DOCSLIB.ORG

Factors Relevant to the Validity of Experiments in Social Settings1 Donald T

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Factors Relevant to the Validity of Experiments in Social Settings1 Donald T PSYCHOLOGICAL BULLETIN VOL. 54, No. 4, 1957 FACTORS RELEVANT TO THE VALIDITY OF EXPERIMENTS IN SOCIAL SETTINGS1 DONALD T. CAMPBELL Northwestern University What do we seek to control in ex- the process of analyzing three pre- perimental designs? What extraneous experimental designs. In the subse- variables which would otherwise con- quent evaluation of the applicability found our interpretation of the of three true experimental designs, experiment do we wish to rule out? factors leading to external invalidity The present paper attempts a specifi- will be introduced. The effects of cation of the major categories of such these extraneous variables will be extraneous variables and employs considered at two levels: as simple or these categories in evaluating the main effects, they occur independ- validity of standard designs for ex- ently of or in addition to the effects perimentation in the social sciences. of the experimental variable; as Validity will be evaluated in terms interactions, the effects appear in of two major criteria. First, and as a conjunction with the experimental basic minimum, is what can be called variable. The main effects typically internal validity: did in fact the ex- turn out to be relevant to internal perimental stimulus make some sig- validity, the interaction effects to ex- nificant difference in this specific in- ternal validity or representativeness. stance? The second criterion is that The following designation for ex- of external validity, representativeness, perimental designs will be used: X or generalizability: to what popula- will represent the exposure of a group tions, settings, and variables can this to the experimental variable or event, effect be generalized? Both criteria the effects of which are to be meas- are obviously important although it ured; 0 will refer to the process of turns out that they are to some ex- observation or measurement, which tent incompatible, in that the con- can include watching what people do, trols required for internal validity listening, recording, interviewing, ad- often tend to jeopardize representa- ministering tests, counting lever de- tiveness. pressions, etc. The Xs and Os in a The extraneous variables affecting given row are applied to the same internal validity will be introduced in specific persons. The left to right di- 1 mension indicates temporal order. A dittoed version of this paper was pri- Parallel rows represent equivalent vately distributed in 1953 under the title "Designs for Social Science Experiments." samples of persons unless otherwise The author has had the opportunity to benefit specified. The designs will be num- from the careful reading and suggestions of bered and named for cross-reference L. S. Burwen, J. W. Cotton, C. P. Duncan, purposes. D. W. Fiske, C. I. Hovland, L. V. Jones, E. S. Marks, D. C. Pelz, and B. J. Underwood, THREE PRE-EXPERIMENTAL DESIGNS among others, and wishes to express his ap- preciation. They have not had the opportu- AND THEIR CONFOUNDED EXTRANE- nity of seeing the paper in its present form, OUS VARIABLES and bear no responsibility for it. The author also wishes to thank S. A. Stouffer (33) and The One-Shot Case Study. As B. J. Underwood (36) for their public en- Stouffer (32) has pointed out, much couragement. social science research still uses De- 297 298 DONALD T. CAMPBELL sign 1, in which a single individual or in which all extraneous stimuli are group is studied in detail only once, eliminated. The approximation of and in which the observations are such control in much physical and attributed to exposure to some prior biological research has permitted the situation. satisfactory employment of Design 2. X 0 1. One-Shot Case Study But in social psychology and the other social sciences, if history is con- This design does not merit the title of founded with X the results are gen- experiment, and is introduced only to erally uninterpretable. provide a reference point. The very The second class of variables con- minimum of useful scientific infor- founded with X in Design 2 is here mation involves at least one formal designated as maturation. This covers comparison and therefore at least two those effects which are systematic careful observations (2). with the passage of time, and not, The One-Group Pretest-Posttest De- like history, a function of the specific sign. This design does provide for one events involved. Thus between Oi formal comparison of two observa- and 02 the respondents may have tions, and is still widely used. grown older, hungrier, tireder, etc., 0i X 02 2. One-Group Pretest-Posttest and these may have produced the Design difference between 0\ and 02, inde- However, in it there are four or five pendently of X. While in the typical categories