Annals of Applied Statistics
- Ann. Appl. Stat.
- Volume 7, Number 1 (2013), 295-318.
Agnostic notes on regression adjustments to experimental data: Reexamining Freedman’s critique
Full-text: Open access
Abstract
Freedman [Adv. in Appl. Math. 40 (2008) 180–193; Ann. Appl. Stat. 2 (2008) 176–196] critiqued ordinary least squares regression adjustment of estimated treatment effects in randomized experiments, using Neyman’s model for randomization inference. Contrary to conventional wisdom, he argued that adjustment can lead to worsened asymptotic precision, invalid measures of precision, and small-sample bias. This paper shows that in sufficiently large samples, those problems are either minor or easily fixed. OLS adjustment cannot hurt asymptotic precision when a full set of treatment–covariate interactions is included. Asymptotically valid confidence intervals can be constructed with the Huber–White sandwich standard error estimator. Checks on the asymptotic approximations are illustrated with data from Angrist, Lang, and Oreopoulos’s [Am. Econ. J.: Appl. Econ. 1:1 (2009) 136–163] evaluation of strategies to improve college students’ achievement. The strongest reasons to support Freedman’s preference for unadjusted estimates are transparency and the dangers of specification search.
Article information
Source
Ann. Appl. Stat., Volume 7, Number 1 (2013), 295-318.
Dates
First available in Project Euclid: 9 April 2013
Permanent link to this document
https://projecteuclid.org/euclid.aoas/1365527200
Digital Object Identifier
doi:10.1214/12-AOAS583
Mathematical Reviews number (MathSciNet)
MR3086420
Zentralblatt MATH identifier
06171273
Keywords
Analysis of covariance covariate adjustment randomization inference sandwich estimator robust standard errors social experiments program evaluation
Citation
Lin, Winston. Agnostic notes on regression adjustments to experimental data: Reexamining Freedman’s critique. Ann. Appl. Stat. 7 (2013), no. 1, 295--318. doi:10.1214/12-AOAS583. https://projecteuclid.org/euclid.aoas/1365527200
References
- Angrist, J. D. and Imbens, G. W. (2002). Comment on “Covariance adjustment in randomized experiments and observational studies” by P. R. Rosenbaum. Statist. Sci. 17 304–307.Mathematical Reviews (MathSciNet): MR1962487
Digital Object Identifier: doi:10.1214/ss/1042727942
Project Euclid: euclid.ss/1042727942 - Angrist, J. D., Lang, D. and Oreopoulos, P. (2009). Incentives and services for college achievement: Evidence from a randomized trial. Am. Econ. J.: Appl. Econ. 1 136–163.
- Angrist, J. D. and Pischke, J. S. (2009). Mostly Harmless Econometrics: An Empiricist’s Companion. Princeton Univ. Press, Princeton.Zentralblatt MATH: 1159.62090
- Ashenfelter, O. and Plant, M. W. (1990). Nonparametric estimates of the labor-supply effects of negative income tax programs. J. Labor Econ. 8 S396–S415.
- Berk, R., Barnes, G., Ahlman, L. and Kurtz, E. (2010). When second best is good enough: A comparison between a true experiment and a regression discontinuity quasi-experiment. J. Exp. Criminol. 6 191–208.
- Chamberlain, G. (1982). Multivariate regression models for panel data. J. Econometrics 18 5–46.Mathematical Reviews (MathSciNet): MR661664
Zentralblatt MATH: 0512.62115
Digital Object Identifier: doi:10.1016/0304-4076(82)90094-X - Chung, E. Y. and Romano, J. P. (2011a). Exact and asymptotically robust permutation tests. Technical Report 2011-05, Dept. Statistics, Stanford Univ.
- Chung, E. Y. and Romano, J. P. (2011b). Asymptotically valid and exact permutation tests based on two-sample $U$-statistics. Technical Report 2011-09, Dept. Statistics, Stanford Univ.
- Cochran, W. G. (1942). Sampling theory when the sampling-units are of unequal sizes. J. Amer. Statist. Assoc. 37 199–212.Mathematical Reviews (MathSciNet): MR6671
Zentralblatt MATH: 0063.00937
Digital Object Identifier: doi:10.1080/01621459.1942.10500626 - Cochran, W. G. (1957). Analysis of covariance: Its nature and uses. Biometrics 13 261–281.
