Bayesian regression tree models for causal inference: regularization, confounding and heterogeneity

Size: px
Start display at page:

Download "Bayesian regression tree models for causal inference: regularization, confounding and heterogeneity"

Transcription

1 Bayesian regression tree models for causal inference: regularization, confounding and heterogeneity P. Richard Hahn, Jared Murray, and Carlos Carvalho June 22, 2017

2 The problem setting We want to estimate treatment effects using a regression model, assuming: observational data (not from experiments), conditional unconfoundedness (we ve measured everything we need to), covariate-dependent treatment effects (people can have different responses to treatment according to their covariates) binary treatment variable (you either got the drug or you didn t) 1

3 More formally We assume strong ignorability: Y (0), Y (1) Z X, 0 < Pr(Z i = 1 x i ) < 1 for all i. Therefore E(Y i (1) x i ) = E(Y i x i, Z i = 1), E(Y i (0) x i ) = E(Y i x i, Z i = 0) and the treatment effect is α(x i ) := E(Y i x i, Z i = 1) E(Y i x i, Z i = 0). 2

4 Additive, homoskedastic errors Here we consider mean-zero, additive error representations Y i = f (x i, z i ) + ɛ i, so that E(Y i x i, z i ) = f (x i, z i ). The treatment effect of setting z i = 1 versus z i = 0 is expressed as α(x i ) := f (x i, 1) f (x i, 0). nb: In this context, conditional ignorability is often expressed as ɛ i Z i x i. 3

5 Regression trees no x 1 < c Tree T h yes g(x, T h, M h ) µ h2 µ h1 x 3 < d no yes x 3 d µ h3 µ h1 µ h2 µ h3 x 1 c Leaf/End node parameters M h = (µ h1, µ h2, µ h3 ) Partition A h = {A h1, A h2, A h3 } g(x, T h, M h ) = µ ht if x A ht (for 1 t b h ). 4

6 Bayesian Additive Regression Trees (BART) Bayesian additive regression trees (BART) (Chipman, George and McCulloch, 2010): y i = f (x i ) + ɛ i, ɛ i N(0, σ 2 ) m f (x) = g(x, T h, M h ) h=1 g are basis functions determined by a binary tree T h and vector of parameters M h. Hill (2012) specifically proposes BART for causal inference: in several simulation studies it works really, really well. 5

7 Improving BART for causal inference BART is excellent for causal inference, but it exhibits undesirable behavior in certain situations. 1. In cases with strong confounding estimates of the average treatment effect from BART exhibit severe bias. 2. Effect estimates from synthetic data with known homogeneous effect produce individual effect estimates that are over-dispersed. Our goal is to develop a modified BART model that improves these two weaknesses. 6

8 Example of problem one Consider a problem with p = 2, n = 1, 000, with homogeneous effects. True treatment effect is α = 1. Y i = µ i + Z i + ɛ i, µ i = 1(x i1 < x i2 ) 1(x i1 x i2 ) P(Z i = 1 x i1, x i2 ) = Φ(µ i ), ɛ i iid N(0, ), x i1, x i2 iid N(0, 1). Y : measure of heart distress, Z: took heart medication, x 1 and x 2 are blood pressure measurements. This example demonstrates targeted treatment: patients with x i1 < x i2 are 5 times as likely to receive the new drug precisely because they are more likely to have higher levels of heart distress. 7

9 BART shows substantial bias BART (white) exhibits substantial bias. Density Treatment effect Figure 1: BART (white) misses the truth, by a lot, across 250 simulations. (I will explain the blue and pink in a moment.) 8

10 Regularization induced confounding Why is BART biased in this example? µ(x) needs many axis-aligned splits to be approximated by trees. the response surface can be parsimoniously approximated with just one axis-aligned split in the treatment variable and an over-stated treatment effect. therefore, priors over f that penalize the total number of splits tend to over-attribute changes in E(Y x, Z) to a treatment effect. 9

11 Regularization induced confounding x x 1 Figure 2: It takes many axis-aligned splits for a tree to fit a steep response gradient along a diagonal. Our example response surface was 1 above the diagonal and 1 below it. 10

12 The fix: ps-bart We can fix this by estimating π(x) = P(Z = 1 x) (using BART) and then using ˆπ(x) as an extra predictor variable in a BART model for the response surface. Table 1: The BART prior exhibits substantial bias in estimating the treatment effect. Modified BART priors allowing splits in either the true propensity score (Oracle BART) or an estimated propensity score (ps-bart) perform markedly better. Prior Bias Coverage RMSE BART % 0.15 Oracle BART % 0.05 ps-bart %

13 R.I.C. in linear regression Consider the response model Y i = β 0 + αz i + β t x i + ε i, Z i = γ t x i + ν i. For a flat prior on α and a ridge prior on β the bias is bias(ˆα rr ) = ( (Z t Z) 1 Z t X ) (I p + X t (X ˆX Z )) 1 β. For Ẑi γ t x i, Z = (Z, Ẑ) gives bias bias(ˆα rr ) = { ( Z t Z) 1 Z t X } 1 (I p + X t (X ˆX Z )) 1 β 0. 12

14 Example of problem two ps-bart fixes the severe bias under strong confounding, but offers no direct control on the prior for treatment effects. Individual effect estimates are quite variable: stronger regularization would likely improve average estimation error, but how to impose it? Frequency ITE Figure 3: ps-bart (in pink) gives widely variable individual treatment effect estimates, even when the true effect is homogeneous (here it is α = 0.25).This is a single data set with 250 individuals. Our new approach is shown in gray. 13