of extraneous variables left brief experiment in the psychology uncontrolled which thus become rival laboratory, maturation is unlikely to explanations of any difference be- be a source of change, it has been a tween 0i and 02, confounded with problem in research in child develop- the possible effect of X. ment and can be so in extended ex- The first of these is the main effect periments in social psychology and of history. During the time span education. In the form of "spontane- ous remission" and the general between 0i and 02 many events have occurred in addition to X, and the processes of healing it becomes an results might be attributed to these. important variable to control in Thus in Collier's (8) experiment, medical research, psychotherapy, and 2 social remediation. while his respondents were reading Nazi propaganda materials, France There is a third source of variance fell, and the obtained attitude that could explain the difference be- changes seemed more likely a result of tween Oi and 02 without a recourse to this event than of the propaganda.3 the effect of X. This is the effect of By history is meant the specific event testing itself. It is often true that series other than X, i.e., the extra- persons taking a test for the second experimental uncontrolled stimuli. time make scores systematically dif- Relevant to this variable is the con- ferent from those taking the test for cept of experimental isolation, the the first time. This is indeed the case employment of experimental settings for intelligence tests, where a second mean may be expected to run as s In line with the central focus on social much as five IQ points higher than psychology and the social sciences, the term the first one. This possibility makes respondent is employed in place of the terms subject, patient, or client. important a distinction between re- 3 Collier actually used a more adequate de- active measures and nonreactive meas- sign than this, an approximation to Design 4. ures. A reactive measure is one VALIDITY OF EXPERIMENTS IN SOCIAL SETTINGS 299 which modifies the phenomenon un- niques must be rated as reactive, as der study, which changes the very shown, for example, by Crespi's (9) thing that one is trying to measure. evidence. In general, any measurement proce- Even within the personality and dure which makes the subject self- attitude test domain, it may be conscious or aware of the fact of the found that tests differ in the degree to experiment can be suspected of being which they are reactive. For some a reactive measurement. Whenever purposes, tests involving voluntary the measurement process is not a part self-description may turn out to be of the normal environment it is prob- more reactive (especially at the inter- ably reactive. Whenever measure- action level to be discussed below) ment exercises the process under than are devices which focus the study, it is almost certainly reactive. respondent upon describing the ex- Measurement of a person's height is ternal world, or give him less latitude relatively nonreactive. However, in describing himself (e.g., 5). It measurement of weight, introduced seems likely that, apart from consid- into an experimental design involving erations of validity, the Rorschach adult American women, would turn test is less reactive than the TAT or out to be reactive in that the process MMPI. Where the reactive nature of of measuring would stimulate weight the testing process results from the reduction. A photograph of a crowd focusing of attention on the experi- taken in secret from a second story mental variable, it may be reduced window would be nonreactive, but a by imbedding the relevant content in news photograph of the same scene a comprehensive array of topics, as might very well be reactive, in that has regularly been done in Hovland's the presence of the photographer attitude change studies (14). It would modify the behavior of people seems likely that with attention to seeing themselves being photo- the problem, observational and meas- graphed. In a factory, production urement techniques can be devel- records introduced for the purpose of oped which are much less reactive an experiment would be reactive, but than those now in use. if such records were a regular part of Instrument decay provides a fourth the operating environment they uncontrolled source of variance which would be nonreactive. An English could produce an Oi-Os difference anthropologist may be nonreactive as that might be mistaken for the effect a participant-observer at an English of X. This variable can be exem- wedding, but might be a highly reac- plified by the fatiguing of a spring tive measuring instrument at a Dobu scales, or the condensation of water nuptials. Some measures are so ex- vapor in a cloud chamber. For psy- tremely reactive that their use in a chology and the social sciences it pretest-posttest design is not usually becomes a particularly acute problem considered.