- Cochran, W. G. (1969). The use of covariance in observational studies. J. R. Stat. Soc. Ser. C. Appl. Stat. 18 270–275.
- Cochran, W. G. (1977). Sampling Techniques, 3rd ed. Wiley, New York.Mathematical Reviews (MathSciNet): MR474575
- Cox, D. R. and McCullagh, P. (1982). Some aspects of analysis of covariance. Biometrics 38 541–561.
- Cox, D. R. and Reid, N. (2000). The Theory of the Design of Experiments. CRC Press, Boca Raton, FL.Zentralblatt MATH: 1009.62061
- Davidson, R. and MacKinnon, J. G. (1993). Estimation and Inference in Econometrics. Oxford Univ. Press, New York.
- Davison, A. C. and Hinkley, D. V. (1997). Bootstrap Methods and Their Application. Cambridge Series in Statistical and Probabilistic Mathematics 1. Cambridge Univ. Press, Cambridge.
- Deaton, A. (2010). Instruments, randomization, and learning about development. J. Econ. Lit. 48 424–455.
- Eicker, F. (1967). Limit theorems for regressions with unequal and dependent errors. In Proc. Fifth Berkeley Sympos. Math. Statist. and Probability (Berkeley, Calif., 1965/66), Vol. I 59–82. Univ. California Press, Berkeley, CA.
- Fienberg, S. E. and Tanur, J. M. (1987). Experimental and sampling structures: Parallels diverging and meeting. Internat. Statist. Rev. 55 75–96.
- Fisher, R. A. (1932). Statistical Methods for Research Workers, 4th ed. Oliver and Boyd, Edinburgh.
- Fisher, R. A. (1935). The Design of Experiments. Oliver and Boyd, Edinburgh.
- Freedman, D. A. (1991). Statistical models and shoe leather (with discussion). Socio. Meth. 21 291–358.
- Freedman, D. A. (2006). On the so-called “Huber sandwich estimator” and “robust standard errors”. Amer. Statist. 60 299–302.Mathematical Reviews (MathSciNet): MR2291297
Digital Object Identifier: doi:10.1198/000313006X152207 - Freedman, D. A. (2008a). On regression adjustments to experimental data. Adv. in Appl. Math. 40 180–193.Mathematical Reviews (MathSciNet): MR2388610
Zentralblatt MATH: 1130.62003
Digital Object Identifier: doi:10.1016/j.aam.2006.12.003 - Freedman, D. A. (2008b). On regression adjustments in experiments with several treatments. Ann. Appl. Stat. 2 176–196.Mathematical Reviews (MathSciNet): MR2415599
Zentralblatt MATH: 1144.62027
Digital Object Identifier: doi:10.1214/07-AOAS143
Project Euclid: euclid.aoas/1206367817 - Freedman, D. A. (2008c). Editorial: Oasis or mirage? Chance 21(1) 59–61. Annotated references at http://www.stat.berkeley.edu/~census/chance.pdf.Mathematical Reviews (MathSciNet): MR2422783
Digital Object Identifier: doi:10.1007/s00144-008-0047-x - Freedman, D. A. (2010). Survival analysis: An epidemiological hazard? In Statistical Models and Causal Inference: A Dialogue with the Social Sciences (D. Collier, J. S. Sekhon and P. B. Stark, eds.) 169–192. Cambridge Univ. Press, Cambridge.
- Freedman, D. A., Pisani, R. and Purves, R. (2007). Statistics, 4th ed. Norton, New York.
- Fuller, W. A. (1975). Regression analysis for sample survey. Sankhyā Ser. C 37 117–132.
- Fuller, W. A. (2002). Regression estimation for survey samples. Surv. Meth. 28 5–23.
- Fuller, W. A. (2009). Sampling Statistics. Wiley, Hoboken, NJ.Zentralblatt MATH: 1179.62019
- Gail, M. H., Mark, S. D., Carroll, R. J., Green, S. B. and Pee, D. (1996). On design considerations and randomization-based inference for community intervention trials. Stat. Med. 15 1069–1092.
