Skip to main content
. Author manuscript; available in PMC: 2012 Jun 18.
Published in final edited form as: Q J Econ. 2011 May;126(2):987–1027. doi: 10.1093/qje/qjr008

Table VII.

Effect of the Euro200 program on Cognitive and Computer Skills

Children Survey
dependent variable Raven's Progressive
Matrices Test
Computer Test Computer Fluency Applications Fluency Web Fluency Email Fluency
(1) (2) (3) (4) (5) (6)
Nonparametric 0.327** 0.268** 0.212* 0.250** 0.021 −0.065
Bandwidth - 30 [0.134] [0.114] [0.118] [0.118] [0.116] [0.118]
Observations 1,084 1,027 1,082 1,082 1,082 1,082
Nonparametric 0.306** 0.237* 0.214* 0.213** 0.016 −0.049
CV Bandwidth [0.125] [0.121] [0.124] [0.104] [0.126] [0.120]
Observations 1,247 887 1,006 1,320 906 1,006
Nonparametric 0.030 0.579*** 0.254 0.077 −0.181 −0.281
IK Bandwidth [0.302] [0.216] [0.272] [0.261] [0.255] [0.244]
Observations 265 242 223 254 246 244
Parametric 0.381*** 0.331*** 0.244** 0.277*** 0.104 0.025
Quadratic Spline [0.120] [0.099] [0.103] [0.104] [0.103] [0.106]
Observations 4,532 4,276 4,516 4,516 4,516 4,516

Notes: Robust standard errors clustered at the household level are in brackets.

***, ** and * indicate statistical significance at the 1, 5 and 10 percent level respectively. The dependent variables are defined in Tables I, II, and III. The reported coefficients are for the variable "Winner" is defined as 1 for individuals with an income below the program cutoff of 62.58 RON, 0 otherwise. All non-parametric specifications use a rectangular kernel. CV refers to the modified cross-validation procedure used to derive the optimal bandwidth; IK refers to the Imbens-Kalyanarman optimal bandwidth. All regressions include controls for age, gender, ethnicity and education of the head of household, as well as gender and age dummy variables of the child. Source: 2009 Euro 200 survey.