Load more

Recommended publications
  • Toward an Ethical Experiment
    TOWARD AN ETHICAL EXPERIMENT By Yusuke Narita April 2018 COWLES FOUNDATION DISCUSSION PAPER NO. 2127 COWLES FOUNDATION FOR RESEARCH IN ECONOMICS YALE UNIVERSITY Box 208281 New Haven, Connecticut 06520-8281 http://cowles.yale.edu/ ∗ Toward an Ethical Experiment y Yusuke Narita April 17, 2018 Abstract Randomized Controlled Trials (RCTs) enroll hundreds of millions of subjects and in- volve many human lives. To improve subjects' welfare, I propose an alternative design of RCTs that I call Experiment-as-Market (EXAM). EXAM Pareto optimally randomly assigns each treatment to subjects predicted to experience better treatment effects or to subjects with stronger preferences for the treatment. EXAM is also asymptotically incentive compatible for preference elicitation. Finally, EXAM unbiasedly estimates any causal effect estimable with standard RCTs. I quantify the welfare, incentive, and information properties by applying EXAM to a water cleaning experiment in Kenya (Kremer et al., 2011). Compared to standard RCTs, EXAM substantially improves subjects' predicted well-being while reaching similar treatment effect estimates with similar precision. Keywords: Research Ethics, Clinical Trial, Social Experiment, A/B Test, Market De- sign, Causal Inference, Development Economics, Spring Protection, Discrete Choice ∗I am grateful to Dean Karlan for a conversation that inspired this project; Joseph Moon for industrial and institutional input; Jason Abaluck, Josh Angrist, Tim Armstrong, Sylvain Chassang, Naoki Egami, Peter Hull, Costas Meghir, Bobby Pakzad-Hurson,
    [Show full text]
  • Using Randomized Evaluations to Improve the Efficiency of US Healthcare Delivery
    Using Randomized Evaluations to Improve the Efficiency of US Healthcare Delivery Amy Finkelstein Sarah Taubman MIT, J-PAL North America, and NBER MIT, J-PAL North America February 2015 Abstract: Randomized evaluations of interventions that may improve the efficiency of US healthcare delivery are unfortunately rare. Across top journals in medicine, health services research, and economics, less than 20 percent of studies of interventions in US healthcare delivery are randomized. By contrast, about 80 percent of studies of medical interventions are randomized. The tide may be turning toward making randomized evaluations closer to the norm in healthcare delivery, as the relevant actors have an increasing need for rigorous evidence of what interventions work and why. At the same time, the increasing availability of administrative data that enables high-quality, low-cost RCTs and of new sources of funding that support RCTs in healthcare delivery make them easier to conduct. We suggest a number of design choices that can enhance the feasibility and impact of RCTs on US healthcare delivery including: greater reliance on existing administrative data; measuring a wide range of outcomes on healthcare costs, health, and broader economic measures; and designing experiments in a way that sheds light on underlying mechanisms. Finally, we discuss some of the more common concerns raised about the feasibility and desirability of healthcare RCTs and when and how these can be overcome. _____________________________ We are grateful to Innessa Colaiacovo, Lizi Chen, and Belinda Tang for outstanding research assistance, to Katherine Baicker, Mary Ann Bates, Kelly Bidwell, Joe Doyle, Mireille Jacobson, Larry Katz, Adam Sacarny, Jesse Shapiro, and Annetta Zhou for helpful comments, and to the Laura and John Arnold Foundation for financial support.