- Green, D. P. and Aronow, P. M. (2011). Analyzing experimental data using regression: When is bias a practical concern? Working paper, Yale Univ.
- Greenberg, D. and Shroder, M. (2004). The Digest of Social Experiments, 3rd ed. Urban Institute Press, Washington, DC.
- Hansen, B. B. and Bowers, J. (2009). Attributing effects to a cluster-randomized get-out-the-vote campaign. J. Amer. Statist. Assoc. 104 873–885.Mathematical Reviews (MathSciNet): MR2562000
Digital Object Identifier: doi:10.1198/jasa.2009.ap06589 - Hinkley, D. V. (1977). Jacknifing in unbalanced situations. Technometrics 19 285–292.Mathematical Reviews (MathSciNet): MR458734
Digital Object Identifier: doi:10.1080/00401706.1977.10489550 - Hinkley, D. V. and Wang, S. (1991). Efficiency of robust standard errors for regression coefficients. Comm. Statist. Theory Methods 20 1–11.Mathematical Reviews (MathSciNet): MR1114631
Digital Object Identifier: doi:10.1080/03610929108830479 - Holland, P. W. (1986). Statistics and causal inference. J. Amer. Statist. Assoc. 81 945–970.Mathematical Reviews (MathSciNet): MR867618
Zentralblatt MATH: 0607.62001
Digital Object Identifier: doi:10.1080/01621459.1986.10478354 - Holt, D. and Smith, T. M. F. (1979). Post stratification. J. Roy. Statist. Soc. Ser. A 142 33–46.
- Huber, P. J. (1967). The behavior of maximum likelihood estimates under nonstandard conditions. In Proc. Fifth Berkeley Sympos. Math. Statist. and Probability (Berkeley, Calif., 1965/66), Vol. I: Statistics 221–233. Univ. California Press, Berkeley, CA.
- Imbens, G. W. (2010). Better LATE than nothing: Some comments on Deaton (2009) and Heckman and Urzua (2009). J. Econ. Lit. 48 399–423.
- Imbens, G. W. and Wooldridge, J. M. (2009). Recent developments in the econometrics of program evaluation. J. Econ. Lit. 47 5–86.
- Klar, N. and Darlington, G. (2004). Methods for modelling change in cluster randomization trials. Stat. Med. 23 2341–2357.
- Kline, P. (2011). Oaxaca–Blinder as a reweighting estimator. Am. Econ. Rev. 101(3) 532–537.
- Kline, P. and Santos, A. (2012). Higher order properties of the wild bootstrap under misspecification. J. Econometrics 171 54–70.Mathematical Reviews (MathSciNet): MR2970336
Digital Object Identifier: doi:10.1016/j.jeconom.2012.06.001 - Lin, W. (2013). Supplement to “Agnostic notes on regression adjustments to experimental data: Reexamining Freedman’s critique.” DOI:10.1214/12-AOAS583SUPP.
- Lin, W., Robins, P. K., Card, D., Harknett, K. and Lui-Gurr, S. (1998). When Financial Incentives Encourage Work: Complete 18-Month Findings from the Self-Sufficiency Project. Social Research and Demonstration Corp., Ottawa.
- Lumley, T. (2010). Complex Surveys: A Guide to Analysis Using R. Wiley, Hoboken, NJ.
- MacKinnon, J. G. (2013). Thirty years of heteroskedasticity-robust inference. In Recent Advances and Future Directions in Causality, Prediction, and Specification Analysis: Essays in Honor of Halbert L. White Jr. (X. Chen and N. R. Swanson, eds.) 437–461. Springer, New York.
- MacKinnon, J. G. and White, H. (1985). Some heteroskedasticity-consistent covariance matrix estimators with improved finite sample properties. J. Econometrics 29 305–325.
- Meyer, B. D. (1995). Lessons from the U.S. unemployment insurance experiments. J. Econ. Lit. 33 91–131.
- Middleton, J. A. and Aronow, P. M. (2012). Unbiased estimation of the average treatment effect in cluster-randomized experiments. Working Paper, Yale Univ.
- Miller, R. G. Jr. (1986). Beyond ANOVA, Basics of Applied Statistics. Wiley, New York.
