[go: up one dir, main page]
IDEAS home Printed from https://ideas.repec.org/p/ces/ceswps/_9064.html
   My bibliography  Save this paper

When Should We (Not) Interpret Linear IV Estimands as LATE?

Author

Listed:
  • Tymon Sloczynski
Abstract
In this paper I revisit the interpretation of the linear instrumental variables (IV) estimand as a weighted average of conditional local average treatment effects (LATEs). I focus on a practically relevant situation in which additional covariates are required for identification while the reduced-form and first-stage regressions implicitly restrict the effects of the instrument to be homogeneous, and are thus possibly misspecified. I show that the weights on some conditional LATEs are negative and the IV estimand is no longer interpretable as a causal effect under a weaker version of monotonicity, i.e. when there are compliers but no defiers at some covariate values and defiers but no compliers elsewhere. The problem of negative weights disappears in the overidentified specification of Angrist and Imbens (1995) and in an alternative method, termed “reordered IV,” that I also develop. Even if all weights are positive, the IV estimand in the just identified specification is not interpretable as the unconditional LATE parameter unless the groups with different values of the instrument are roughly equal sized. I illustrate my findings in an application to causal effects of college education using the college proximity instrument. The benchmark estimates suggest that college attendance yields earnings gains of about 60 log points, which is well outside the range of estimates in the recent literature. I demonstrate that this result is driven by the existence of defiers and the presence of negative weights. Corrected estimates indicate that attending college causes earnings to be roughly 20% higher.

Suggested Citation

  • Tymon Sloczynski, 2021. "When Should We (Not) Interpret Linear IV Estimands as LATE?," CESifo Working Paper Series 9064, CESifo.
    • Handle: RePEc:ces:ceswps:_9064
    as

    Download full text from publisher

    File URL: https://www.cesifo.org/DocDL/cesifo1_wp9064.pdf
    Download Restriction: no
    ---><---

    Other versions of this item:

