Table 3.

Comparison of Standardized Biases After Matching: Female Participants

Variable	All female participants	Method 1	Method 2	Method 3	Method 4	Method 5
Propensity score	0.38	0.02	0.03	0.06	0.02	0.06
Maternal substance use history	−0.11	0.09	0.00	0.10	0.02	−0.03
Maternal years of schooling	0.07	0.10	0.08	0.07	0.08	0.03
Family income	−0.03	0.06	0.00	0.18	0.01	0.02
Below poverty threshold	0.12	0.05	0.02	0.18	0.00	0.02
Teacher rating of underachievement	0.02	0.10	0.02	0.15	−0.09	0.00
Teacher rating of aggression	0.23	0.00	0.00	0.13	−0.03	0.04
Teacher rating of shyness	0.14	0.06	0.06	0.10	−0.10	0.00
Teacher rating of immaturity	0.18	0.04	0.03	0.10	−0.02	−0.01
Teacher rating of inattention	0.17	0.12	0.04	0.13	−0.04	0.03
Precision relative to a 1:1 match		1.00	0.82	0.80	0.86	0.81
Precision relative to a 2:1 match		1.22	1.00	0.92	0.99	0.93
N	265	88	132	265	265	265

Note. Standardized bias is defined as the weighted difference in means divided by the standard deviation in the full group of participants who were not heavy marijuana users. Numbers in bold indicate standardized biases that decreased in comparison with the original sample. Methods are as follows: 1 = 1:1 optimal nearest neighbor matching; 2 = 2:1 optimal nearest neighbor matching; 3 = six subclasses; 4 = full matching; and 5 = constrained full matching.