    [Show full text]
  • Social Psychology
    Social Psychology OUTLINE OF RESOURCES Introducing Social Psychology Lecture/Discussion Topic: Social Psychology’s Most Important Lessons (p. 853) Social Thinking The Fundamental Attribution Error Lecture/Discussion Topic: Attribution and Models of Helping (p. 856) Classroom Exercises: The Fundamental Attribution Error (p. 854) Students’ Perceptions of You (p. 855) Classroom Exercise/Critical Thinking Break: Biases in Explaining Events (p. 855) NEW Feature (Short) Film: The Lunch Date (p. 856) Worth Video Anthology: The Actor-Observer Difference in Attribution: Observe a Riot in Action* Attitudes and Actions Lecture/Discussion Topics: The Looking Glass Effect (p. 856) The Theory of Reasoned Action (p. 857) Actions Influence Attitudes (p. 857) The Justification of Effort (p. 858) Self-Persuasion (p. 859) Revisiting the Stanford Prison Experiment (p. 859) Abu Ghraib Prison and Social Psychology (p. 860) Classroom Exercise: Introducing Cognitive Dissonance Theory (p. 858) Worth Video Anthology: Zimbardo’s Stanford Prison Experiment* The Stanford Prison Experiment: The Power of the Situation* Social Influence Conformity: Complying With Social Pressures Lecture/Discussion Topics: Mimicry and Prosocial Behavior (p. 861) Social Exclusion and Mimicry (p. 861) The Seattle Windshield Pitting Epidemic (p. 862) Classroom Exercises: Suggestibility (p. 862) Social Influence (p. 863) Student Project: Violating a Social Norm (p. 863) Worth Video Anthology: Social Influence* NEW Liking and Imitation: The Sincerest Form of Flattery* Obedience: Following Orders Lecture/Discussion Topic: Obedience in Everyday Life (p. 865) Classroom Exercises: Obedience and Conformity (p. 864) Would You Obey? (p. 864) Wolves or Sheep? (p. 866) * Titles in the Worth Video Anthology are not described within the core resource unit.
    [Show full text]
  • The Core Analytics of Randomized Experiments for Social Research
    MDRC Working Papers on Research Methodology The Core Analytics of Randomized Experiments for Social Research Howard S. Bloom August 2006 This working paper is part of a series of publications by MDRC on alternative methods of evaluating the implementation and impacts of social and educational programs and policies. The paper will be published as a chapter in the forthcoming Handbook of Social Research by Sage Publications, Inc. Many thanks are due to Richard Dorsett, Carolyn Hill, Rob Hollister, and Charles Michalopoulos for their helpful suggestions on revising earlier drafts. This working paper was supported by the Judith Gueron Fund for Methodological Innovation in Social Policy Research at MDRC, which was created through gifts from the Annie E. Casey, Rocke- feller, Jerry Lee, Spencer, William T. Grant, and Grable Foundations. The findings and conclusions in this paper do not necessarily represent the official positions or poli- cies of the funders. Dissemination of MDRC publications is supported by the following funders that help finance MDRC’s public policy outreach and expanding efforts to communicate the results and implications of our work to policymakers, practitioners, and others: Alcoa Foundation, The Ambrose Monell Foundation, The Atlantic Philanthropies, Bristol-Myers Squibb Foundation, Open Society Institute, and The Starr Foundation. In addition, earnings from the MDRC Endowment help sustain our dis- semination efforts. Contributors to the MDRC Endowment include Alcoa Foundation, The Ambrose Monell Foundation, Anheuser-Busch Foundation, Bristol-Myers Squibb Foundation, Charles Stew- art Mott Foundation, Ford Foundation, The George Gund Foundation, The Grable Foundation, The Lizabeth and Frank Newman Charitable Foundation, The New York Times Company Foundation, Jan Nicholson, Paul H.
    [Show full text]
  • Introduction To" Social Experimentation"
    This PDF is a selection from an out-of-print volume from the National Bureau of Economic Research Volume Title: Social Experimentation Volume Author/Editor: Jerry A. Hausman and David A. Wise, eds. Volume Publisher: University of Chicago Press Volume ISBN: 0-226-31940-7 Volume URL: http://www.nber.org/books/haus85-1 Publication Date: 1985 Chapter Title: Introduction to "Social Experimentation" Chapter Author: Jerry A. Hausman, David A. Wise Chapter URL: http://www.nber.org/chapters/c8371 Chapter pages in book: (p. 1 - 10) Introduction Jerry A. Hausman and Davis A. Wise During the past decade the United States government has spent over 500 million dollars on social experiments. The experiments attempt to deter- mine the potential effect of a policy option by trying it out on a group of subjects, some of whom are randomly assigned to a treatment group and are the recipients of the proposed policy, while others are assigned to a control group. The difference in the outcomes for the two groups is the estimated effect of the policy option. This approach is an alternative to making judgments about the effect of the proposed policy from infer- ences based on observational (survey) data, but without the advantages of randomization. While a few social experiments have been conducted in the past, this development is a relatively new approach to the evaluation of the effect of proposed government policies. Much of the $500 million has gone into transfer payments to the experimental subjects, most of whom have benefited from the experiments. But the most important question is whether the experiments have been successful in their primary goal of providing precise estimates of the effects of a proposed govern- ment policy.