    References listed on IDEAS

    as
    1. Hoderlein, Stefan & Holzmann, Hajo & Meister, Alexander, 2017. "The triangular model with random coefficients," Journal of Econometrics, Elsevier, vol. 201(1), pages 144-169.
    2. James J. Heckman & Sergio Urzua & Edward Vytlacil, 2006. "Understanding Instrumental Variables in Models with Essential Heterogeneity," The Review of Economics and Statistics, MIT Press, vol. 88(3), pages 389-432, August.
    3. Gautier, Eric & Hoderlein, Stefan, 2011. "A triangular treatment effect model with random coefficients in the selection equation," TSE Working Papers 15-598, Toulouse School of Economics (TSE), revised 25 Aug 2015.
    4. Martin Nybom, 2017. "The Distribution of Lifetime Earnings Returns to College," Journal of Labor Economics, University of Chicago Press, vol. 35(4), pages 903-952.
    5. Frölich, Markus & Lechner, Michael, 2010. "Exploiting Regional Treatment Intensity for the Evaluation of Labor Market Policies," Journal of the American Statistical Association, American Statistical Association, vol. 105(491), pages 1014-1029.
    6. Stephen V. Cameron & Christopher Taber, 2004. "Estimation of Educational Borrowing Constraints Using Returns to Schooling," Journal of Political Economy, University of Chicago Press, vol. 112(1), pages 132-182, February.
    7. Clément de Chaisemartin, 2017. "Tolerating defiance? Local average treatment effects without monotonicity," Quantitative Economics, Econometric Society, vol. 8(2), pages 367-396, July.
    8. Thomas J. Kane & Cecilia Rouse, 1993. "Labor Market Returns to Two- And Four-Year College: Is A Credit a Credit And Do Degrees Matter?," Working Papers 690, Princeton University, Department of Economics, Industrial Relations Section..
    9. Jack Mountjoy, 2022. "Community Colleges and Upward Mobility," American Economic Review, American Economic Association, vol. 112(8), pages 2580-2630, August.
    10. Philipp Eisenhauer & James J. Heckman & Edward Vytlacil, 2015. "The Generalized Roy Model and the Cost-Benefit Analysis of Social Programs," Journal of Political Economy, University of Chicago Press, vol. 123(2), pages 413-443.
    11. James J. Heckman & Edward Vytlacil, 2005. "Structural Equations, Treatment Effects, and Econometric Policy Evaluation," Econometrica, Econometric Society, vol. 73(3), pages 669-738, May.
    12. Pedro Carneiro & James J. Heckman & Edward J. Vytlacil, 2011. "Estimating Marginal Returns to Education," American Economic Review, American Economic Association, vol. 101(6), pages 2754-2781, October.
    13. Kling, Jeffrey R, 2001. "Interpreting Instrumental Variables Estimates of the Returns to Schooling," Journal of Business & Economic Statistics, American Statistical Association, vol. 19(3), pages 358-364, July.
    14. Stephen G. Donald & Yu-Chin Hsu & Robert P. Lieli, 2014. "Testing the Unconfoundedness Assumption via Inverse Probability Weighted Estimators of (L)ATT," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 32(3), pages 395-415, July.
    15. Lance Lochner & Enrico Moretti, 2015. "Estimating and Testing Models with Many Treatment Levels and Limited Instruments," The Review of Economics and Statistics, MIT Press, vol. 97(2), pages 387-397, May.
    16. Angrist, Joshua D, 1990. "Lifetime Earnings and the Vietnam Era Draft Lottery: Evidence from Social Security Administrative Records: Errata," American Economic Review, American Economic Association, vol. 80(5), pages 1284-1286, December.
    17. Christopher R. Walters, 2018. "The Demand for Effective Charter Schools," Journal of Political Economy, University of Chicago Press, vol. 126(6), pages 2179-2223.
    18. Thomas J. Kane & Cecilia E. Rouse, 1993. "Labor Market Returns to Two- and Four-Year Colleges: Is a Credit a Credit and Do Degrees Matter?," NBER Working Papers 4268, National Bureau of Economic Research, Inc.
    19. Angrist, Joshua D, 1990. "Lifetime Earnings and the Vietnam Era Draft Lottery: Evidence from Social Security Administrative Records," American Economic Review, American Economic Association, vol. 80(3), pages 313-336, June.
    20. Toru Kitagawa, 2015. "A Test for Instrument Validity," Econometrica, Econometric Society, vol. 83(5), pages 2043-2063, September.
