There are relatively few systematic comparisons of the ex ante counterfactual pre dictions from structural models to what occurs ex post. The counterfactual analysis jonathan bennett syracuse university two distinctions philosophical theories of causation can be split two ways, into four groups. As a simplistic example, consider a counterfactual exercise in a multinomial choice model where some characteristic of choices, sa,y the price, changes. Hansen 2000, 20201 university of wisconsin department of economics this revision. Counterfactuals university of california, berkeley. This same analysis applies to our choices of career.
Counterfactual analyses have received a good deal of attention in recent years, resulting in a host of counterexamples and objections to the simple analysis and its descendants. A read is counted each time someone views a publication summary such as the title, abstract, and list of authors, clicks on a figure, or views or downloads the fulltext. Recently, there has been growing interest in developing econometric tools to conduct counterfactual analysis with aggregate data when a single \treated unit su ers an intervention, such as a policy change, and there is no obvious control group. The abc of counterfactuals the enlightened economist. What is missing from the term impact evaluation is the way impact shows up longterm. Differenceindifferences an overview sciencedirect topics. It isnt taught properly in economics courses, although essential in competition analysis and also in good econometrics, including estimating the effect of introducing a lowpriced copy of a consumer good into a market. Bayesian counterfactual analysis of the sources of the great moderation kim changjin,a james morleyb and jeremy pigerc a deparment of economics, korea university, seoul, korea.
Counterfactual analysis of inequality and social mobility. The counterexamples are often complex and can seem baroque to the outsider indeed, even to the insider, and it may be tempting to dismiss them as irrelevant or. Econometric analysis and counterfactual studies in the. The same applies to most counterfactual questions, for example, the effect of treatment on the treated ett and mediation problems.
Counterfactual distributions are important ingredients for policy analysis and decomposition analysis in empirical economics. A counterfactual analysis from ethiopia salvatore di falco. Taking stock of recent literature on causality, we. Pearl 2009 provides an overview of the concepts and develops an analysis. It is kept here because margins cannot be used in some contexts, such as multiple imputation. In this paper, we examine the use of the counterfactual method in eu merger control. February, 2020 comments welcome 1this manuscript may be printed and reproduced for individual or instructional use, but may not be printed for. How can african agriculture adapt to climate change. To some, counterfactual analysis is central to comparative inquiry because such research. In the econometric analysis of games, it is relevant to distinguish two di. A counterfactual conditional abbreviated cf, is a conditional with a false ifclause. A brief guide to the content of the folder is given in the readme. I will share with readers my current thoughts on heckmans approach to causality and on where causality is heading in econometrics. Abstract the counterfactual package implements the estimation and inference methods of cher nozhukov et al.
We do this by breaking iv analysis into two supervised stages that can each be targeted with deep networks and that, when solved, allow us to make counterfactual claims and perform causal inference. Inference on counterfactual distributions chernozhukov. In its simplest form, counterfactual impact evaluation cie is a method of comparison which involves comparing the outcomes of interest of those having benefitted from a policy or programme the treated group with those of a group similar in all respects to the treatment group the comparisoncontrol group, the only difference being that the comparisoncontrol group has not been. Heckman the university of chicago, usa american bar foundation, usa university college dublin, ireland edward j. For example, the wage that an individual would have earned had she not gone to college. Usually the counterfactuals on offer are proposed as causal surrogates. The term counterfactual has a variety of distinct, though connected, uses in philosophy, history, economics and statistics. The main objective and contribution of this paper is to provide estimation and inference procedures for the entire marginal counterfactual distribution of y and its functionals based on regression methods. Levy i focus primarily on the utility of counterfactual analysis for helping to validate causal inferences in historical analysis. Identi cation of structural and counterfactual parameters. The guiding idea behind counterfactual analyses of causation is the thought that as david lewis puts it we think of a cause as something that makes a difference, and the difference it makes must be a difference from what would have happened without it. Using standard econometric methods, i find sizable investment effects.
Between complexity and parsimony limited diversity. April 20 comments are welcome but please do not quote, cite or distributeupload this preliminary draft. Analysis counterfactuals, causal inference, and historical. Statistical simulation and counterfactual analysis in.
Ragin and john sonnett 1 overview counterfactual analysis has a long and distinguished history in comparative research. Counterfactuals explanation and examples conceptually. Coping with change the aim of standard statistical analysis, typi. Compare results to the counterfactual one of the three tasks involved in understanding causes is to compare the observed results to those you would expect if the intervention had not been implemented this is known as the counterfactual. Inferring causal impact using bayesian structural time. Vytlacil columbia university, usa contents abstract 4780 keywords 4781 1. This paper provides an overview on the counterfactual and related approaches. The term counterfactual has a wide range of uses in philosophy, history, economics and statistics. Countryspecic oil supply shocks and the global economy. Campos brunel university and izabonn fabrizio coricelli paris school of economics and ceprlondon luigi moretti university of padova this version.
Patton2 1department of economics, university of washington, seattle, washington 98195. We use binary regressions to model conditional distributions of real outcomes. The study of counterfactual speculation has increasingly engaged the interest of scholars in a wide range of domains such as philosophy, human geography. Econometric analysis, 7e by greene is a major revision both in terms of organization of the material and in terms of new ideas and treatments in the seventh edition, greene substantially rearranged the early part of the book to produce a more natural sequence of topics for the graduate econometrics course. The role of empirical assumptions in economic analysis. Statistical simulation and counterfactual analysis in social. So, who needs to see counterfactual variables explicitly in the graph. The critical step in any causal analysis is estimating the counterfactual a prediction of what would have happened in the absence of the treatment. An empirical investigation into the effects of quantitative easing. Statistical simulation and counterfactual analysis in social sciences francois gelineau, pierreolivier bedard, mathieu ouimet universite laval in this paper, we present statistical simulation techniques of interest in substantial interpretation of regression results. An r package for counterfactual analysis by mingli chen, victor chernozhukov, ivan fernandezval and blaise melly abstract the counterfactual package implements the estimation and inference methods ofchernozhukov et al. This paper indeed clarifies some of my questions, yet raises others. Counterfactuals and policy analysis in structural models.
