Skip to main content

Table 2 The L1 measure of imbalance between two groups before and after Coarsened Exact Matching

From: The effects of family physician-contracted service on health-related quality of life and equity in health in China

Variables Before Matching After Matching
L1 (Mean) L1 (SE) L1 (Mean) L1 (SE)
Sex 0.0083 0.0083 2.6 × 10−15 2.9 × 10−15
Age group 0.0833 0.1662 3.8 × 10− 15 −7.1 × 10− 15
Chronic conditions 0.0632 0.0632 2.2 × 10− 15 2.8 × 10− 15
Economic status 0.1057 −0.2737 2.7 × 10− 15 −3.1 × 10− 15
Educational level 0.1451 −0.3527 3.2 × 10− 15 −5.3 × 10− 15
Marital status 0.0144 0.0247 3.7 × 10−16 −4.4 × 10− 15
Employment status 0.0256 0.0256 2.8 × 10−15 1.3 × 10− 15
Basic medical insurance 0.1514 0.1514 7.9 × 10−16 −2.4 × 10−15
Commercial insurance 0.0023 −0.0023 6.2 × 10−16 4.7 × 10−16
Minimum travel time to the nearest health-care facility 0.0024 −0.0024 1.2 × 10−16 1.1 × 10−15
Residential areas 0.4242 3.3935 3.1 × 10−15 5.5 × 10−14
Multivariate L1 0.5648   3.6 × 10−15  
Total, N 6503   4566  
  1. Note: The overall imbalance is given by L1 statistic, introduced in Iacus, King, and Porro (2008) as a comprehensive measure of global imbalance. L1 reported the L1j measure, which is L1 computed for the jth variable separated. The mean was labeled in parentheses reported the difference in means