    [Show full text]
  • Methods for the Experimenting Society
    TRACES TRACES are what evaluators left behind—discoveries, records, tracks-which made marks on the profession of program evaluation. Published here are excerpts from our past (e.g., articles, passages from books, speeches) that show where we have been or affected where we are g(r)o(w)ing. Suggestions for inclusion should be sent to the Editor, along with rationale for their import. Photocopies of the original printed versions are preferred with full bibliographic information. Copying rights will be secured by the Editor. Editor’s Note: We are proud to present here a widely distributed but previously unpublished paper by Donald Campbell. After publication of his milestone paper, "Reforms as Experiments," in 1969 (American Psychologist, 24(4), 409-429), Campbell wrote a series of papers elaborating on his ideas for an experimenting society. "Methods for the Experimenting Society," printed here, was the basis for his 1971 "abbreviated and extemporaneous" presentations to the Eastern Psychological Association and the Ameri- can Psychological Association. In the paper, Campbell proposed that a few social scientists dedicate themselves to being methodologists for the experimenting society. He then recounted many of the problems that must be addressed and discussed possible solutions. In 1988, the 1971 draftwas revised and published in a selection of Campbell’s papers entitled Methodology and Epistemology for Social Science (edited by E. Samuel Overman and published by The University of Chicago Press). But the original version, here in EP, contains more detail on the methods. Certainly we can trace a great deal of our evaluation history to Dr. Campbell. We are grateful for his permission to publish the paper in EP.
    [Show full text]
  • A Reexamination of the Evidence from the Highscope Perry Preschool Program
    A Service of Leibniz-Informationszentrum econstor Wirtschaft Leibniz Information Centre Make Your Publications Visible. zbw for Economics Heckman, James; Moon, Seong Hyeok; Pinto, Rodrigo; Savelyev, Peter; Yavitz, Adam Article Analyzing social experiments as implemented: A reexamination of the evidence from the HighScope Perry Preschool Program Quantitative Economics Provided in Cooperation with: The Econometric Society Suggested Citation: Heckman, James; Moon, Seong Hyeok; Pinto, Rodrigo; Savelyev, Peter; Yavitz, Adam (2010) : Analyzing social experiments as implemented: A reexamination of the evidence from the HighScope Perry Preschool Program, Quantitative Economics, ISSN 1759-7331, Wiley, Hoboken, NJ, Vol. 1, Iss. 1, pp. 1-46, http://dx.doi.org/10.3982/QE8 This Version is available at: http://hdl.handle.net/10419/150304 Standard-Nutzungsbedingungen: Terms of use: Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Documents in EconStor may be saved and copied for your Zwecken und zum Privatgebrauch gespeichert und kopiert werden. personal and scholarly purposes. Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle You are not to copy documents for public or commercial Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich purposes, to exhibit the documents publicly, to make them machen, vertreiben oder anderweitig nutzen. publicly available on the internet, or to distribute or otherwise use the documents in public. Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, If the documents have been made available under an Open gelten abweichend von diesen Nutzungsbedingungen die in der dort Content Licence (especially Creative Commons Licences), you genannten Lizenz gewährten Nutzungsrechte. may exercise further usage rights as specified in the indicated licence.