Counterfactual the unobserved, alternative outcome that the individual has not realized. Pdf econometric techniques are changing very rapidly along with developments in economic theories. How can we use what did not happen but which easily could have happened to understand what did happen. The r package counterfactual implements the methods of chernozhukov et al. The counterfactual analysis of causation became a focus of philosophical debate after the 1973 publication of the late david lewiss groundbreaking paper, causation, which argues against the previously accepted regularity analysis and in favor of what he called the promising alternative of the counterfactual analysis. The counterfactual analysis in eu merger control ssrn. Pearl 2009 provides an overview of the concepts and develops an analysis of causality based on structural models. Here we introduce the notion of a counterfactual which is fundamental in causal analysis. Causal inference based on counterfactuals bmc medical. Counterfactual distributions ilet 0 denote 1979 and 1 denote 1988. Event theories give pride of place to causal statements such as. We can do this for counterfactuals as well as for factuals. Inference on counterfactual distributions the econometric.
Counterfactual analysis consists of evaluating the e ects of such changes. This paper proposes to infer causal impact on the basis of a diffusionregression statespace model that predicts the counter. May 20 this workshop focuses on graphical causal models. Limited diversity, counterfactual cases, and comparative analysis charles c. Bayesian counterfactual analysis of the sources of the. Policy analysis in economics aims to predict the e. An empirical investigation into the effects of quantitative easing, authormohammad hashem pesaran and r. Levy 2015 counterfactuals, causal inference, and historical.
Three essays in counterfactual econometrics by santiago pereda ernandezf a dissertation submitted in partial satisfaction of the requirements for the degree of. Counterfactual theories of causation stanford encyclopedia. In june 20 the commission published a communication and a practical guide on quantifying antitrust damages, which contain a detailed analysis of various counterfactuals. How would the income distribution in my sample change if all the black people were white. Differencesindifferences strategies are simple paneldata methods applied to sets of group means in cases when certain groups are exposed to.
An important problem in econometrics and marketing is to infer the causal impact that a designed market intervention has exerted on an outcome metric over time. Introduction counterfactuals are a hot topic in economics today, at least among economists concerned with methodology. This is an elementary introduction to causal inference in economics written for readers familiar with machine learning methods. Advanced level of economic analysis requires training in advanced econometrics. Teaching causal inference in undergraduate econometrics. Then, the counterfactual choice probability s is an integration of each agent is counterfactual choice decision ye i. Structural estimation and counterfactual experiments in. Using econometric terminology, we can often think of a counterfactual distribution as the. Counterfactual analysis enables evaluators to attribute cause and effect between interventions and outcomes. Supplement to inference on counterfactual distributions this zip file contains the data and programs for the empirical application. Sep, 2005 the counterfactual or potential outcome model has become increasingly standard for causal inference in epidemiological and medical studies. Causal analysis in theory and practice counterfactual.
An r package for counterfactual analysis mingli chen, victor chernozhukov, ivan fernandezval and blaise melly, the r journal 2017 9. Iy is wages and x is a vector of worker characteristics education, experience. Aug 14, 2019 prepared for the handbook of econometrics, vol. In philosophy counterfactual scenarios are often used in the analysis of causality, e. Inferring causal impact using bayesian structural timeseries.
Department of economics, university of washington, seattle, washington, usa b department of economics, washington university, st louis, missouri, usa. An empirical investigation into the effects of quantitative easing this paper is concerned with ex ante and counterfactual analyses in the case of ex post macroeconometric applications where a single unit is observed before and after a given policy intervention. I just wish people would learn to think about counterfactuals. Real e ective exchange rate misalignment in the euro area. Geradin the counterfactual method in eu competition law. The counterfactual measures what would have happened to beneficiaries in the absence of the intervention, and impact is estimated by comparing counterfactual outcomes to those observed under the intervention. Making predictions with counterfactual data in stata. We can also do counterfactual social mobility analysis. The powerful techniques used in machine learning may. Households data are combined with spatial climate data.
The graphical approach to causal inference using directed acyclic graphs dags is equivalent to the potential outcomes approach to causal inference. We can do a parallel analysis for those who switch from s 1 to s 0. In this article, we develop modeling and inference tools for counterfactual distributions based on regression methods. Generative learning of counterfactual for synthetic control. These are just the kinds of questions heckman considers in his applied work, where he is at pains to point out that the question itself must be carefully formulated. The term counterfactual conditional was coined by nelson goodman in 1947, extending roderick chisholms 1946 notion of a contrarytofact conditional. It is kept here because margins cannot be used in some contexts, such as multiple imputation social science researchers often want to ask hypothetical questions. The second counterfactual, therefore, couldonlybetrueifno. First, there is the split between event and fact or state of affairs theories.
1374 89 971 842 462 240 160 335 240 276 171 55 196 1442 1188 1482 1268 97 1352 1294 486 1293 1410 505 121 1324 1450 1647 1026 1401 929 1086 940 670 264 547 1479 305 768 1091