Presentations

Ingmar Weber presents, "Tapping Into Public Advertising Data to Monitor Migration, Gender Gaps, Poverty and, Maybe, Censorship", at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, March 6, 2019

Abstract: Facebook, LinkedIn and other social networks provide advertisers with “audience estimates” on how many of their users match certain targeting criteria. These estimates are usually used for budget planning and include targeting criteria such as (i) countries a user has lived in, (ii) their gender, and (iii) the type of mobile device they use. In this talk I report on how we work with UN agencies and other partners to use this type of information to monitoring international migration, track digital gender gaps and map poverty. I’ll also discuss some observations...

Read more about Ingmar Weber presents, "Tapping Into Public Advertising Data to Monitor Migration, Gender Gaps, Poverty and, Maybe, Censorship"
Roland Neil presents "Testing for Racial and Ethnic Discrimination in Police Stops", at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, February 27, 2019

Abstract: Whether police discriminate on the basis of race and ethnicity when making stops is a topic of frequent debate among academics, in courts, and beyond. However, due to implausible assumptions about police behavior, the most commonly used tests are quite susceptible to indicating discrimination when it is not present or to indicating a lack of discrimination when it is present. This is true of research on the New York Police Department’s (NYPD) practice of Stop, Question, and Frisk (SQF), a particularly contentious case where findings have been mixed. Using data...

Read more about Roland Neil presents "Testing for Racial and Ethnic Discrimination in Police Stops"
Ankur Pandya presents "Modeling the Cost Effectiveness of Two Big League Pay-for-Performance Policies", at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, February 20, 2019

Abstract: To date, evidence on pay-for-performance has been mixed. When pay-for-performance policies improve health outcomes, researchers should evaluate whether these health gains are worth the incremental costs (financial incentives and increased utilization) needed to achieve them. We used simulation modeling to evaluate the cost-effectiveness of two pay-for-performance policies that were recently evaluated in major journals: 1) a randomized controlled trial of financial incentives on patients, physicians, or both for cholesterol control (Asch et al. JAMA 2015...

Read more about Ankur Pandya presents "Modeling the Cost Effectiveness of Two Big League Pay-for-Performance Policies"
Ilya Shpitser presents "Fair Inference on Outcomes", at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, February 13, 2019

Abstract: Systematic discriminatory biases present in our society influence the way data is collected and stored, the way variables are defined, and the way scientific findings are put into practice as policy. Automated decision procedures and learning algorithms applied to such data may serve to perpetuate existing injustice or unfairness in our society.  We consider how to solve prediction and policy learning problems in a way which ``breaks the cycle of injustice'' by correcting for the unfair dependence of outcomes, decisions, or both, on sensitive features (e.g...

Read more about Ilya Shpitser presents "Fair Inference on Outcomes"
Maya Mathur presents "Sensitivity analysis for publication bias and selective reporting in meta-analysis" , at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, February 6, 2019
Abstract: We propose sensitivity analyses for selection in meta-analysis due to publication bias, selective reporting, and "p-hacking". We consider a publication process such that "statistically significant'' positive results are more likely to be published than negative or "nonsignificant'' results by an unknown ratio. Using inverse-probability weighting and robust estimation that accommodates non-normal true effects, small meta-analyses, and clustering, we develop... Read more about Maya Mathur presents "Sensitivity analysis for publication bias and selective reporting in meta-analysis"
Drew Dimmery presents "Permutation Weighting", at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, January 30, 2019

Abstract: This work introduces permutation weighting: a weighting estimator for observational causal inference under general treatment regimes which preserves arbitrary measures of covariate balance. We show that estimating weights which obey balance constraints is equivalent to a simple two-class classification problem between the observed data and a permuted dataset (no matter the cardinality of treatment). Arbitrary probabilistic classifiers may be used in this method; the hypothesis space of the classifier corresponds to the nature...

Read more about Drew Dimmery presents "Permutation Weighting"
Johann Gagnon-Bartsch presents "The Duality of Negative Controls and Replicates", at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, December 5, 2018
Abstract: Negative controls can be used to adjust for unobserved confounders in an observational study.  A negative control is a variable that is known a priori to be (1) unaffected by treatment, and (2) affected by the unobserved confounders.  Any observed variation in a negative control may be attributed to the confounders, but not to treatment.  Thus, negative controls can be used to partially identify the unobserved confounders.  A similar situation arises when a single observational unit is observed multiple...
Read more about Johann Gagnon-Bartsch presents "The Duality of Negative Controls and Replicates"
Tracy Ke presents "Statistical Analysis of Large Social Networks", at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, November 28, 2018

Abstract: Severe degree heterogeneity is a universal phenomenon in large social networks. However, the degree parameters are largely nuisance to our major interest, and their effects can be carefully removed with proper statistical strategies. In the first part of the talk, I will take the mixed-membership estimation as an example and present several useful ideas for dealing with degree heterogeneity.   We assume the network has K perceivable communities. Each node is associated with a K-dimensional “membership” vector whose...

Read more about Tracy Ke presents "Statistical Analysis of Large Social Networks"
Matthew Blackwell presents "Telescope Matching: A Flexible Approach to Estimating Direct Effects" , at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, November 14, 2018
Abstract: Estimating the direct effect of a treatment fixing the value of a consequence of that treatment is becoming a common part of social science research. In many cases, however, these effects are difficult to estimate standard methods since they can induce post-treatment bias. More complicated methods like marginal structural models or structural nested mean models can recover direct effects in these situations but require parametric models for the outcome or the post-treatment covariates. In this paper, we propose an alternative approach, which we call telescope... Read more about Matthew Blackwell presents "Telescope Matching: A Flexible Approach to Estimating Direct Effects"
Zhichao Jiang presents "Causal Inference with Interference and Noncompliance in Two-Stage Randomized Experiments" , at CGIS Knafel Building (K354) - 12-1:30 pm, Wednesday, November 7, 2018

Abstract: In many social science experiments, subjects often interact with each other and as a result one unit's treatment influences the outcome of another unit. Over the last decade, a significant progress has been made towards causal inference in the presence of such interference between units. However, much of the literature has assumed perfect compliance with treatment assignment. In this paper, we establish the nonparametric identification of the complier average direct and spillover effects in two-stage randomized experiments with interference and noncompliance....

Read more about Zhichao Jiang presents "Causal Inference with Interference and Noncompliance in Two-Stage Randomized Experiments"

Pages