15 The fix: Bayesian causal forests In order to regularize treatment effects directly, our new model is f (x i, z i ) = m(x i, ˆπ(x i )) + α(x i, ˆπ(x i ))z i, where m and α are given independent BART priors. Now the treatment effect is E(Y i x i, Z i = 1) E(Y i x i, Z i = 0) = {m(x i, ˆπ)+α(x i, ˆπ)} m(x i, ˆπ) = α(x i, ˆπ), and we can shrink towards homogeneity with stronger regression on α than m. In fact, we can directly set the prior probability of homogeneity. Even setting it to 1% corresponds to much more aggressive regularization than the default BART prior. 14

16 Heterogeneous effect example Consider the previous data generating process but let the treatment effect varies depending on an observable covariate x 3 N(0, 1): α i = 1(x i3 > 1/4) (x i3 > 1/2) (x i3 > 3/4), so α i {0, 1, 1.25, 1.5} according to the level of x i3. We consider a smaller sample size here, n = 250. Table 2: BART vs ps-bart vs BCF on RMSE on the heterogeneous effect vector α(x) over 250 replicates. Prior coverage of ATE ave. RMSE ATE ave. RMSE ITE BART 3% ps-bart 96% BCF 94%

17 Notable related approaches van der Laan, M. J. (2010). Targeted maximum likelihood based causal inference. The International Journal of Biostatistics. McCaffrey, D. F., Griffin, B. A., Almirall, D., Slaughter, M. E., Ramchand, R. and Burgette, L. F. (2013). A tutorial on propensity score estimation for multiple treatments using generalized boosted models. Statistics in Medicine. Zigler, C. M. and Dominici, F. (2014). Uncertainty in propensity score estimation: Bayesian methods for variable selection and model-averaged causal effects. Journal of the American Statistical Association. Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C. et al. (2016). Double machine learning for treatment and causal parameters. Wager, S. and Athey, S. (2017). Estimation and Inference of Heterogeneous Treatment Effects using Gradient Forests. 16

18 2017 ACIC Data Analysis Challenge Treatment-response pairs were simulated according to 32 distinct data generating processes (DGPs), given fixed covariates (n = 4, 302, p = 58) from an empirical study. We varied three parameters among two levels High or Low noise level, Strong or Weak confounding, Small or Large effect size. The error distributions were one of four types Additive, homoskedastic, independent, Nonadditive, homoskedastic, independent, Additive, heteroskedastic, independent. To assess coverage, 250 replicate data sets were generated for each DGP. 17

19 Results: Inference for ATE on homoskedastic DGPs 18

20 Results: Estimation for ATE on homoskedastic DGPs 19

21 Results: Inference for ITE on homoskedastic DGPs 20

22 Results: Inference for ATE on easy DGPs 21

23 Results: Estimation for ATE on easy DGPs 22

24 Results: Inference for ITE on easy DGPs 23

25 Results: Inference for ATE on difficult DGPs 24

26 Results: Estimation for ATE on difficult DGPs 25

27 Results: Inference for ITE on difficult DGPs 26

28 Results: Inference for ATE on heteroskedastic DGPs 27

29 Results: Estimation for ATE on heteroskedastic DGPs 28

30 Results: Inference for ITE on heteroskedastic DGPs 29

31 1987 National Medical Expenditure Survey (NMES) What is the effect of smoking on medical expenditures? outcome variable Y is medical expenses (verified, log transformed), treatment variable Z indicates heavy smoking (> 1/2 pack per day), n = 7.7k complete-case analysis for Y > 0, covariates include age: age in years at the time of the survey smoke age: age in years when the individual started smoking gender: male or female race: other, black or white marriage status: married, widowed, divorced, separated, never married education level: college graduate, some college, high school graduate, other census region: geographic location, Northeast, Midwest, South, West poverty status: poor, near poor, low income, middle income, high income seat belt: does patient regularly use a seat belt when in a car 30

32 Prediction and ITE estimates: BART vs. BCF BCF BCF Vanilla BART vanilla BART 31

33 Posterior of ATE Frequency Average Treatment effect 32

34 Treatment effect Subgroup inference Individual 33

35 Subgroup inference CART (applied to the posterior) suggests that less educated (high school graduate), married individuals with a relatively high propensity for smoking (ˆπ(x i ) > 0.63) have a higher treatment effect than everyone else. Density The corresponding subgroup ATE is indeed significant. 34

36 Takeaways BART is an impressive response surface method for causal inference; our new BCF model improves on BART in key respects. Regularization-induced confounding can adversely bias treatment effect estimates. Explicitly modeling selection allows regularization to be imposed robustly and directly on the estimand of interest. Expect an R package soon. The paper is up on my web page check it out! 35

37 Extensions Interesting connections to covariate-dependent g-priors. Incorporating uncertainty in the estimated propensity score? Applications to mediation analysis. Model improvements, including heteroskedasticity and more aggresive shrinkage priors (when many garbage variables are plausible). 36

38 Extensions Interesting connections to covariate-dependent g-priors. Incorporating uncertainty in the estimated propensity score? Applications to mediation analysis. Model improvements, including heteroskedasticity and more aggresive shrinkage priors (when many garbage variables are plausible). Thank you for your time. 37

Bayesian causal forests: dealing with regularization induced confounding and shrinking towards homogeneous effects

Bayesian causal forests: dealing with regularization induced confounding and shrinking towards homogeneous effects Bayesian causal forests: dealing with regularization induced confounding and shrinking towards homogeneous effects P. Richard Hahn, Jared Murray, and Carlos Carvalho July 29, 2018 Regularization induced

More information

Bayesian Causal Forests

Bayesian Causal Forests Bayesian Causal Forests for estimating personalized treatment effects P. Richard Hahn, Jared Murray, and Carlos Carvalho December 8, 2016 Overview We consider observational data, assuming conditional unconfoundedness,

More information

Selective Inference for Effect Modification

Selective Inference for Effect Modification Inference for Modification (Joint work with Dylan Small and Ashkan Ertefaie) Department of Statistics, University of Pennsylvania May 24, ACIC 2017 Manuscript and slides are available at http://www-stat.wharton.upenn.edu/~qyzhao/.

