Open Access
February 2020 Rerandomization in $2^{K}$ factorial experiments
Xinran Li, Peng Ding, Donald B. Rubin
Ann. Statist. 48(1): 43-63 (February 2020). DOI: 10.1214/18-AOS1790
Abstract

With many pretreatment covariates and treatment factors, the classical factorial experiment often fails to balance covariates across multiple factorial effects simultaneously. Therefore, it is intuitive to restrict the randomization of the treatment factors to satisfy certain covariate balance criteria, possibly conforming to the tiers of factorial effects and covariates based on their relative importances. This is rerandomization in factorial experiments. We study the asymptotic properties of this experimental design under the randomization inference framework without imposing any distributional or modeling assumptions of the covariates and outcomes. We derive the joint asymptotic sampling distribution of the usual estimators of the factorial effects, and show that it is symmetric, unimodal and more “concentrated” at the true factorial effects under rerandomization than under the classical factorial experiment. We quantify this advantage of rerandomization using the notions of “central convex unimodality” and “peakedness” of the joint asymptotic sampling distribution. We also construct conservative large-sample confidence sets for the factorial effects.

References

1.

Angrist, J., 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., 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.

2.

Bailey, R. A. (1983). Restricted randomization. Biometrika 70 183–198. 0517.62069 10.1093/biomet/70.1.183Bailey, R. A. (1983). Restricted randomization. Biometrika 70 183–198. 0517.62069 10.1093/biomet/70.1.183

3.

Baldi Antognini, A. and Zagoraiou, M. (2011). The covariate-adaptive biased coin design for balancing clinical trials in the presence of prognostic factors. Biometrika 98 519–535. 1231.62148 10.1093/biomet/asr021Baldi Antognini, A. and Zagoraiou, M. (2011). The covariate-adaptive biased coin design for balancing clinical trials in the presence of prognostic factors. Biometrika 98 519–535. 1231.62148 10.1093/biomet/asr021

4.

Bickel, P. J. and Lehmann, E. L. (1976). Descriptive statistics for nonparametric models. III. Dispersion. Ann. Statist. 4 1139–1158. 0351.62031 10.1214/aos/1176343648 euclid.aos/1176343648Bickel, P. J. and Lehmann, E. L. (1976). Descriptive statistics for nonparametric models. III. Dispersion. Ann. Statist. 4 1139–1158. 0351.62031 10.1214/aos/1176343648 euclid.aos/1176343648

5.

Birnbaum, Z. W. (1948). On random variables with comparable peakedness. Ann. Math. Stat. 19 76–81. 0031.36801 10.1214/aoms/1177730293 euclid.aoms/1177730293Birnbaum, Z. W. (1948). On random variables with comparable peakedness. Ann. Math. Stat. 19 76–81. 0031.36801 10.1214/aoms/1177730293 euclid.aoms/1177730293

6.

Bose, R. C. (1947). Mathematical theory of the symmetrical factorial design. Sankhyā 8 107–166. 0038.09601Bose, R. C. (1947). Mathematical theory of the symmetrical factorial design. Sankhyā 8 107–166. 0038.09601

7.

Box, G. E. P., Hunter, J. S. and Hunter, W. G. (2005). Statistics for Experimenters: Design, Innovation, and Discovery, 2nd ed. Wiley Series in Probability and Statistics. Wiley Interscience, Hoboken, NJ. 1082.62063Box, G. E. P., Hunter, J. S. and Hunter, W. G. (2005). Statistics for Experimenters: Design, Innovation, and Discovery, 2nd ed. Wiley Series in Probability and Statistics. Wiley Interscience, Hoboken, NJ. 1082.62063

8.

Branson, Z., Dasgupta, T. and Rubin, D. B. (2016). Improving covariate balance in $2^{K}$ factorial designs via rerandomization with an application to a New York City Department of Education high school study. Ann. Appl. Stat. 10 1958–1976. 06688764 10.1214/16-AOAS959 euclid.aoas/1483606847Branson, Z., Dasgupta, T. and Rubin, D. B. (2016). Improving covariate balance in $2^{K}$ factorial designs via rerandomization with an application to a New York City Department of Education high school study. Ann. Appl. Stat. 10 1958–1976. 06688764 10.1214/16-AOAS959 euclid.aoas/1483606847

9.