    [Show full text]
  • The Entry of Randomized Assignment Into the Social Sciences
    WPS8062 Policy Research Working Paper 8062 Public Disclosure Authorized The Entry of Randomized Assignment into the Social Sciences Public Disclosure Authorized Julian C. Jamison Public Disclosure Authorized Public Disclosure Authorized Development Economics Vice Presidency Development Policy Department May 2017 Policy Research Working Paper 8062 Abstract Although the concept of randomized assignment to control introduced randomized control trials within a few years of for extraneous factors reaches back hundreds of years, the one another in the 1920s: agricultural science, clinical med- first empirical use appears to have been in an 1835 trial icine, educational psychology, and social policy (specifically of homeopathic medicine. Throughout the 19th century, political science). Randomized control trials brought more there was primarily a growing awareness of the need for rigor to fields that were in the process of expanding their careful comparison groups, albeit often without the real- purviews and focusing more on causal relationships. In the ization that randomization could be a particularly clean third phase, the 1950s through the 1970s saw a surge of method to achieve that goal. In the second and more crucial interest in more applied randomized experiments in eco- phase of this history, four separate but related disciplines nomics and elsewhere, in the lab and especially in the field. This paper is a product of the Development Policy Department, Development Economics Vice Presidency. It is part of a larger effort by the World Bank to provide open access to its research and make a contribution to development policy discussions around the world. Policy Research Working Papers are also posted on the Web at http://econ.worldbank.org.
    [Show full text]
  • Incorporating Welfare Into Randomized Controlled Trials
    EXPERIMENT-AS-MARKET: INCORPORATING WELFARE INTO RANDOMIZED CONTROLLED TRIALS By Yusuke Narita August 2019 Revised May 2019 COWLES FOUNDATION DISCUSSION PAPER NO. 2127R COWLES FOUNDATION FOR RESEARCH IN ECONOMICS YALE UNIVERSITY Box 208281 New Haven, Connecticut 06520-8281 http://cowles.yale.edu/ Experiment-as-Market: Incorporating Welfare into Randomized Controlled Trials∗ Yusuke Narita† May 10, 2019 Abstract Randomized Controlled Trials (RCTs) enroll hundreds of millions of subjects and in- volve many human lives. To improve subjects’ welfare, I propose a design of RCTs that I call Experiment-as-Market (EXAM). EXAM produces a Pareto efficient allocation of treatment assignment probabilities, is asymptotically incentive compatible for prefer- ence elicitation, and unbiasedly estimates any causal effect estimable with standard RCTs. I quantify these properties by applying EXAM to a water cleaning experiment in Kenya (Kremer et al., 2011). In this empirical setting, compared to standard RCTs, EXAM improves subjects’ predicted well-being while reaching similar treatment effect estimates with similar precision. Keywords: Social Experiment, Clinical Trial, A/B Test, Market Design, Competitive Equilibrium from Equal Income, Pareto Efficiency, Causal Inference, Development Economics ∗Presentation slides for this paper are available at https://www.dropbox.com/s/uvlgtxz45zehqtu/ EXAMslide90min.pdf?dl=0. I am grateful to Dean Karlan for a conversation that inspired this project; Jason Abaluck, Josh Angrist, Tim Armstrong, James Berry, Sylvain
    [Show full text]
  • Experimental Analysis of Neighborhood Effects
    Econometrica, Vol. 75, No. 1 (January, 2007), 83–119 EXPERIMENTAL ANALYSIS OF NEIGHBORHOOD EFFECTS BY JEFFREY R. KLING,JEFFREY B. LIEBMAN, AND LAWRENCE F. KATZ1 Families, primarily female-headed minority households with children, living in high- poverty public housing projects in five U.S. cities were offered housing vouchers by lottery in the Moving to Opportunity program. Four to seven years after random as- signment, families offered vouchers lived in safer neighborhoods that had lower poverty rates than those of the control group not offered vouchers. We find no significant over- all effects of this intervention on adult economic self-sufficiency or physical health. Mental health benefits of the voucher offers for adults and for female youth were sub- stantial. Beneficial effects for female youth on education, risky behavior, and physical health were offset by adverse effects for male youth. For outcomes that exhibit sig- nificant treatment effects, we find, using variation in treatment intensity across voucher types and cities, that the relationship between neighborhood poverty rate and outcomes is approximately linear. KEYWORDS: Social experiment, housing vouchers, neighborhoods, mental health, urban poverty. THE RESIDENTS OF DISADVANTAGED NEIGHBORHOODS fare substantially worse on a wide range of socioeconomic and health outcomes than do those with more affluent neighbors. Economic models of residential sorting— partially motivated by these observed associations between neighborhood characteristics and individual outcomes—suggest that inefficient equilibria can arise when individual outcomes are influenced by neighbors and individuals do not take their external effects on neighbors into account in their location deci- sions (e.g., Benabou (1993)). 1This paper integrates material previously circulated in Kling and Liebman (2004), Kling, Liebman, Katz, and Sanbonmatsu (2004), and Liebman, Katz, and Kling (2004).