More information

Achieving Optimal Covariate Balance Under General Treatment Regimes

Achieving Optimal Covariate Balance Under General Treatment Regimes Achieving Under General Treatment Regimes Marc Ratkovic Princeton University May 24, 2012 Motivation For many questions of interest in the social sciences, experiments are not possible Possible bias in

More information

Propensity Score Weighting with Multilevel Data

Propensity Score Weighting with Multilevel Data Propensity Score Weighting with Multilevel Data Fan Li Department of Statistical Science Duke University October 25, 2012 Joint work with Alan Zaslavsky and Mary Beth Landrum Introduction In comparative

More information

Variable selection and machine learning methods in causal inference

Variable selection and machine learning methods in causal inference Variable selection and machine learning methods in causal inference Debashis Ghosh Department of Biostatistics and Informatics Colorado School of Public Health Joint work with Yeying Zhu, University of

More information

THE DESIGN (VERSUS THE ANALYSIS) OF EVALUATIONS FROM OBSERVATIONAL STUDIES: PARALLELS WITH THE DESIGN OF RANDOMIZED EXPERIMENTS DONALD B.

THE DESIGN (VERSUS THE ANALYSIS) OF EVALUATIONS FROM OBSERVATIONAL STUDIES: PARALLELS WITH THE DESIGN OF RANDOMIZED EXPERIMENTS DONALD B. THE DESIGN (VERSUS THE ANALYSIS) OF EVALUATIONS FROM OBSERVATIONAL STUDIES: PARALLELS WITH THE DESIGN OF RANDOMIZED EXPERIMENTS DONALD B. RUBIN My perspective on inference for causal effects: In randomized

More information

Potential Outcomes Model (POM)

Potential Outcomes Model (POM) Potential Outcomes Model (POM) Relationship Between Counterfactual States Causality Empirical Strategies in Labor Economics, Angrist Krueger (1999): The most challenging empirical questions in economics

More information

Analysis of propensity score approaches in difference-in-differences designs

Analysis of propensity score approaches in difference-in-differences designs Author: Diego A. Luna Bazaldua Institution: Lynch School of Education, Boston College Contact email: diego.lunabazaldua@bc.edu Conference section: Research methods Analysis of propensity score approaches

More information

Individualized Treatment Effects with Censored Data via Nonparametric Accelerated Failure Time Models

Individualized Treatment Effects with Censored Data via Nonparametric Accelerated Failure Time Models Individualized Treatment Effects with Censored Data via Nonparametric Accelerated Failure Time Models Nicholas C. Henderson Thomas A. Louis Gary Rosner Ravi Varadhan Johns Hopkins University July 31, 2018

More information

DATA-ADAPTIVE VARIABLE SELECTION FOR

DATA-ADAPTIVE VARIABLE SELECTION FOR DATA-ADAPTIVE VARIABLE SELECTION FOR CAUSAL INFERENCE Group Health Research Institute Department of Biostatistics, University of Washington shortreed.s@ghc.org joint work with Ashkan Ertefaie Department

More information

Deductive Derivation and Computerization of Semiparametric Efficient Estimation

Deductive Derivation and Computerization of Semiparametric Efficient Estimation Deductive Derivation and Computerization of Semiparametric Efficient Estimation Constantine Frangakis, Tianchen Qian, Zhenke Wu, and Ivan Diaz Department of Biostatistics Johns Hopkins Bloomberg School

More information

Causal Inference Lecture Notes: Causal Inference with Repeated Measures in Observational Studies

Causal Inference Lecture Notes: Causal Inference with Repeated Measures in Observational Studies Causal Inference Lecture Notes: Causal Inference with Repeated Measures in Observational Studies Kosuke Imai Department of Politics Princeton University November 13, 2013 So far, we have essentially assumed

More information

Propensity scores for repeated treatments: A tutorial for the iptw function in the twang package

Propensity scores for repeated treatments: A tutorial for the iptw function in the twang package Propensity scores for repeated treatments: A tutorial for the iptw function in the twang package Lane Burgette, Beth Ann Griffin and Dan McCaffrey RAND Corporation July, 07 Introduction While standard

More information

Causal Inference with General Treatment Regimes: Generalizing the Propensity Score

Causal Inference with General Treatment Regimes: Generalizing the Propensity Score Causal Inference with General Treatment Regimes: Generalizing the Propensity Score David van Dyk Department of Statistics, University of California, Irvine vandyk@stat.harvard.edu Joint work with Kosuke

More information

Lecture 1 January 18

Lecture 1 January 18 STAT 263/363: Experimental Design Winter 2016/17 Lecture 1 January 18 Lecturer: Art B. Owen Scribe: Julie Zhu Overview Experiments are powerful because you can conclude causality from the results. In most

More information

Covariate Balancing Propensity Score for General Treatment Regimes

Covariate Balancing Propensity Score for General Treatment Regimes Covariate Balancing Propensity Score for General Treatment Regimes Kosuke Imai Princeton University October 14, 2014 Talk at the Department of Psychiatry, Columbia University Joint work with Christian

More information

Combining Non-probability and Probability Survey Samples Through Mass Imputation

Combining Non-probability and Probability Survey Samples Through Mass Imputation Combining Non-probability and Probability Survey Samples Through Mass Imputation Jae-Kwang Kim 1 Iowa State University & KAIST October 27, 2018 1 Joint work with Seho Park, Yilin Chen, and Changbao Wu

