Nominate a speaker »
**Seminars will be held In Person unless otherwise noted**
Spring 2024
Seminar One-Cancelled
Thursday, March 21, 2024, 4:00pm to 5:00pm
Griffin-Floyd Hall, Room 100
Peng Ding
UC-Berkeley
Title:
Causal inference in network experiments: regression-based analysis and
design-based properties.
Abstract:
Investigating interference or spillover effects among units is a central
task in many social science problems. Network experiments are powerful tools for this task, which avoids endogeneity by randomly assigning treatments to units over networks. However, it is non-trivial to analyze network experiments properly without imposing strong modeling assumptions. Previously, many researchers have proposed sophisticated point estimators and standard errors for causal effects under network experiments. We show that regression-based point estimators and standard errors can have strong theoretical guarantees if the regression functions and robust standard errors are carefully specified to accommodate the interference patterns under network experiments. We demonstrate that the regression-based approach offers three notable advantages: its ease of implementation, the ability to derive standard errors through the same weighted-least-squares fit, and the capacity to integrate covariates into the analysis, thereby enhancing estimation efficiency. Furthermore, we analyze the asymptotic bias of the regression-based network-robust standard errors. Since covariance estimators can be anti-conservative, we propose an adjusted
covariance estimator to improve the empirical coverage rates.
Seminar Two
Thursday, March 28, 2024, 4:00pm to 5:00pm
Griffin-Floyd Hall, Room 100
Edward Kennedy
Carnegie Mellon University
Title:
Doubly robust capture-recapture methods for estimating population size.
Abstract:
Estimation of population size using incomplete lists has a long history across many biological and social sciences. For example, human rights groups often construct partial lists of victims of armed conflicts, to estimate the total number of victims. Earlier statistical methods for this setup often use parametric assumptions, or rely on suboptimal plug-in-type nonparametric estimators; but both approaches can lead to substantial bias, the former via model misspecification and the latter via smoothing. Under an identifying assumption that two lists are conditionally independent given measured covariates, we make several contributions. First, we derive the nonparametric efficiency bound for estimating the capture probability, which indicates the best possible performance of any estimator, and sheds light on the statistical limits of capture-recapture methods. Then we present a new estimator, that has a double robustness property new to capture-recapture, and is near-optimal in a nonasymptotic sense, under relatively mild nonparametric conditions. Next, we give a confidence interval construction method for total population size from generic capture probability estimators, and prove nonasymptotic near-validity. Finally, we apply them to estimate the number of killings and disappearances in Peru during its internal armed conflict between 1980 and 2000.
Seminar Three
Thursday, April 4, 2024 4:00pm to 5:00pm
Griffin-Floyd Hall, Room 100
Masayo Hirose
Kyushu University
Title:
A Poverty Mapping based on Arc-sin Transformed Area Level Model
Abstract:
There is a high demand for poverty mapping to understand the present poverty-related situation. In Japan, a poverty-related social problem has been increasing attention, especially for a decade. To address such a big issue, making a reliable document to understand some poverty situations for small domains may be essential. In this study, we map the poverty rate of a small demographic domain for each prefecture, which was constructed using official Japanese microdata. To analyze such data, we also modified the Hirose, Ghosh, and Ghosh (2023) method to take care of a complex sampling design. And I will suggest a simple confidence interval for this purpose. This is joint work with Dr. Mayumi Oka at the Institute of Statistical Mathematics.
Seminar Four
Thursday, April 9, 2024, 4:00pm to 5:00pm
Griffin-Floyd Hall, Room 100
Jose Ramon Zubizarreta
Harvard University
Title:
Anatomy of Two-Way Fixed Effects Models: Hypothetical Experiment, Exact Decomposition, and Robust Estimation
Abstract:
In recent decades, event studies have emerged as a central methodology in the health and social sciences for evaluating the causal effects of discrete interventions. In this talk, we will provide a novel characterization of the classical dynamic two-way fixed effects (TWFE) regression estimator for event studies. The decomposition is expressed in closed-form and reveals, in finite samples and without approximations, the hypothetical experiment that TWFE regression adjustments approximate. This decomposition offers insights into how standard regression estimators use information from various units and time points, generalizing the notion of forbidden comparison noted in the literature in simpler settings. We will introduce a robust weighting approach for estimation in event studies, which allows investigators to progressively build larger valid weighted contrasts by leveraging, in a sequential manner, increasingly stronger assumptions on the potential outcomes and the assignment mechanism. We will provide visualization tools, and illustrate these methods in a case study of the impact of divorce reforms on female suicide.
Seminar Five
Thursday, April 23, 2024, 4:00pm to 5:00pm
Griffin-Floyd Hall, Room 100
Jason Roy
Rutgers University
Title:
TBD
Abstract:
TBD