    [Show full text]
  • Evaluating the Methodology of $ Ocfal Experiments
    Evaluating the Methodology of $ocfal Experiments Arnold Zellner and Peter E. Rossi* In view of the many papers and books that have been written analyzing the methodology of the income maintenance experiments as well as other social experiments, it is indeed difficult to say anything entirely new. However, we shall emphasize what we consider to be im- portant, basic points in the planning, execution and evaluation of social experiments that may prove useful in future experiments. The plan of the paper is as follows. In the next section, we put forward considera- tions relevant for evaluating social experiments. We then take up design issues within the context of static designs, while the following section is devoted to issues that arise in dynamic contexts, the usual setting for most social experiments. Suggestions for linking social experiments to already existing longitudinal data bases are presented and discussed. In both static and dynamic contexts, we discuss the roles of models, whether statistical or structural, and of randomization. Design for prediction of relevant experimental outcomes is emphasized and illus- trated in terms of simplified versions of the negative income tax experi- ments. Finally, we present a summary and some concluding remarks. Considerations Relevant for Evaluating the Methodology of Social Experiments Since social experiments usually involve the expenditure of millions of dollars, resources that have alternative research uses and potentially great social value, it is critical that the experiments be conducted in a *Professor of Economics and Statistics and Assistant Professor of Econometrics and Statistics, respectively, Graduate School of Business, University of Chicago. Michael A.
    [Show full text]
  • The Experimental Approach to Development Economics
    The Experimental Approach to Development Economics Abhijit V. Banerjee and Esther Duflo Department of Economics and Abdul Latif Jameel Poverty Action Lab, Massachusetts Institute of Technology, Cambridge, Massachusetts 02142; email: [email protected], [email protected] Annu. Rev. Econ. 2009. 1:151–78 Key Words First published online as a Review in Advance on randomized experiments, development economics, program April 21, 2009 evaluation The Annual Review of Economics is online at econ.annualreviews.org Abstract Annu. Rev. Econ. 2009.1:151-178. Downloaded from www.annualreviews.org This article’s doi: Randomized experiments have become a popular tool in develop- 10.1146/annurev.economics.050708.143235 ment economics research and have been the subject of a number of Copyright © 2009 by Annual Reviews. criticisms. This paper reviews the recent literature and discusses the Access provided by Massachusetts Institute of Technology (MIT) on 10/22/15. For personal use only. All rights reserved strengths and limitations of this approach in theory and in practice. 1941-1383/09/0904-0151$20.00 We argue that the main virtue of randomized experiments is that, owing to the close collaboration between researchers and implemen- ters, they allow the estimation of parameters that would not other- wise be possible to evaluate. We discuss the concerns that have been raised regarding experiments and generally conclude that, although real, they are often not specific to experiments. We conclude by dis- cussing the relationship between theory and experiments. 151 1. INTRODUCTION The past few years have seen a veritable explosion of randomized experiments in develop- ment economics. At the fall 2008 NEUDC conference, a large conference in development economics attended mainly by young researchers and PhD students, 24 papers reported on randomized field experiments, out of the 112 papers that used microeconomics data (laboratory experiments excluded).
    [Show full text]