Skip to main content
. Author manuscript; available in PMC: 2014 Dec 1.
Published in final edited form as: Am J Community Psychol. 2013 Dec;52(0):380–392. doi: 10.1007/s10464-013-9604-4

Table 3.

Estimates of the Causal Effect of Head Start vs. Parental Care.

ATE ATT

Method Estimate Std. Error p-value Estimate Std. Error p-value
 Unadjusted −3.62 0.30 <0.001 --- --- ---
 ANCOVA including four covariatesa −1.57 0.31 <0.001 --- --- ---
 Weighting −1.46 0.51 0.004 −0.35 0.42 0.402
 Matching – nearest neighbor --- --- --- −0.24 0.41 0.562
 Matching – optimal --- --- --- −0.34 0.40 0.389
 Subclassification −1.39 0.45 0.003 −0.31 0.38 0.413

Notes. Estimates greater than zero indicate higher mean reading score in Head Start group. Dashed lines indicate that effect is not applicable.

a

Covariates included were child’s gender, child’s race, mother’s education and socio-economic status