    21. Jonathan Smith & Joshua Goodman & Michael Hurwitz, 2020. "The Economic Impact of Access to Public Four-Year Colleges," NBER Working Papers 27177, National Bureau of Economic Research, Inc.
    22. Joshua D. Angrist & Jörn-Steffen Pischke, 2009. "Mostly Harmless Econometrics: An Empiricist's Companion," Economics Books, Princeton University Press, edition 1, number 8769.
    23. Peter Z. Schochet & John Burghardt & Sheena McConnell, 2008. "Does Job Corps Work? Impact Findings from the National Job Corps Study," American Economic Review, American Economic Association, vol. 98(5), pages 1864-1886, December.
    24. Shoya Ishimaru, 2024. "Empirical Decomposition of the IV-OLS Gap with Heterogeneous and Nonlinear Effects," The Review of Economics and Statistics, MIT Press, vol. 106(2), pages 505-520, March.
    25. Seth D. Zimmerman, 2014. "The Returns to College Admission for Academically Marginal Students," Journal of Labor Economics, University of Chicago Press, vol. 32(4), pages 711-754.
    26. repec:mpr:mprres:6097 is not listed on IDEAS
    27. Imbens, Guido W & Angrist, Joshua D, 1994. "Identification and Estimation of Local Average Treatment Effects," Econometrica, Econometric Society, vol. 62(2), pages 467-475, March.
    28. Abadie, Alberto, 2003. "Semiparametric instrumental variable estimation of treatment response models," Journal of Econometrics, Elsevier, vol. 113(2), pages 231-263, April.
    29. Huntington-Klein Nick, 2020. "Instruments with Heterogeneous Effects: Bias, Monotonicity, and Localness," Journal of Causal Inference, De Gruyter, vol. 8(1), pages 182-208, January.
    30. Peter M. Aronow & Cyrus Samii, 2016. "Does Regression Produce Representative Estimates of Causal Effects?," American Journal of Political Science, John Wiley & Sons, vol. 60(1), pages 250-267, January.
    31. Thomas J. Kane & Cecilia E. Rouse, 1993. "Labor Market Returns to Two- And Four-Year College: Is a Credit a Credit And Do Degrees Matter?," Working Papers 690, Princeton University, Department of Economics, Industrial Relations Section..
    32. Mark Hoekstra, 2009. "The Effect of Attending the Flagship State University on Earnings: A Discontinuity-Based Approach," The Review of Economics and Statistics, MIT Press, vol. 91(4), pages 717-724, November.
    33. David S. Lee, 2009. "Training, Wages, and Sample Selection: Estimating Sharp Bounds on Treatment Effects," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 76(3), pages 1071-1102.
    34. Han Hong & Denis Nekipelov, 2010. "Semiparametric efficiency in nonlinear LATE models," Quantitative Economics, Econometric Society, vol. 1(2), pages 279-304, November.
    35. Rouse, Cecilia Elena, 1995. "Democratization or Diversion? The Effect of Community Colleges on Educational Attainment," Journal of Business & Economic Statistics, American Statistical Association, vol. 13(2), pages 217-224, April.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Attar, Itay & Cohen-Zada, Danny & Elder, Todd E., 2024. "Measuring and Correcting Monotonicity Bias: The Case of School Entrance Age Effects," IZA Discussion Papers 17088, Institute of Labor Economics (IZA).
    2. Tymon Sloczynski & S. Derya Uysal & Jeffrey M. Wooldridge & Derya Uysal, 2022. "Doubly Robust Estimation of Local Average Treatment Effects Using Inverse Probability Weighted Regression Adjustment," CESifo Working Paper Series 10105, CESifo.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Tymon S{l}oczy'nski, 2020. "When Should We (Not) Interpret Linear IV Estimands as LATE?," Papers 2011.06695, arXiv.org, revised Oct 2024.
    2. Cornelissen, Thomas & Dustmann, Christian & Raute, Anna & Schönberg, Uta, 2016. "From LATE to MTE: Alternative methods for the evaluation of policy interventions," Labour Economics, Elsevier, vol. 41(C), pages 47-60.
    3. Federica Braccioli & Paolo Ghinetti & Simone Moriconi & Costanza Naguib & Michele Pellizzari, 2023. "Education Expansion, College Choice and Labour Market Success," CESifo Working Paper Series 10842, CESifo.
    4. Federica Braccioli & Paolo Ghinetti & Simone Moriconi & Costanza Naguib & Michele Pellizzari, 2023. "Education Expansion, College Choice and Labour Market Success," CESifo Working Paper Series 10842, CESifo.