More information

Regression with a Single Regressor: Hypothesis Tests and Confidence Intervals

Regression with a Single Regressor: Hypothesis Tests and Confidence Intervals Regression with a Single Regressor: Hypothesis Tests and Confidence Intervals (SW Chapter 5) Outline. The standard error of ˆ. Hypothesis tests concerning β 3. Confidence intervals for β 4. Regression

More information

Propensity Score Analysis with Hierarchical Data

Propensity Score Analysis with Hierarchical Data Propensity Score Analysis with Hierarchical Data Fan Li Alan Zaslavsky Mary Beth Landrum Department of Health Care Policy Harvard Medical School May 19, 2008 Introduction Population-based observational

More information

Econ 2148, fall 2017 Instrumental variables I, origins and binary treatment case

Econ 2148, fall 2017 Instrumental variables I, origins and binary treatment case Econ 2148, fall 2017 Instrumental variables I, origins and binary treatment case Maximilian Kasy Department of Economics, Harvard University 1 / 40 Agenda instrumental variables part I Origins of instrumental

More information

Bootstrapping Sensitivity Analysis

Bootstrapping Sensitivity Analysis Bootstrapping Sensitivity Analysis Qingyuan Zhao Department of Statistics, The Wharton School University of Pennsylvania May 23, 2018 @ ACIC Based on: Qingyuan Zhao, Dylan S. Small, and Bhaswar B. Bhattacharya.

More information

arxiv: v1 [stat.me] 18 Nov 2018

arxiv: v1 [stat.me] 18 Nov 2018 MALTS: Matching After Learning to Stretch Harsh Parikh 1, Cynthia Rudin 1, and Alexander Volfovsky 2 1 Computer Science, Duke University 2 Statistical Science, Duke University arxiv:1811.07415v1 [stat.me]

More information

The Supervised Learning Approach To Estimating Heterogeneous Causal Regime Effects

The Supervised Learning Approach To Estimating Heterogeneous Causal Regime Effects The Supervised Learning Approach To Estimating Heterogeneous Causal Regime Effects Thai T. Pham Stanford Graduate School of Business thaipham@stanford.edu May, 2016 Introduction Observations Many sequential

More information

Flexible Estimation of Treatment Effect Parameters

Flexible Estimation of Treatment Effect Parameters Flexible Estimation of Treatment Effect Parameters Thomas MaCurdy a and Xiaohong Chen b and Han Hong c Introduction Many empirical studies of program evaluations are complicated by the presence of both

More information

Estimating and Using Propensity Score in Presence of Missing Background Data. An Application to Assess the Impact of Childbearing on Wellbeing

Estimating and Using Propensity Score in Presence of Missing Background Data. An Application to Assess the Impact of Childbearing on Wellbeing Estimating and Using Propensity Score in Presence of Missing Background Data. An Application to Assess the Impact of Childbearing on Wellbeing Alessandra Mattei Dipartimento di Statistica G. Parenti Università

More information

Vector-Based Kernel Weighting: A Simple Estimator for Improving Precision and Bias of Average Treatment Effects in Multiple Treatment Settings

Vector-Based Kernel Weighting: A Simple Estimator for Improving Precision and Bias of Average Treatment Effects in Multiple Treatment Settings Vector-Based Kernel Weighting: A Simple Estimator for Improving Precision and Bias of Average Treatment Effects in Multiple Treatment Settings Jessica Lum, MA 1 Steven Pizer, PhD 1, 2 Melissa Garrido,

More information

High Dimensional Propensity Score Estimation via Covariate Balancing

High Dimensional Propensity Score Estimation via Covariate Balancing High Dimensional Propensity Score Estimation via Covariate Balancing Kosuke Imai Princeton University Talk at Columbia University May 13, 2017 Joint work with Yang Ning and Sida Peng Kosuke Imai (Princeton)

More information

Targeted Maximum Likelihood Estimation in Safety Analysis

Targeted Maximum Likelihood Estimation in Safety Analysis Targeted Maximum Likelihood Estimation in Safety Analysis Sam Lendle 1 Bruce Fireman 2 Mark van der Laan 1 1 UC Berkeley 2 Kaiser Permanente ISPE Advanced Topics Session, Barcelona, August 2012 1 / 35

More information

Gov 2002: 4. Observational Studies and Confounding

Gov 2002: 4. Observational Studies and Confounding Gov 2002: 4. Observational Studies and Confounding Matthew Blackwell September 10, 2015 Where are we? Where are we going? Last two weeks: randomized experiments. From here on: observational studies. What

More information

Bayesian Additive Regression Tree (BART) with application to controlled trail data analysis

Bayesian Additive Regression Tree (BART) with application to controlled trail data analysis Bayesian Additive Regression Tree (BART) with application to controlled trail data analysis Weilan Yang wyang@stat.wisc.edu May. 2015 1 / 20 Background CATE i = E(Y i (Z 1 ) Y i (Z 0 ) X i ) 2 / 20 Background

More information

Marginal versus conditional effects: does it make a difference? Mireille Schnitzer, PhD Université de Montréal

Marginal versus conditional effects: does it make a difference? Mireille Schnitzer, PhD Université de Montréal Marginal versus conditional effects: does it make a difference? Mireille Schnitzer, PhD Université de Montréal Overview In observational and experimental studies, the goal may be to estimate the effect

More information

The Impact of Measurement Error on Propensity Score Analysis: An Empirical Investigation of Fallible Covariates

The Impact of Measurement Error on Propensity Score Analysis: An Empirical Investigation of Fallible Covariates The Impact of Measurement Error on Propensity Score Analysis: An Empirical Investigation of Fallible Covariates Eun Sook Kim, Patricia Rodríguez de Gil, Jeffrey D. Kromrey, Rheta E. Lanehart, Aarti Bellara,