Bruhn, M. and McKenzie, D. (2009). In pursuit of balance: Randomization in practice in development field experiments. Am. Econ. J. Appl. Econ. 1 200–232.Bruhn, M. and McKenzie, D. (2009). In pursuit of balance: Randomization in practice in development field experiments. Am. Econ. J. Appl. Econ. 1 200–232.

10.

Cochran, W. G. and Cox, G. M. (1950). Experimental Designs. Wiley, New York. 0850.62005Cochran, W. G. and Cox, G. M. (1950). Experimental Designs. Wiley, New York. 0850.62005

11.

Cox, D. R. (1982). Randomization and concomitant variables in the design of experiments. In Statistics and Probability: Essays in Honor of C. R. Rao (P. R. K. G. Kallianpur and J. K. Ghosh, eds.) 197–202. North-Holland, Amsterdam. 0482.62067Cox, D. R. (1982). Randomization and concomitant variables in the design of experiments. In Statistics and Probability: Essays in Honor of C. R. Rao (P. R. K. G. Kallianpur and J. K. Ghosh, eds.) 197–202. North-Holland, Amsterdam. 0482.62067

12.

Cox, D. R. (2009). Randomization in the design of experiments. Int. Stat. Rev. 77 415–429.Cox, D. R. (2009). Randomization in the design of experiments. Int. Stat. Rev. 77 415–429.

13.

Cox, D. R. and Reid, N. (2000). The Theory of the Design of Experiments. Chapman and Hall/CRC, New York. 1009.62061Cox, D. R. and Reid, N. (2000). The Theory of the Design of Experiments. Chapman and Hall/CRC, New York. 1009.62061

14.

Dasgupta, T., Pillai, N. S. and Rubin, D. B. (2015). Causal inference from $2^{K}$ factorial designs by using potential outcomes. J. R. Stat. Soc. Ser. B. Stat. Methodol. 77 727–753. 1414.62337 10.1111/rssb.12085Dasgupta, T., Pillai, N. S. and Rubin, D. B. (2015). Causal inference from $2^{K}$ factorial designs by using potential outcomes. J. R. Stat. Soc. Ser. B. Stat. Methodol. 77 727–753. 1414.62337 10.1111/rssb.12085

15.

Dharmadhikari, S. and Joag-Dev, K. (1988). Unimodality, Convexity, and Applications. Probability and Mathematical Statistics. Academic Press, Boston, MA. 0646.62008Dharmadhikari, S. and Joag-Dev, K. (1988). Unimodality, Convexity, and Applications. Probability and Mathematical Statistics. Academic Press, Boston, MA. 0646.62008

16.

Dharmadhikari, S. W. and Jogdeo, K. (1976). Multivariate unimodality. Ann. Statist. 4 607–613. 0338.62006 10.1214/aos/1176343466 euclid.aos/1176343466Dharmadhikari, S. W. and Jogdeo, K. (1976). Multivariate unimodality. Ann. Statist. 4 607–613. 0338.62006 10.1214/aos/1176343466 euclid.aos/1176343466

17.

Finney, D. J. (1943). The fractional replication of factorial arrangements. Ann. Hum. Genet. 12 291–301.Finney, D. J. (1943). The fractional replication of factorial arrangements. Ann. Hum. Genet. 12 291–301.

18.

Fisher, R. A. (1926). The arrangement of field experiments. J. Minist. Agric. G.B. 33 503–513.Fisher, R. A. (1926). The arrangement of field experiments. J. Minist. Agric. G.B. 33 503–513.

19.

Fisher, R. A. (1935). The Design of Experiments, 1st ed. Oliver and Boyd, Edinburgh.Fisher, R. A. (1935). The Design of Experiments, 1st ed. Oliver and Boyd, Edinburgh.

20.

Giovagnoli, A. and Wynn, H. P. (1995). Multivariate dispersion orderings. Statist. Probab. Lett. 22 325–332. 0813.62048 10.1016/0167-7152(94)00084-LGiovagnoli, A. and Wynn, H. P. (1995). Multivariate dispersion orderings. Statist. Probab. Lett. 22 325–332. 0813.62048 10.1016/0167-7152(94)00084-L

21.

