high-dimensional multivariate binary responses
2:00 pm — 3:00 pm •Virtual
Speaker(s): Antik Chakraborty
Mar
10
2023
Seminar Series - Dr. Baharan Mirzasoleiman
The Department for Statistics and Data Sciences at UT Austin presents its Spring 23 Seminar Series with speaker Dr. Baharan Mirzasoleiman.
2:00 pm — 3:00 pm •Virtual
Speaker(s): Baharan Mirzasoleiman
Mar
24
2023
Seminar Series - Dr. Lindsay Berry
The Department for Statistics and Data Sciences at UT Austin presents its Spring 23 Seminar Series with speaker Dr. Lindsay Berry
2:00 pm — 3:00 pm •In Person & Virtual
Speaker(s): Lindsay Berry
Mar
31
2023
Seminar Series - Dr. Mevin Hooten
Running on Empty: Recharge Dynamics from Animal Movement Data
2:00 pm — 3:00 pm •In Person & Virtual
Speaker(s): Mevin Hooten
Apr
7
2023
Ph.D. Program Poster Session
Ph.D. Poster Session
3:00 pm — 4:30 pm •In Person
Speaker(s): PhD Students
Apr
14
2023
Seminar Series - Dr. Eric Vance
Teaching Collaboration in Statistics and Data Science
2:00 pm — 3:00 pm •In Person & Virtual
Speaker(s): Eric Vance
Apr
21
2023
Seminar Series - Dr. Faming Liang
A Stochastic Neural Network Bridging from Linear Models to Deep Learning
2:00 pm — 3:00 pm •Virtual & In Person
Speaker(s): Faming Liang
May
5
2023
CANCELED: Seminar Series - Dr. Ana-Maria Staicu
Spatial functional principal component analysis
2:00 pm — 3:00 pm •In Person & Virtual
Speaker(s): Ana-Maria Staicu