Abstract
Optimal matching without groups, or optimal nonbipartite matching, offers many additional options for matched designs in both observational studies and experiments. One starts with a square, symmetric distance matrix with one row and one column for each subject recording the distance between any two subjects. Then the subjects are divided into pairs to minimize the total distance within pairs. The method may be used to match with doses of treatment, or with multiple control groups, or as an aid to risk-set matching. An extended discussion of Card and Krueger’s study of the minimum wage is used to illustrate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Fortran code by Derigs [11] has been made available inside R by Bo Lu et al. [24] through a function nonbimatch( n,d) , where d is the vector form of an n×n symmetric matrix of nonnegative integer distances.
>dm
    1   2   3   4   5   6
1 Â Â 0 106 119 231 110 101
2 106 Â Â 0 207 126 192 Â 68
3 119 207 Â Â 0 156 247 Â 25
4 231 126 156 Â Â 0 Â 34 Â 67
5 110 192 247 Â 34 Â Â 0 212
6 101 Â 68 Â 25 Â 67 212 Â Â 0
>nonbimatch( 6,as.vector( dm) )
[1] 2 1 6 5 4 3
This says that unit 1 is paired with unit 2, unit 2 is paired with unit 1, unit 3 is paired with unit 6, unit 4 is paired with unit 5, unit 5 is paired with unit 4, and unit 6 is paired with unit 3.
- 2.
Card and Krueger’s [4, 5] data are at Princeton University’s Industrial Relations Section webpage http://www.irs.princeton.edu . Restaurants were interviewed twice, once in February 1992, before New Jersey increased its minimum wage, and once in November 1992, after New Jersey increased its minimum wage. Card and Krueger define full-time-equivalent employment as the number of managers plus the number of full-time employees plus half the number of part-time employees, which is NMGRS+EMPFT+EMPPT/2 in their first interview and NMGRS2+EMPFT2+EMPPT2/2 in the second, and the change in employment is the difference between these two quantities, November−minus−February. The price of a full meal refers to the sum of the price of a soda, fries, and an entree, or PSODA+PFRY+PENTREE in the first interview and PSODA2+PFRY2+PENTREE2 in the second, and the change in price is the difference of these two quantities. The starting wage before the increase in the minimum wage is WAGE_ST from the first interview. Other variables used are the restaurant chain (CHAIN), whether the restaurant was company owned (CO_OWNED), and hours open (HRSOPEN). There are 410 restaurants, but the analysis here uses the 351 restaurants with complete data on employment and starting wage. The variable SHEET is Card and Krueger’s identification number for a restaurant.
- 3.
As it turned out, the discarded restaurant was a company owned Pennsylvania KFC open 10 h per day and paying a starting wage before the increase of $5.25. It was Sheet #481.
Bibliography
Baiocchi, M., Small, D.S., Lorch, S., Rosenbaum, P.R.: Building a stronger instrument in an observational study of perinatal care for premature infants. J. Am. Stat. Assoc. 105, 1285–1296 (2010)
Baiocchi, M., Small, D.S., Yang, L., Polsky, D., Groeneveld, P.W.: Near/far matching: a study design approach to instrumental variables. Health Serv. Outcomes Res. Method 12, 237–253 (2012)
Cahuc, P., Carcillo, S., Zylberberg, A.: Labor Economics (2nd edn.). MIT Press, Cambridge (2014)
Card, D., Krueger, A.B.: Minimum wages and employment: a case study of the fast-food industry in New Jersey and Pennsylvania. Am. Econ. Rev. 84, 772–793 (1994)
Card, D., Krueger, A.B.: Myth and Measurement: The New Economics of the Minimum Wage. Princeton University Press, Princeton (1995). Data: http://www.irs.princeton.edu/
Cochran, W.G., Cox, G.M.: Experimental Designs. Wiley, New York (1957)
Cook, W.J., Rohe, A. : Computing minimum-weight perfect matchings. INFORMS J. Comput. 11, 138–148 (1999). Software: http://www2.isye.gatech.edu/~wcook/
Cook, W.J., Cunningham, W.H., Pulleyblank, W.R., Schrijver, A.: Combinatorial Optimization. Wiley, New York (1998)
Cox, D.R., Reid, N.: The Theory of the Design of Experiments. Chapman and Hall/CRC, New York (2000)