More information

Robust Bayesian Variable Selection for Modeling Mean Medical Costs

Robust Bayesian Variable Selection for Modeling Mean Medical Costs Robust Bayesian Variable Selection for Modeling Mean Medical Costs Grace Yoon 1,, Wenxin Jiang 2, Lei Liu 3 and Ya-Chen T. Shih 4 1 Department of Statistics, Texas A&M University 2 Department of Statistics,

More information

Partial factor modeling: predictor-dependent shrinkage for linear regression

Partial factor modeling: predictor-dependent shrinkage for linear regression modeling: predictor-dependent shrinkage for linear Richard Hahn, Carlos Carvalho and Sayan Mukherjee JASA 2013 Review by Esther Salazar Duke University December, 2013 Factor framework The factor framework

More information

Correlation & Regression Chapter 5

Correlation & Regression Chapter 5 Correlation & Regression Chapter 5 Correlation: Do you have a relationship? Between two Quantitative Variables (measured on Same Person) (1) If you have a relationship (p

More information

Item Response Theory for Conjoint Survey Experiments

Item Response Theory for Conjoint Survey Experiments Item Response Theory for Conjoint Survey Experiments Devin Caughey Hiroto Katsumata Teppei Yamamoto Massachusetts Institute of Technology PolMeth XXXV @ Brigham Young University July 21, 2018 Conjoint

More information

Bayesian Ensemble Learning

Bayesian Ensemble Learning Bayesian Ensemble Learning Hugh A. Chipman Department of Mathematics and Statistics Acadia University Wolfville, NS, Canada Edward I. George Department of Statistics The Wharton School University of Pennsylvania

More information

Introduction to Machine Learning CMU-10701

Introduction to Machine Learning CMU-10701 Introduction to Machine Learning CMU-10701 23. Decision Trees Barnabás Póczos Contents Decision Trees: Definition + Motivation Algorithm for Learning Decision Trees Entropy, Mutual Information, Information

More information

Causal Inference in Observational Studies with Non-Binary Treatments. David A. van Dyk

Causal Inference in Observational Studies with Non-Binary Treatments. David A. van Dyk Causal Inference in Observational Studies with Non-Binary reatments Statistics Section, Imperial College London Joint work with Shandong Zhao and Kosuke Imai Cass Business School, October 2013 Outline

More information

Use of Matching Methods for Causal Inference in Experimental and Observational Studies. This Talk Draws on the Following Papers:

Use of Matching Methods for Causal Inference in Experimental and Observational Studies. This Talk Draws on the Following Papers: Use of Matching Methods for Causal Inference in Experimental and Observational Studies Kosuke Imai Department of Politics Princeton University April 13, 2009 Kosuke Imai (Princeton University) Matching

More information

An Introduction to Causal Analysis on Observational Data using Propensity Scores

An Introduction to Causal Analysis on Observational Data using Propensity Scores An Introduction to Causal Analysis on Observational Data using Propensity Scores Margie Rosenberg*, PhD, FSA Brian Hartman**, PhD, ASA Shannon Lane* *University of Wisconsin Madison **University of Connecticut

More information

Chapter 11. Regression with a Binary Dependent Variable

Chapter 11. Regression with a Binary Dependent Variable Chapter 11 Regression with a Binary Dependent Variable 2 Regression with a Binary Dependent Variable (SW Chapter 11) So far the dependent variable (Y) has been continuous: district-wide average test score

More information

Selective Inference for Effect Modification: An Empirical Investigation

Selective Inference for Effect Modification: An Empirical Investigation Observational Studies () Submitted ; Published Selective Inference for Effect Modification: An Empirical Investigation Qingyuan Zhao Department of Statistics The Wharton School, University of Pennsylvania

More information

Data analysis strategies for high dimensional social science data M3 Conference May 2013

Data analysis strategies for high dimensional social science data M3 Conference May 2013 Data analysis strategies for high dimensional social science data M3 Conference May 2013 W. Holmes Finch, Maria Hernández Finch, David E. McIntosh, & Lauren E. Moss Ball State University High dimensional

More information

The risk of machine learning

The risk of machine learning / 33 The risk of machine learning Alberto Abadie Maximilian Kasy July 27, 27 2 / 33 Two key features of machine learning procedures Regularization / shrinkage: Improve prediction or estimation performance

More information

Machine learning, shrinkage estimation, and economic theory

Machine learning, shrinkage estimation, and economic theory Machine learning, shrinkage estimation, and economic theory Maximilian Kasy December 14, 2018 1 / 43 Introduction Recent years saw a boom of machine learning methods. Impressive advances in domains such

More information

Propensity-Score Based Methods for Causal Inference in Observational Studies with Fixed Non-Binary Treatments

Propensity-Score Based Methods for Causal Inference in Observational Studies with Fixed Non-Binary Treatments Propensity-Score Based Methods for Causal Inference in Observational Studies with Fixed Non-Binary reatments Shandong Zhao David A. van Dyk Kosuke Imai July 3, 2018 Abstract Propensity score methods are

More information

Lecture 3: Causal inference

Lecture 3: Causal inference MACHINE LEARNING FOR HEALTHCARE 6.S897, HST.S53 Lecture 3: Causal inference Prof. David Sontag MIT EECS, CSAIL, IMES (Thanks to Uri Shalit for many of the slides) *Last week: Type 2 diabetes 1994 2000

More information

Variable Selection and Sensitivity Analysis via Dynamic Trees with an application to Computer Code Performance Tuning

Variable Selection and Sensitivity Analysis via Dynamic Trees with an application to Computer Code Performance Tuning Variable Selection and Sensitivity Analysis via Dynamic Trees with an application to Computer Code Performance Tuning Robert B. Gramacy University of Chicago Booth School of Business faculty.chicagobooth.edu/robert.gramacy

