Daniel Lee June 23, 2015 10:00 AM-12:00 PM 4240 Public Affairs Building Stan is an open-source, Bayesian inference tool with interfaces in R, Python, Matlab, Julia, Stata, and the command […]
"Inferring and understanding travel and migration movements at a global scale"
Abstract: Despite extensive work on the dynamics and outcomes of large-scale migrations, timely and accurate estimates of population movements do not exist. While censuses, surveys, and observational data have been used to measure migration, estimates based on these data sources are constrained in their inability to detect unfolding migrations, and lack temporal and demographic detail. In this study, we present a novel approach for generating estimates of migration that can measure movements of particular demographic groups across country lines.
Specifically, we model migration as a function of long-term moves across countries using aggregated Facebook data. We demonstrate that this methodological approach can be used to produce accurate measures of past and ongoing migrations - both short-term patterns and long-term changes in residence. Several case studies confirm the validity of our approach, and highlight the tremendous potential of information obtained from online platforms to enable novel research on human migration events.
Presented By: Mark S. Handcock (Professor, Statistics) Jeffrey B. Lewis (Professor, Political Science) Marc A. Suchard (Professor, Biomathematics, Biostatistics and Human Genetics) Reproducibility is one of the main principles […]
"Electronic Homestyle: Tweeting Ideology"
Abstract: Ideal points are central to the study of political partisanship and an essential component to our understanding of legislative and electoral behavior. We employ automated text analysis on tweets from Members of Congress to estimate their ideal points using Naive Bayes classification and Support Vector Machine classification. We extend these tools to estimate the proportion of partisan speech used in each legislator's tweets. We demonstrate an association between these measurements, existing ideal point measurements, and district ideology.
"Quantifying the dynamics of multimodal communication with multimodal data."
*Presented by the Center for Social Statistics
Abstract: Human communication is built upon an array of signals, from body movement to word selection. The sciences of language and communication tend to study these signals individually. However, natural human communication uses all these signals together simultaneously, and in complex social systems of various sizes. It is an open puzzle to uncover how this multimodal communication is structured in time and organized at different scales. Such a puzzle includes analysis of two-person interactions. It also involves an understanding of much larger systems, such as communication over social media at an unprecedentedly massive scale.
Collaborators and I have explored communication across both of these scales, and I will describe examples in the domain of conflict. For example, we've studied conflict communication in two-person interactions using video analysis of body and voice dynamics. At the broader scale, we have also used large-scale social media behavior (Twitter) during a massively shared experience of conflict, the 2012 Presidential Debates. These projects reveal the importance of dynamics. In two-person conflict, for example, signal dynamics (e.g., body, voice) during interaction can reveal the quality of that interaction. In addition, collective behavior on Twitter can be predicted even by simple linear models using debate dynamics between Obama and Romney (e.g., one interrupting the other).
The collection, quantification, and modeling of multitemporal and multivariate datasets hold much promise for new kinds of interdisciplinary collaborations. I will end by discussing how they may guide new theoretical directions for pursuing the organization and temporal structure of multimodality in communication.
"Innovative Sampling Approaches for Hard to Reach Populations: Design of a National Probability Study of Lesbians, Gay Men, Bisexuals, and Transgender Peoples and Network Sampling of Hard to Reach Populations"
Ilan H. Meyer, Williams Distinguished Senior Scholar for Public Policy at the Williams Institute
Mark S. Handcock, Professor of Statistics at UCLA and Director of the Center for Social Statistics
Come for the exciting seminar then stay for the free lunch and discussion. A seminar led by Ilan H. Meyer followed immediately by a Brown Bag Lunch led by Mark S. Handcock.
Dr. Meyer is Principal Investigator of the Generations and TransPop Surveys. Generations is a survey of a nationally representative sample of 3 generations of lesbians, gay men, and bisexuals. TransPop is the first national probability sample survey of transgender individuals in the United States. Both studies attempt to obtain large nationally representative samples of hard to reach populations. Dr. Meyer will review sampling issues with LGBT populations and speak on the importance of measuring population health of LGBTs and the underlying aspects in designing a national probability survey.
From a contrasting perspective, the field of Survey Methodology is facing many challenges. The general trend of declining response rates is making it harder for survey researchers to reach their intended population of interest using classical survey sampling methods.