    5. Phillip Heiler, 2020. "Efficient Covariate Balancing for the Local Average Treatment Effect," Papers 2007.04346, arXiv.org.
    6. Huber, Martin & Wüthrich, Kaspar, 2017. "Evaluating local average and quantile treatment effects under endogeneity based on instruments: a review," FSES Working Papers 479, Faculty of Economics and Social Sciences, University of Freiburg/Fribourg Switzerland.
    7. Sokbae Lee & Bernard Salanié, 2018. "Identifying Effects of Multivalued Treatments," Econometrica, Econometric Society, vol. 86(6), pages 1939-1963, November.
    8. Sloczynski, Tymon, 2018. "A General Weighted Average Representation of the Ordinary and Two-Stage Least Squares Estimands," IZA Discussion Papers 11866, Institute of Labor Economics (IZA).
    9. Peter Hull & Michal Kolesár & Christopher Walters, 2022. "Labor by design: contributions of David Card, Joshua Angrist, and Guido Imbens," Scandinavian Journal of Economics, Wiley Blackwell, vol. 124(3), pages 603-645, July.
    10. Tymon S{l}oczy'nski, 2018. "Interpreting OLS Estimands When Treatment Effects Are Heterogeneous: Smaller Groups Get Larger Weights," Papers 1810.01576, arXiv.org, revised May 2020.
    11. Laura Schmitz, 2022. "Heterogeneous Effects of After-School Care on Child Development," Discussion Papers of DIW Berlin 2006, DIW Berlin, German Institute for Economic Research.
    12. Joshua D. Angrist, 2022. "Empirical Strategies in Economics: Illuminating the Path From Cause to Effect," Econometrica, Econometric Society, vol. 90(6), pages 2509-2539, November.
    13. Nobuyoshi Kikuchi, 2017. "Marginal Returns to Schooling and Education Policy Change in Japan," ISER Discussion Paper 0996r, Institute of Social and Economic Research, Osaka University, revised Oct 2017.
    14. Kédagni, Désiré, 2023. "Identifying treatment effects in the presence of confounded types," Journal of Econometrics, Elsevier, vol. 234(2), pages 479-511.
    15. Black, Dan A. & Joo, Joonhwi & LaLonde, Robert & Smith, Jeffrey A. & Taylor, Evan J., 2022. "Simple Tests for Selection: Learning More from Instrumental Variables," Labour Economics, Elsevier, vol. 79(C).
    16. Thomas Carr & Toru Kitagawa, 2021. "Testing Instrument Validity with Covariates," Papers 2112.08092, arXiv.org, revised Sep 2023.
    17. Acton, Riley & Cortes, Kalena E. & Miller, Lois & Morales, Camila, 2024. "Distance to Degrees: How College Proximity Shapes Students' Enrollment Choices and Attainment across Race-Ethnicity and Socioeconomic Status," IZA Discussion Papers 17338, Institute of Labor Economics (IZA).
    18. Nobuyoshi Kikuchi, 2017. "Marginal Returns to Schooling and Education Policy Change in Japan," ISER Discussion Paper 0996, Institute of Social and Economic Research, Osaka University.
    19. Heckman, James J. & Humphries, John Eric & Veramendi, Gregory, 2016. "Dynamic treatment effects," Journal of Econometrics, Elsevier, vol. 191(2), pages 276-292.
    20. Federica Braccioli & Paolo Ghinetti & Simone Moriconi & Michele Pellizzari & Costanza Naguib, 2022. "Education expansion, college choice and labour market success," Diskussionsschriften dp2207, Universitaet Bern, Departement Volkswirtschaft.

    More about this item

    Keywords

    causal interpretability; instrumental variables; local average treatment effect; model misspecification; monotonicity; treatment effect heterogeneity; two-stage least squares;
    All these keywords.

    JEL classification:

    • C21 - Mathematical and Quantitative Methods - - Single Equation Models; Single Variables - - - Cross-Sectional Models; Spatial Models; Treatment Effect Models
    • C25 - Mathematical and Quantitative Methods - - Single Equation Models; Single Variables - - - Discrete Regression and Qualitative Choice Models; Discrete Regressors; Proportions; Probabilities
    • C26 - Mathematical and Quantitative Methods - - Single Equation Models; Single Variables - - - Instrumental Variables (IV) Estimation
    • I26 - Health, Education, and Welfare - - Education - - - Returns to Education

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:ces:ceswps:_9064. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Klaus Wohlrabe (email available below). General contact details of provider: https://edirc.repec.org/data/cesifde.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.