Daniel, S., Armstrong, K., Silber, J.H., Rosenbaum, P.R.: An algorithm for optimal tapered matching, with application to disparities in survival. J. Comput. Graph. Stat. 17, 914–924 (2008)
Derigs, U. : Solving nonbipartite matching problems by shortest path techniques. Ann. Oper. Res. 13, 225–261 (1988)
Edmonds, J. : Matching and a polyhedron with 0-1 vertices. J. Res. Nat. Bur. Stand. 65B, 125–130 (1965)
Ertefaie, A., Small, D.S., Rosenbaum, P.R.: Quantitative evaluation of the trade-off of strengthened instruments and sample size in observational studies. J. Am. Stat. Assoc. 113, 1122–1134 (2018)
Greevy, R., Lu, B. , Silber, J.H., Rosenbaum, P.R.: Optimal matching before randomization. Biostatistics 5, 263–275 (2004)
Hornik, R., Jacobsohn, L., Orwin, R., Piesse, A., Kalton, G.: Effects of the national youth anti-drug media campaign on youths. Am. J. Public Health 98, 2229–2236 (2008)
Imai, K. , van Dyk, D.A. : Causal inference with general treatment regimes: generalizing the propensity score. J. Am. Stat. Assoc. 99, 854–866 (2004)
Imbens, G.W. : The role of the propensity score in estimating dose-response functions. Biometrika 87, 706–710 (2000)
Joffe, M.M., Rosenbaum, P.R.: Propensity scores. Am. J. Epidemiol. 150, 327–333 (1999)
Karmakar, B., Small, D.S., Rosenbaum, P.R.: Using approximation algorithms to build evidence factors and related designs for observational studies. J. Comput. Graph. Stat. 28, 698–709 (2019)
Li, Y.F.P., Propert, K.J., Rosenbaum, P.R.: Balanced risk set matching. J. Am. Stat. Assoc. 96, 870–882 (2001)
Lu , B.: Propensity score matching with time-dependent covariates. Biometrics 61, 721–728 (2005)
Lu , B., Rosenbaum, P.R.: Optimal matching with two control groups. J. Comput. Graph. Stat. 13, 422–434 (2004)
Lu , B., Zanutto, E., Hornik, R., Rosenbaum, P.R.: Matching with doses in an observational study of a media campaign against drug abuse. J. Am. Stat. Assoc. 96, 1245–1253 (2001)
Lu, B., Greevy, R., Xu, X., Beck, C.: Optimal nonbipartite matching and its statistical applications. Am. Stat. 65, 21–30 (2011)
Papadimitriou, C.H., Steiglitz, K.: Combinatorial Optimization: Algorithms and Complexity. Prentice Hall, Englewood Cliffs (1982)
Pimentel, S.D., Small, D.S., Rosenbaum, P.R.: Constructed second control groups and attenuation of unmeasured biases. J. Am. Stat. Assoc. 111, 1157–1167 (2016)
Pimentel, S.D., Small, D.S., Rosenbaum, P.R.: An exact test of fit for the Gaussian linear model using optimal nonbipartite matching. Technometrics 59, 330–337 (2017)
R Development Core Team.: R: A Language and Environment for Statistical Computing. R Foundation, Vienna (2007). http://www.R-project.org
Rigdon, J., Baiocchi, M., Basu, S.: Near-far matching in R: the nearfar package. J. Stat. Softw. 86, 5 (2018). https://doi.org/10.18637/jss.v086.c05
Rosenbaum, P.R.: Evidence factors in observational studies. Biometrika 97, 333–345 (2010)
Rosenbaum, P.R., Silber, J.H. : Sensitivity analysis for equivalence and difference in an observational study of neonatal intensive care units. J. Am. Stat. Assoc. 104, 501–511 (2009)
Silber, J.H. , Lorch, S.L. , Rosenbaum, P.R., Medoff-Cooper, B. , Bakewell-Sachs, S. , Millman, A. , Mi, L. , Even-Shoshan, O. , Escobar, G.E. : Additional maturity at discharge and subsequent health care costs. Health Serv. Res. 44, 444–463 (2009)
Stigler, G.J. : The economics of minimum wage legislation. Am. Econ. Rev. 36, 358–365 (1946)
Yang, F., Zubizarreta, J.R., Small, D.S., Lorch, S., Rosenbaum, P.R.: Dissonant conclusions when testing the validity of an instrumental variable. Am. Stat. 68, 253–263 (2014)
Zubizarreta, J.R., Small, D.S., Goyal, N.K., Lorch, S., Rosenbaum, P.R.: Stronger instruments via integer programming in an observational study of late preterm birth outcomes. Ann. Appl. Stat. 7, 25–50 (2013)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
R. Rosenbaum, P. (2020). Matching Without Groups. In: Design of Observational Studies. Springer Series in Statistics. Springer, Cham. https://doi.org/10.1007/978-3-030-46405-9_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-46405-9_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-46404-2
Online ISBN: 978-3-030-46405-9
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)