In the followup Brown Bag Lunch, led by Mark S. Handcock, participants will discuss statistical challenges and approaches to sampling hard to reach populations. Transgenders, for example, are a rare and stigmatized population. If the transgender community exhibits networked social behavior, then network sampling methods may be useful approaches that compliment classical survey methods.
Participants are encouraged to speak on ideas of statistical methods for surveys.
The tenth annual West Coast Experiments Conference will be held at UCLA on Monday, April 24 and Tuesday, April 25, 2017, preceded by in-depth methods training workshops on Sunday, April 23. The conference […]
The Center for Social Statistics Presents: Predicting the Evolution of Intrastate Conflict: Evidence from Nigeria url: http://css.stat.ucla.edu/event/shahryar-minhas/ The endogenous nature of civil conflict has limited scholars' abilities to draw clear inferences […]
“Fragile Families Challenge: Getting Started Workshop” Ian Lundberg Ph.D. Student, Sociology and Social Policy, Princeton University The Fragile Families Challenge is a scientific mass collaboration that combines predictive modeling, causal inference, and […]
The UCLA Departments of Epidemiology, Biostatistics, Statistics and the Center for Social Statistics presents: Causal Methods in Epidemiology: Where has it got us and what can we expect in the […]
The UCLA Department of Statistics and the Center for Social Statistics presents: Redefine Statistical Significance Daniel Benjamin will discuss his paper (written by him and 71 other authors), “Redefine Statistical […]
The UCLA Department of Statistics and the Center for Social Statistics presents: Statistical Significance and Discussion of the Challenges of Avoiding the Abuse of Statistical Methodology Sander Greenland will offer […]
The UCLA Department of Statistics and the Center for Social Statistics presents: Programming data science with R & the tidyverse Tidy evaluation is a new framework for non-standard evaluation that […]
Abstract: Traditional approaches to public health concerns have conferred great advances in the duration and quality of life. Public health interventions – from improved sanitation efforts, to vaccination campaigns, to […]
"When Should Researchers Use Inferential Statistics When Analyzing Data on Full Populations?"
Abstract: Many researchers uncritically use inferential statistical procedures (e.g., hypothesis tests) when analyzing complete population data—a situation in which inference may seem unnecessary. We begin by reviewing and analyzing the most common rationales for employing inferential procedures when analyzing full population data. Two common rationales—having to do with handling missing data and generalizing results to other times and/or places—either lack merit or amount to analyzing sample (not population) data. Whether it is appropriate to use inferential procedures depends on whether researchers are analyzing sample or population data and on whether they seek to make causal or descriptive claims. When doing descriptive research, the distinction between sample and population data is paramount: Inferential statistics should only be used to analyze sample data (to account for sampling variability) and never to analyze population data. When doing causal research, the distinction between sample data and population data is unimportant: Inferential procedures can and should always be used to distinguish (for example) robust associations from those that may have come about by chance alone. Crucially, using inferential procedures to analyze population data to make descriptive claims can lead to incorrect substantive conclusions—especially when population sizes and/or effect sizes are small.
The UCLA Department of Statistics and the Center for Social Statistics presents: Modelling Mobility Tables as Weighted Networks Contemporary research on occupational mobility, i.e. how people move between jobs, tends […]
"Heterogeneous Causal Effects: A Propensity Score Approach "
Abstract: Heterogeneity is ubiquitous in social science. Individuals differ not only in background characteristics, but also in how they respond to a particular treatment. In this presentation, Yu Xie argues that a useful approach to studying heterogeneous causal effects is through the use of the propensity score. He demonstrates the use of the propensity score approach in three scenarios: when ignorability is true, when treatment is randomly assigned, and when ignorability is not true but there are valid instrumental variables.
"Rules of Engagement in Evidence-Informed Policy: Practices and Norms of Statistical Science in Government"
Abstract: Collaboration between statistical scientists (data scientists, behavioral and social scientists, statisticians) and policy makers promises to improve government and the lives of the public. And the data and design challenges arising from governments offer academics new chances to improve our understanding of both extant methods and behavioral and social science theory. However, the practices that ensure the integrity of statistical work in the academy — such as transparent sharing of data and code — do not translate neatly or directly into work with governmental data and for policy ends. This paper proposes a set of practices and norms that academics and practitioners can agree on before launching a partnership so that science can advance and the public can be protected while policy can be improved. This work is at an early stage. The aim is a checklist or statement of principles or memo of understanding that can be a template for the wide variety of ways that statistical scientists collaborate with governmental actors.