- Miratrix, L. W., Sekhon, J. S. and Yu, B. (2012). Adjusting treatment effect estimates by post-stratification in randomized experiments. J. R. Stat. Soc. Ser. B. Stat. Methodol. 75 369–396.
- Moher, D., Hopewell, S. and Schulz, K. F. et al. (2010). CONSORT 2010 explanation and elaboration: Updated guidelines for reporting parallel group randomised trials. BMJ 340 c869.
- Neyman, J. (1923). On the application of probability theory to agricultural experiments. Essay on principles. Section 9. Ann. Agric. Sci. 101–151 (in Polish). [Reprinted in English with discussion by T. Speed and D. B. Rubin in Statist. Sci. 5 (1990) 463–480. MR1092986]
- Raudenbush, S. W. (1997). Statistical analysis and optimal design for cluster randomized trials. Psychol. Meth. 2 173–185.
- Reichardt, C. S. and Gollob, H. F. (1999). Justifying the use and increasing the power of a $t$ test for a randomized experiment with a convenience sample. Psychol. Meth. 4 117–128.
- Rosenbaum, P. R. (2002). Covariance adjustment in randomized experiments and observational studies. Statist. Sci. 17 286–327.Mathematical Reviews (MathSciNet): MR1962487
Digital Object Identifier: doi:10.1214/ss/1042727942
Project Euclid: euclid.ss/1042727942 - Rosenbaum, P. R. (2010). Design of Observational Studies. Springer, New York.
- Royall, R. M. and Cumberland, W. G. (1978). Variance estimation in finite population sampling. J. Amer. Statist. Assoc. 73 351–358.Mathematical Reviews (MathSciNet): MR501487
Zentralblatt MATH: 0437.62014
Digital Object Identifier: doi:10.1080/01621459.1978.10481581 - Rubin, D. B. (1974). Estimating causal effects of treatments in randomized and nonrandomized studies. J. Educ. Psychol. 66 688–701.
- Rubin, D. B. (1984). William G. Cochran’s contributions to the design, analysis, and evaluation of observational studies. In W. G. Cochran’s Impact on Statistics (P. S. R. S. Rao andJ. Sedransk, eds.) 37–69. Wiley, New York.Mathematical Reviews (MathSciNet): MR758447
- Rubin, D. B. (2005). Causal inference using potential outcomes: Design, modeling, decisions. J. Amer. Statist. Assoc. 100 322–331.Mathematical Reviews (MathSciNet): MR2166071
Zentralblatt MATH: 1117.62418
Digital Object Identifier: doi:10.1198/016214504000001880 - Rubin, D. B. and van der Laan, M. J. (2011). Targeted ANCOVA estimator in RCTs. In Targeted Learning: Causal Inference for Observational and Experimental Data (M. J. van der Laan and S. Rose, eds.) 201–215. Springer, New York.Mathematical Reviews (MathSciNet): MR2867124
Digital Object Identifier: doi:10.1007/978-1-4419-9782-1_12 - Samii, C. and Aronow, P. M. (2012). On equivalencies between design-based and regression-based variance estimators for randomized experiments. Statist. Probab. Lett. 82 365–370.Mathematical Reviews (MathSciNet): MR2875224
- Schochet, P. Z. (2010). Is regression adjustment supported by the Neyman model for causal inference? J. Statist. Plann. Inference 140 246–259.Mathematical Reviews (MathSciNet): MR2568136
Zentralblatt MATH: 1178.62079
Digital Object Identifier: doi:10.1016/j.jspi.2009.07.008 - Senn, S. J. (1989). Covariate imbalance and random allocation in clinical trials. Stat. Med. 8 467–475.
- Stock, J. H. (2010). The other transformation in econometric practice: Robust tools for inference. J. Econ. Perspect. 24(2) 83–94.
- Stonehouse, J. M. and Forrester, G. J. (1998). Robustness of the $t$ and $U$ tests under combined assumption violations. J. Appl. Stat. 25 63–74.
- Tibshirani, R. (1986). Discussion of “Jackknife, bootstrap and other resampling methods in regression analysis” by C. F. J. Wu. Ann. Statist. 14 1335–1339. [Correction: (1988) 16 479.]