More information

Propensity Scores for Repeated Treatments

Propensity Scores for Repeated Treatments C O R P O R A T I O N Propensity Scores for Repeated Treatments A Tutorial for the iptw Function in the TWANG Package Lane F. Burgette, Beth Ann Griffin, Daniel F. McCaffrey For more information on this

More information

What s New in Econometrics. Lecture 1

What s New in Econometrics. Lecture 1 What s New in Econometrics Lecture 1 Estimation of Average Treatment Effects Under Unconfoundedness Guido Imbens NBER Summer Institute, 2007 Outline 1. Introduction 2. Potential Outcomes 3. Estimands and

More information

Dynamics in Social Networks and Causality

Dynamics in Social Networks and Causality Web Science & Technologies University of Koblenz Landau, Germany Dynamics in Social Networks and Causality JProf. Dr. University Koblenz Landau GESIS Leibniz Institute for the Social Sciences Last Time:

More information

Learning Representations for Counterfactual Inference. Fredrik Johansson 1, Uri Shalit 2, David Sontag 2

Learning Representations for Counterfactual Inference. Fredrik Johansson 1, Uri Shalit 2, David Sontag 2 Learning Representations for Counterfactual Inference Fredrik Johansson 1, Uri Shalit 2, David Sontag 2 1 2 Counterfactual inference Patient Anna comes in with hypertension. She is 50 years old, Asian

More information

Instrumental Variables

Instrumental Variables Instrumental Variables James H. Steiger Department of Psychology and Human Development Vanderbilt University James H. Steiger (Vanderbilt University) Instrumental Variables 1 / 10 Instrumental Variables

More information

Quantitative Economics for the Evaluation of the European Policy

Quantitative Economics for the Evaluation of the European Policy Quantitative Economics for the Evaluation of the European Policy Dipartimento di Economia e Management Irene Brunetti Davide Fiaschi Angela Parenti 1 25th of September, 2017 1 ireneb@ec.unipi.it, davide.fiaschi@unipi.it,

More information

The Econometric Evaluation of Policy Design: Part I: Heterogeneity in Program Impacts, Modeling Self-Selection, and Parameters of Interest

The Econometric Evaluation of Policy Design: Part I: Heterogeneity in Program Impacts, Modeling Self-Selection, and Parameters of Interest The Econometric Evaluation of Policy Design: Part I: Heterogeneity in Program Impacts, Modeling Self-Selection, and Parameters of Interest Edward Vytlacil, Yale University Renmin University, Department

More information

Instrumental Variables

Instrumental Variables James H. Steiger Department of Psychology and Human Development Vanderbilt University Regression Modeling, 2009 1 Introduction 2 3 4 Instrumental variables allow us to get a better estimate of a causal

More information

Estimation of Optimal Treatment Regimes Via Machine Learning. Marie Davidian

Estimation of Optimal Treatment Regimes Via Machine Learning. Marie Davidian Estimation of Optimal Treatment Regimes Via Machine Learning Marie Davidian Department of Statistics North Carolina State University Triangle Machine Learning Day April 3, 2018 1/28 Optimal DTRs Via ML

More information

Program Evaluation with High-Dimensional Data

Program Evaluation with High-Dimensional Data Program Evaluation with High-Dimensional Data Alexandre Belloni Duke Victor Chernozhukov MIT Iván Fernández-Val BU Christian Hansen Booth ESWC 215 August 17, 215 Introduction Goal is to perform inference

More information

A spatial causal analysis of wildfire-contributed PM 2.5 using numerical model output. Brian Reich, NC State

A spatial causal analysis of wildfire-contributed PM 2.5 using numerical model output. Brian Reich, NC State A spatial causal analysis of wildfire-contributed PM 2.5 using numerical model output Brian Reich, NC State Workshop on Causal Adjustment in the Presence of Spatial Dependence June 11-13, 2018 Brian Reich,

More information

Investigating mediation when counterfactuals are not metaphysical: Does sunlight exposure mediate the effect of eye-glasses on cataracts?

Investigating mediation when counterfactuals are not metaphysical: Does sunlight exposure mediate the effect of eye-glasses on cataracts? Investigating mediation when counterfactuals are not metaphysical: Does sunlight exposure mediate the effect of eye-glasses on cataracts? Brian Egleston Fox Chase Cancer Center Collaborators: Daniel Scharfstein,

More information

Statistical Inference for Data Adaptive Target Parameters

Statistical Inference for Data Adaptive Target Parameters Statistical Inference for Data Adaptive Target Parameters Mark van der Laan, Alan Hubbard Division of Biostatistics, UC Berkeley December 13, 2013 Mark van der Laan, Alan Hubbard ( Division of Biostatistics,

More information

Bayesian Nonparametric Accelerated Failure Time Models for Analyzing Heterogeneous Treatment Effects

Bayesian Nonparametric Accelerated Failure Time Models for Analyzing Heterogeneous Treatment Effects Bayesian Nonparametric Accelerated Failure Time Models for Analyzing Heterogeneous Treatment Effects Nicholas C. Henderson Thomas A. Louis Gary Rosner Ravi Varadhan Johns Hopkins University September 28,

More information

Truncation and Censoring

Truncation and Censoring Truncation and Censoring Laura Magazzini laura.magazzini@univr.it Laura Magazzini (@univr.it) Truncation and Censoring 1 / 35 Truncation and censoring Truncation: sample data are drawn from a subset of

More information

Making Our Cities Safer: A Study In Neighbhorhood Crime Patterns

Making Our Cities Safer: A Study In Neighbhorhood Crime Patterns Making Our Cities Safer: A Study In Neighbhorhood Crime Patterns Aly Kane alykane@stanford.edu Ariel Sagalovsky asagalov@stanford.edu Abstract Equipped with an understanding of the factors that influence