Covariate Selection for Generalizing Experimental Results
Researchers are often interested in generalizing the average treatment effect (ATE) estimated in a randomized experiment to non-experimental target populations. Researchers can estimate the population ATE without bias if they adjust for a set of variables affecting both selection into the experiment and treatment heterogeneity.Although this separating set has simple mathematical representation, it is often unclear how to select this set in applied contexts. In this paper, we propose a data-driven method to estimate a separating set. Our approach has two advantages. First, our algorithm relies only on the experimental data. As long as researchers can collect a rich set of covariates on experimental samples, the proposed method can inform which variables they should adjust for. Second, we can incorporate researcher-specific data constraints. When researchers know certain variables are unmeasurable in the target population, our method can select a separating set subject to such constraints, if one is feasible. We validate our proposed method using simulations, including naturalistic simulations based on real-world data.
Co-Sponsored with The Center for Social Statistics
Bayesian Population Projections with Migration Uncertainty
The United Nations recently issued official probabilistic population projections for all countries for the first time, using a Bayesian hierarchical modeling framework developed by our group at the University of Washington. These take account of uncertainty about future fertility and mortality, but not international migration. We propose a Bayesian hierarchical autoregressive model for obtaining joint probabilistic projections of migration rates for all countries, broken down by age and sex. Joint trajectories for all countries are constrained to satisfy the requirement of zero global net migration. We evaluate our model using out-of-sample validation and compare point projections to the projected migration rates from a persistence model similar to the UN's current method for projecting migration, and also to a state of the art gravity model. We also resolve an apparently paradoxical discrepancy between growth trends in the proportion of the world population migrating and the average absolute migration rate across countries. This is joint work with Jonathan Azose and Hana Ševčíková.
Co-sponsored with the Center for Social Statistics
Internal vs. external validity in studies with incomplete populations
Researchers working with administrative data rarely have access to the entire universe of units they need to estimate effects and make statistical inferences. Examples are varied and come from different disciplines. In social program evaluation, it is common to have data on all households who received the program, but only partial information on the universe of households who applied or could have applied for the program. In studies of voter turnout, information on the total number of citizens who voted is usually complete, but data on the total number of voting-eligible citizens is unavailable at low levels of aggregation. In criminology, information on arrests by race is available, but the overall population that could have potentially been arrested is typically unavailable. And in studies of drug overdose deaths, we lack complete information about the full population of drug users.
In all these cases, a reasonable strategy is to study treatment effects and descriptive statistics using the information that is available. This strategy may lack the generality of a full-population study, but may nonetheless yield valuable information for the included units if it has sufficient internal validity. However, the distinction between internal and external validity is complex when the subpopulation of units for which information is available is not defined according to a reproducible criterion and/or when this subpopulation itself is defined by the treatment of interest. When this happens, a useful approach is to consider the full range of conclusions that would be obtained under different possible scenarios regarding the missing information. I discuss a general strategy based on partial identification ideas that may be helpful to assess sensitivity of the partial-population study under weak (non-parametric) assumptions, when information about the outcome variable is known with certainty for a subset of the units. I discuss extensions such as the inclusion of covariates in the estimation model and different strategies for statistical inference.
Co-sponsored with the Political Science Department, Statistics Department and the Center for Social Statistics
Matching Methods for Causal Inference with Time-Series Cross-Section Data
Matching methods aim to improve the validity of causal inference in observational studies by reducing model dependence and offering intuitive diagnostics. While they have become a part of standard tool kit for empirical researchers across disciplines, matching methods are rarely used when analyzing time-series cross-section (TSCS) data, which consist of a relatively large number of repeated measurements on the same units.
We develop a methodological framework that enables the application of matching methods to TSCS data. In the proposed approach, we first match each treated observation with control observations from other units in the same time period that have an identical treatment history up to the pre-specified number of lags. We use standard matching and weighting methods to further refine this matched set so that the treated observation has outcome and covariate histories similar to those of its matched control observations. Assessing the quality of matches is done by examining covariate balance. After the refinement, we estimate both short-term and long-term average treatment effects using the difference-in-differences estimator, accounting for a time trend. We also show that the proposed matching estimator can be written as a weighted linear regression estimator with unit and time fixed effects, providing model-based standard errors. We illustrate the proposed methodology by estimating the causal effects of democracy on economic growth, as well as the impact of inter-state war on inheritance tax. The open-source software is available for implementing the proposed matching methods.