Grundy, P. M. and Healy, M. J. R. (1950). Restricted randomization and quasi-Latin squares. J. Roy. Statist. Soc. Ser. B 12 286–291. 0041.45809 10.1111/j.2517-6161.1950.tb00062.xGrundy, P. M. and Healy, M. J. R. (1950). Restricted randomization and quasi-Latin squares. J. Roy. Statist. Soc. Ser. B 12 286–291. 0041.45809 10.1111/j.2517-6161.1950.tb00062.x

22.

Hansen, B. B. and Bowers, J. (2008). Covariate balance in simple, stratified and clustered comparative studies. Statist. Sci. 23 219–236. 1327.62019 10.1214/08-STS254 euclid.ss/1219339114Hansen, B. B. and Bowers, J. (2008). Covariate balance in simple, stratified and clustered comparative studies. Statist. Sci. 23 219–236. 1327.62019 10.1214/08-STS254 euclid.ss/1219339114

23.

Hinkelmann, K. and Kempthorne, O. (2007). Design and Analysis of Experiments, Vol. 1, Introduction to Experimental Design, 2nd ed. Wiley, New York. 1085.62086Hinkelmann, K. and Kempthorne, O. (2007). Design and Analysis of Experiments, Vol. 1, Introduction to Experimental Design, 2nd ed. Wiley, New York. 1085.62086

24.

Kanter, M. (1977). Unimodality and dominance for symmetric random vectors. Trans. Amer. Math. Soc. 229 65–85. MR445580 0379.60015 10.1090/S0002-9947-1977-0445580-7Kanter, M. (1977). Unimodality and dominance for symmetric random vectors. Trans. Amer. Math. Soc. 229 65–85. MR445580 0379.60015 10.1090/S0002-9947-1977-0445580-7

25.

Kempthorne, O. (1952). The Design and Analysis of Experiments. Wiley, New York. 0049.09901Kempthorne, O. (1952). The Design and Analysis of Experiments. Wiley, New York. 0049.09901

26.

Li, X. and Ding, P. (2017). General forms of finite population central limit theorems with applications to causal inference. J. Amer. Statist. Assoc. 112 1759–1769.Li, X. and Ding, P. (2017). General forms of finite population central limit theorems with applications to causal inference. J. Amer. Statist. Assoc. 112 1759–1769.

27.

Li, X., Ding, P. and Rubin, D. B. (2018). Asymptotic theory of rerandomization in treatment-control experiments. Proc. Natl. Acad. Sci. USA 115 9157–9162. 1416.62440 10.1073/pnas.1808191115Li, X., Ding, P. and Rubin, D. B. (2018). Asymptotic theory of rerandomization in treatment-control experiments. Proc. Natl. Acad. Sci. USA 115 9157–9162. 1416.62440 10.1073/pnas.1808191115

28.

Li, X., Ding, P. and Rubin, D. B. (2020). Supplement to “Rerandomization in $2^{K}$ factorial experiments.”  https://doi.org/10.1214/18-AOS1790SUPP.Li, X., Ding, P. and Rubin, D. B. (2020). Supplement to “Rerandomization in $2^{K}$ factorial experiments.”  https://doi.org/10.1214/18-AOS1790SUPP.

29.

Lu, J. (2016). Covariate adjustment in randomization-based causal inference for $2^{K}$ factorial designs. Statist. Probab. Lett. 119 11–20. 1398.62211 10.1016/j.spl.2016.07.010Lu, J. (2016). Covariate adjustment in randomization-based causal inference for $2^{K}$ factorial designs. Statist. Probab. Lett. 119 11–20. 1398.62211 10.1016/j.spl.2016.07.010

30.

Marshall, A. W., Olkin, I. and Arnold, B. C. (2009). Inequalities: Theory of Majorization and Its Applications, 2nd ed. Springer, New York. 1219.26003Marshall, A. W., Olkin, I. and Arnold, B. C. (2009). Inequalities: Theory of Majorization and Its Applications, 2nd ed. Springer, New York. 1219.26003

31.

Morgan, K. L. and Rubin, D. B. (2012). Rerandomization to improve covariate balance in experiments. Ann. Statist. 40 1263–1282. 1274.62509 10.1214/12-AOS1008 euclid.aos/1342625468Morgan, K. L. and Rubin, D. B. (2012). Rerandomization to improve covariate balance in experiments. Ann. Statist. 40 1263–1282. 1274.62509 10.1214/12-AOS1008 euclid.aos/1342625468

32.