- Tsiatis, A. A., Davidian, M., Zhang, M. and Lu, X. (2008). Covariate adjustment for two-sample treatment comparisons in randomized clinical trials: A principled yet flexible approach. Stat. Med. 27 4658–4677.
- Tukey, J. W. (1991). Use of many covariates in clinical trials. Internat. Statist. Rev. 59 123–137.
- Tukey, J. W. (1993). Tightening the clinical trial. Contr. Clin. Trials 14 266–285.
- Watson, D. J. (1937). The estimation of leaf area in field crops. J. Agr. Sci. 27 474–483.
- Welch, B. L. (1949). Further note on Mrs. Aspin’s tables and on certain approximations to the tabled function. Biometrika 36 293–296.
- White, H. (1980a). Using least squares to approximate unknown regression functions. Internat. Econom. Rev. 21 149–170.Mathematical Reviews (MathSciNet): MR572464
Zentralblatt MATH: 0444.62119
Digital Object Identifier: doi:10.2307/2526245 - White, H. (1980b). A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity. Econometrica 48 817–838.
- Wu, C. F. J. (1986). Jackknife, bootstrap and other resampling methods in regression analysis. Ann. Statist. 14 1261–1350.Mathematical Reviews (MathSciNet): MR868303
Zentralblatt MATH: 0618.62072
Digital Object Identifier: doi:10.1214/aos/1176350142
Project Euclid: euclid.aos/1176350142 - Yang, L. and Tsiatis, A. A. (2001). Efficiency study of estimators for a treatment effect in a pretest-posttest trial. Amer. Statist. 55 314–321.Mathematical Reviews (MathSciNet): MR1943328
Zentralblatt MATH: 1182.62069
Digital Object Identifier: doi:10.1198/000313001753272466
Supplemental materials
- Supplementary material: Proofs. Proofs of theorems, corollaries, and selected remarks.Digital Object Identifier: doi:10.1214/12-AOAS583SUPP

- You have access to this content.
- You have partial access to this content.
- You do not have access to this content.
More like this
- Divide and conquer in nonstandard problems and the super-efficiency phenomenon
Banerjee, Moulinath, Durot, Cécile, and Sen, Bodhisattva, Annals of Statistics, 2019 - The Effect of Serial Correlation on Tests for Parameter Change at Unknown Time
Tang, S. M. and MacNeill, I. B., Annals of Statistics, 1993 - The sensitivity of linear regression coefficients’ confidence limits to the omission of a confounder
Hosman, Carrie A., Hansen, Ben B., and Holland, Paul W., Annals of Applied Statistics, 2010
- Divide and conquer in nonstandard problems and the super-efficiency phenomenon
Banerjee, Moulinath, Durot, Cécile, and Sen, Bodhisattva, Annals of Statistics, 2019 - The Effect of Serial Correlation on Tests for Parameter Change at Unknown Time
Tang, S. M. and MacNeill, I. B., Annals of Statistics, 1993 - The sensitivity of linear regression coefficients’ confidence limits to the omission of a confounder
Hosman, Carrie A., Hansen, Ben B., and Holland, Paul W., Annals of Applied Statistics, 2010 - Remodeling and Estimation for Sparse Partially Linear Regression Models
Zeng, Yunhui, Wang, Xiuli, and Lin, Lu, Abstract and Applied Analysis, 2012 - Martingale estimation functions for discretely observed diffusion processes
Martin Bibby, Bo and Sørensen, Michael, Bernoulli, 1995 - The Empirical Distribution Function of Residuals from Generalised Regression
Loynes, R. M., Annals of Statistics, 1980 - A class of robust and fully efficient regression
estimators
Gervini, Daniel and Yohai, Victor J., Annals of Statistics, 2002 - Semiparametric Estimation of Treatment Effect in a Pretest–Posttest Study with Missing Data
Davidian, Marie, Tsiatis, Anastasios A., and Leon, Selene, Statistical Science, 2005 - Can We Reach Consensus on Census Adjustment?
Belin, Thomas R. and Rolph, John E., Statistical Science, 1994 - Entropy methods for reaction-diffusion equations: slowly growing a-priori bounds
Desvillettes, Laurent and Fellner, Klemens, Revista Matemática Iberoamericana, 2008