Co-sponsored with the Political Science Department, Statistics Department and the Center for Social Statistics
Instructor: Michael Tzen Title: Merging Entities: Deterministic, Approximate, & Probabilistic Location: January 31, 2019, 2:00-3:00 PM 4240 Public Affairs Building CCPR Seminar Room Content: Combining information from different groups is […]
Covariate screening in high dimensional data: applications to forecasting and text data
High dimensional (HD) data, where the number of covariates and/or meaningful covariate interactions might exceed the number of observations, is increasing used in prediction in the social sciences. An important question for the researcher is how to select the most predictive covariates among all the available covariates. Common covariate selection approaches use ad hoc rules to remove noise covariates, or select covariates through the criterion of statistical significance or by using machine learning techniques. These can suffer from lack of objectivity, choosing some but not all predictive covariates, and failing reasonable standards of consistency that are expected to hold in most high-dimensional social science data. The literature is scarce in statistics that can be used to directly evaluate covariate predictivity. We address these issues by proposing a variable screening step prior to traditional statistical modeling, in which we screen covariates for their predictivity. We propose the influence (I) statistic to evaluate covariates in the screening stage, showing that the statistic is directly related to predictivity and can help screen out noisy covariates and discover meaningful covariate interactions. We illustrate how our screening approach can removing noisy phrases from U.S. Congressional speeches and rank important ones to measure partisanship. We also show improvements to out-of-sample forecasting in a state failure application. Our approach is applicable via an open-source software package.
Title: Grad Student Panel Discussing the Causal Toolkit Location: February 27, 2019, 2:00-3:30 PM 4240 Public Affairs Building CCPR Seminar Room Content: Focusing on the uses of the causal toolkit, […]
Lan Liu, University of Minnesota at Twin Cities "Parsimonious Regressions for Repeated Measure Analysis" Abstract: Longitudinal data with repeated measures frequently arises in various disciplines. The standard methods typically impose […]
Eloise Kaizar, Ohio State University Randomized controlled trials are often thought to provide definitive evidence on the magnitude of treatment effects. But because treatment modifiers may have a different distribution […]
Estimating Heterogeneous Treatment Effects and Optimal Treatment Assignment Policies
This talk will review recently developed methods for estimating conditional average treatment effects and optimal treatment assignment policies in experimental and observational studies, including settings with unconfoundedness or instrumental variables. Multi-armed bandits for learning treatment assignment policies will also be considered.
Co-sponsored with the Center for Social Statistics
How to Make Causal Inferences Using Texts
Texts are increasingly used to make causal inferences: either with the document serving as the treatment or the outcome. We introduce a new conceptual framework to understand all text-based causal inferences, demonstrate fundamental problems that arise when using manual or computational approaches applied to text for causal inference, and provide solutions to the problems we raise. We demonstrate that all text-based causal inferences depend upon a latent representation of the text and we provide a framework to learn the latent representation. Estimating this latent representation, however, creates new risks: we may unintentionally create a dependency across observations or create opportunities to fish for large effects. To address these risks, we introduce a train/test split framework and apply it to estimate causal effects from an experiment on immigration attitudes and a study on bureaucratic responsiveness. Our work provides a rigorous foundation for text-based causal inferences, connecting two previously disparate literatures. (Joint Work with Egami, Fong, Grimmer and Roberts)
Co-sponsored with the Center for Social Statistics
Title: Getting All Your Research Computing Tools for Summer and Beyond - Hardware and Software Location: May 22, 2019 @ 12:00-1:30 PM 4240 Public Affairs Building CCPR Seminar Room Instructors: […]
Title: Getting The Data Yourself: A Web Scraping Code Through Location: May 29, 2019 @ 12:00-1:30 PM 4240 Public Affairs Building CCPR Seminar Room Instructors: Chad Pickering & Mike Tzen […]
Summer Institute in Computational Social Science Panel Presentation
Friday June 21, 2019 2:00pm – 5:00pm
Reception 5:00pm – 6:00pm
Luskin Conference Center Laureate Room
• 2:00pm – 3:15pm Digital Demography
Prof. Dennis Feehan, UC Berkeley and Prof. Ka-Yuet Liu, UCLA
• 3:30pm – 4:45pm Computational Causal Inference
Prof. Judea Pearl, UCLA and Prof. Sam Pimentel, UC Berkeley