Morgan, K. L. and Rubin, D. B. (2015). Rerandomization to balance tiers of covariates. J. Amer. Statist. Assoc. 110 1412–1421. 1373.62417 10.1080/01621459.2015.1079528Morgan, K. L. and Rubin, D. B. (2015). Rerandomization to balance tiers of covariates. J. Amer. Statist. Assoc. 110 1412–1421. 1373.62417 10.1080/01621459.2015.1079528

33.

Shaked, M. (1985). Ordering distributions by dispersion. In Encyclopedia of Statistical Sciences, Vol. 6 (N. L. Johnson and S. Kotz, eds.) 485–490. Wiley, New York.Shaked, M. (1985). Ordering distributions by dispersion. In Encyclopedia of Statistical Sciences, Vol. 6 (N. L. Johnson and S. Kotz, eds.) 485–490. Wiley, New York.

34.

Sherman, S. (1955). A theorem on convex sets with applications. Ann. Math. Stat. 26 763–767. 0066.37403 10.1214/aoms/1177728435 euclid.aoms/1177728435Sherman, S. (1955). A theorem on convex sets with applications. Ann. Math. Stat. 26 763–767. 0066.37403 10.1214/aoms/1177728435 euclid.aoms/1177728435

35.

Splawa-Neyman, J. (1990). On the application of probability theory to agricultural experiments. Essay on principles (with discussion). Section 9. Statist. Sci. 5 465–472. Translated from the Polish and edited by D. M. Dąbrowska and T. P. Speed. 0955.01560 10.1214/ss/1177012031 euclid.ss/1177012031Splawa-Neyman, J. (1990). On the application of probability theory to agricultural experiments. Essay on principles (with discussion). Section 9. Statist. Sci. 5 465–472. Translated from the Polish and edited by D. M. Dąbrowska and T. P. Speed. 0955.01560 10.1214/ss/1177012031 euclid.ss/1177012031

36.

Student (1938). Comparison between balanced and random arrangements of field plots. Biometrika 29 363–378. 64.1221.01Student (1938). Comparison between balanced and random arrangements of field plots. Biometrika 29 363–378. 64.1221.01

37.

Wu, C. F. J. (2015). Post-Fisherian experimentation: From physical to virtual. J. Amer. Statist. Assoc. 110 612–620. 1373.62589 10.1080/01621459.2014.914441Wu, C. F. J. (2015). Post-Fisherian experimentation: From physical to virtual. J. Amer. Statist. Assoc. 110 612–620. 1373.62589 10.1080/01621459.2014.914441

38.

Wu, C. F. J. and Hamada, M. S. (2011). Experiments: Planning, Analysis, and Optimization. Wiley, Hoboken, NJ. 1229.62100Wu, C. F. J. and Hamada, M. S. (2011). Experiments: Planning, Analysis, and Optimization. Wiley, Hoboken, NJ. 1229.62100

39.

Yates, F. (1937). The design and analysis of factorial experiments. Technical Communication No. 35, Imperial Bureau of Soil Sciences, Harpenden.Yates, F. (1937). The design and analysis of factorial experiments. Technical Communication No. 35, Imperial Bureau of Soil Sciences, Harpenden.

40.

Yates, F. (1948). Comment to F. J. Anscombe. J. R. Stat. Soc., A 111 204–205. MR30181 10.2307/2984159Yates, F. (1948). Comment to F. J. Anscombe. J. R. Stat. Soc., A 111 204–205. MR30181 10.2307/2984159

41.

Youden, W. J. (1972). Randomization and experimentation. Technometrics 14 13–22.Youden, W. J. (1972). Randomization and experimentation. Technometrics 14 13–22.
Copyright © 2020 Institute of Mathematical Statistics
Xinran Li, Peng Ding, and Donald B. Rubin "Rerandomization in $2^{K}$ factorial experiments," The Annals of Statistics 48(1), 43-63, (February 2020). https://doi.org/10.1214/18-AOS1790
Received: 1 September 2017; Published: February 2020
Vol.48 • No. 1 • February 2020
Back to Top