More information

A Bayesian Machine Learning Approach for Optimizing Dynamic Treatment Regimes

A Bayesian Machine Learning Approach for Optimizing Dynamic Treatment Regimes A Bayesian Machine Learning Approach for Optimizing Dynamic Treatment Regimes Thomas A. Murray, (tamurray@mdanderson.org), Ying Yuan, (yyuan@mdanderson.org), and Peter F. Thall (rex@mdanderson.org) Department

More information

Statistical Consulting Topics Classification and Regression Trees (CART)

Statistical Consulting Topics Classification and Regression Trees (CART) Statistical Consulting Topics Classification and Regression Trees (CART) Suppose the main goal in a data analysis is the prediction of a categorical variable outcome. Such as in the examples below. Given

More information

Measuring Social Influence Without Bias

Measuring Social Influence Without Bias Measuring Social Influence Without Bias Annie Franco Bobbie NJ Macdonald December 9, 2015 The Problem CS224W: Final Paper How well can statistical models disentangle the effects of social influence from

More information

Balancing Covariates via Propensity Score Weighting

Balancing Covariates via Propensity Score Weighting Balancing Covariates via Propensity Score Weighting Kari Lock Morgan Department of Statistics Penn State University klm47@psu.edu Stochastic Modeling and Computational Statistics Seminar October 17, 2014

More information

Gaussian Processes. Le Song. Machine Learning II: Advanced Topics CSE 8803ML, Spring 2012

Gaussian Processes. Le Song. Machine Learning II: Advanced Topics CSE 8803ML, Spring 2012 Gaussian Processes Le Song Machine Learning II: Advanced Topics CSE 8803ML, Spring 01 Pictorial view of embedding distribution Transform the entire distribution to expected features Feature space Feature

More information

Weighting. Homework 2. Regression. Regression. Decisions Matching: Weighting (0) W i. (1) -å l i. )Y i. (1-W i 3/5/2014. (1) = Y i.

Weighting. Homework 2. Regression. Regression. Decisions Matching: Weighting (0) W i. (1) -å l i. )Y i. (1-W i 3/5/2014. (1) = Y i. Weighting Unconfounded Homework 2 Describe imbalance direction matters STA 320 Design and Analysis of Causal Studies Dr. Kari Lock Morgan and Dr. Fan Li Department of Statistical Science Duke University

More information

Topic 7: HETEROSKEDASTICITY

Topic 7: HETEROSKEDASTICITY Universidad Carlos III de Madrid César Alonso ECONOMETRICS Topic 7: HETEROSKEDASTICITY Contents 1 Introduction 1 1.1 Examples............................. 1 2 The linear regression model with heteroskedasticity

More information

causal inference at hulu

causal inference at hulu causal inference at hulu Allen Tran July 17, 2016 Hulu Introduction Most interesting business questions at Hulu are causal Business: what would happen if we did x instead of y? dropped prices for risky

More information

Chapter 14. Multiple Regression Models. Multiple Regression Models. Multiple Regression Models

Chapter 14. Multiple Regression Models. Multiple Regression Models. Multiple Regression Models Chapter 14 Multiple Regression Models 1 Multiple Regression Models A general additive multiple regression model, which relates a dependent variable y to k predictor variables,,, is given by the model equation

More information

Habilitationsvortrag: Machine learning, shrinkage estimation, and economic theory

Habilitationsvortrag: Machine learning, shrinkage estimation, and economic theory Habilitationsvortrag: Machine learning, shrinkage estimation, and economic theory Maximilian Kasy May 25, 218 1 / 27 Introduction Recent years saw a boom of machine learning methods. Impressive advances

More information

Balancing Covariates via Propensity Score Weighting: The Overlap Weights

Balancing Covariates via Propensity Score Weighting: The Overlap Weights Balancing Covariates via Propensity Score Weighting: The Overlap Weights Kari Lock Morgan Department of Statistics Penn State University klm47@psu.edu PSU Methodology Center Brown Bag April 6th, 2017 Joint

More information

Combining multiple observational data sources to estimate causal eects

Combining multiple observational data sources to estimate causal eects Department of Statistics, North Carolina State University Combining multiple observational data sources to estimate causal eects Shu Yang* syang24@ncsuedu Joint work with Peng Ding UC Berkeley May 23,

More information

BART: Bayesian additive regression trees

BART: Bayesian additive regression trees BART: Bayesian additive regression trees Hedibert F. Lopes & Paulo Marques Insper Institute of Education and Research São Paulo, Brazil Most of the notes were kindly provided by Rob McCulloch (Arizona

More information

Shrinkage Methods: Ridge and Lasso

Shrinkage Methods: Ridge and Lasso Shrinkage Methods: Ridge and Lasso Jonathan Hersh 1 Chapman University, Argyros School of Business hersh@chapman.edu February 27, 2019 J.Hersh (Chapman) Ridge & Lasso February 27, 2019 1 / 43 1 Intro and

More information

Double Robustness. Bang and Robins (2005) Kang and Schafer (2007)

Double Robustness. Bang and Robins (2005) Kang and Schafer (2007) Double Robustness Bang and Robins (2005) Kang and Schafer (2007) Set-Up Assume throughout that treatment assignment is ignorable given covariates (similar to assumption that data are missing at random

More information

Empirical Bayes Moderation of Asymptotically Linear Parameters

Empirical Bayes Moderation of Asymptotically Linear Parameters Empirical Bayes Moderation of Asymptotically Linear Parameters Nima Hejazi Division of Biostatistics University of California, Berkeley stat.berkeley.edu/~nhejazi nimahejazi.org twitter/@nshejazi github/nhejazi

More information

Propensity Score Methods for Causal Inference

Propensity Score Methods for Causal Inference John Pura BIOS790 October 2, 2015 Causal inference Philosophical problem, statistical solution Important in various disciplines (e.g. Koch s postulates, Bradford Hill criteria, Granger causality) Good

More information

Causal inference in multilevel data structures:

Causal inference in multilevel data structures: Causal inference in multilevel data structures: Discussion of papers by Li and Imai Jennifer Hill May 19 th, 2008 Li paper Strengths Area that needs attention! With regard to propensity score strategies

More information

Semiparametric Generalized Linear Models

Semiparametric Generalized Linear Models Semiparametric Generalized Linear Models North American Stata Users Group Meeting Chicago, Illinois Paul Rathouz Department of Health Studies University of Chicago prathouz@uchicago.edu Liping Gao MS Student

More information

Estimating the Marginal Odds Ratio in Observational Studies

Estimating the Marginal Odds Ratio in Observational Studies Estimating the Marginal Odds Ratio in Observational Studies Travis Loux Christiana Drake Department of Statistics University of California, Davis June 20, 2011 Outline The Counterfactual Model Odds Ratios

More information

A Sampling of IMPACT Research:

A Sampling of IMPACT Research: A Sampling of IMPACT Research: Methods for Analysis with Dropout and Identifying Optimal Treatment Regimes Marie Davidian Department of Statistics North Carolina State University http://www.stat.ncsu.edu/

More information

EMERGING MARKETS - Lecture 2: Methodology refresher

EMERGING MARKETS - Lecture 2: Methodology refresher EMERGING MARKETS - Lecture 2: Methodology refresher Maria Perrotta April 4, 2013 SITE http://www.hhs.se/site/pages/default.aspx My contact: maria.perrotta@hhs.se Aim of this class There are many different

More information

Matching. Quiz 2. Matching. Quiz 2. Exact Matching. Estimand 2/25/14

Matching. Quiz 2. Matching. Quiz 2. Exact Matching. Estimand 2/25/14 STA 320 Design and Analysis of Causal Studies Dr. Kari Lock Morgan and Dr. Fan Li Department of Statistical Science Duke University Frequency 0 2 4 6 8 Quiz 2 Histogram of Quiz2 10 12 14 16 18 20 Quiz2

More information

1 Motivation for Instrumental Variable (IV) Regression

1 Motivation for Instrumental Variable (IV) Regression ECON 370: IV & 2SLS 1 Instrumental Variables Estimation and Two Stage Least Squares Econometric Methods, ECON 370 Let s get back to the thiking in terms of cross sectional (or pooled cross sectional) data

More information

Have you... Unit 1: Introduction to data Lecture 1: Data collection, observational studies, and experiments. Readiness assessment

Have you... Unit 1: Introduction to data Lecture 1: Data collection, observational studies, and experiments. Readiness assessment Have you... Unit 1: Introduction to data Lecture 1: Data collection, observational studies, and experiments Statistics 101 Mine Çetinkaya-Rundel January 15, 2013 been placed into a team? successfully logged

More information

arxiv: v1 [stat.ml] 1 Jul 2017

arxiv: v1 [stat.ml] 1 Jul 2017 Some methods for heterogeneous treatment effect estimation in high-dimensions arxiv:1707.00102v1 [stat.ml] 1 Jul 2017 Scott Powers, Junyang Qian, Kenneth Jung, Alejandro Schuler, Nigam H. Shah, Trevor

More information

Machine Learning and Applied Econometrics

Machine Learning and Applied Econometrics Machine Learning and Applied Econometrics Double Machine Learning for Treatment and Causal Effects Machine Learning and Econometrics 1 Double Machine Learning for Treatment and Causal Effects This presentation

More information

WU Weiterbildung. Linear Mixed Models

WU Weiterbildung. Linear Mixed Models Linear Mixed Effects Models WU Weiterbildung SLIDE 1 Outline 1 Estimation: ML vs. REML 2 Special Models On Two Levels Mixed ANOVA Or Random ANOVA Random Intercept Model Random Coefficients Model Intercept-and-Slopes-as-Outcomes

More information

Lectures of STA 231: Biostatistics

Lectures of STA 231: Biostatistics Lectures of STA 231: Biostatistics Second Semester Academic Year 2016/2017 Text Book Biostatistics: Basic Concepts and Methodology for the Health Sciences (10 th Edition, 2014) By Wayne W. Daniel Prepared

More information

A dynamic perspective to evaluate multiple treatments through a causal latent Markov model

A dynamic perspective to evaluate multiple treatments through a causal latent Markov model A dynamic perspective to evaluate multiple treatments through a causal latent Markov model Fulvia Pennoni Department of Statistics and Quantitative Methods University of Milano-Bicocca http://www.statistica.unimib.it/utenti/pennoni/

More information

How to Use the Internet for Election Surveys

How to Use the Internet for Election Surveys How to Use the Internet for Election Surveys Simon Jackman and Douglas Rivers Stanford University and Polimetrix, Inc. May 9, 2008 Theory and Practice Practice Theory Works Doesn t work Works Great! Black

More information

Selection on Observables: Propensity Score Matching.

Selection on Observables: Propensity Score Matching. Selection on Observables: Propensity Score Matching. Department of Economics and Management Irene Brunetti ireneb@ec.unipi.it 24/10/2017 I. Brunetti Labour Economics in an European Perspective 24/10/2017

More information

Final Exam - Solutions

Final Exam - Solutions Ecn 102 - Analysis of Economic Data University of California - Davis March 19, 2010 Instructor: John Parman Final Exam - Solutions You have until 5:30pm to complete this exam. Please remember to put your

More information

Factor model shrinkage for linear instrumental variable analysis with many instruments

Factor model shrinkage for linear instrumental variable analysis with many instruments Factor model shrinkage for linear instrumental variable analysis with many instruments P. Richard Hahn Booth School of Business University of Chicago Joint work with Hedibert Lopes 1 My goals for this

More information