Estimation of Treatment Effects Without an Exclusion Restriction: With an Application to the Analysis of the School Breakfast Program

Millimet, Daniel L.; Tchernis, Rusty

doi:10.1002/jae.2286

Cited by 69 publications

(60 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While NIPW reduce biases in the estimates compared to the OLS estimates by using appropriate weighting, the MB-NIPW estimator is especially useful, because it minimizes the biases arising from selection on unobservables. Millimet and Tchernis (2013) provide evidence that the MB-NIPW estimator is able to correct for some of the biases due to selection on unobservables and yield more reliable estimates of the causal effects when the conditional independence assumption fails. According to the Monte Carlo evidence reported by Millimet and Tchernis, the MB-NIPW estimator performs particularly well when the estimating equation suffers from omitted variables (such as omitted ability heterogeneity in educational attainment in our case).…”

Section: (3) Conceptual and Empirical Frameworkmentioning

confidence: 96%

“…It is, however, important to appreciate that the advantage of MB-NIPW estimator in terms of causal interpretation comes with a price: the estimates are relevant for only a subset of the population defined by an interval around the bias minimizing propensity score of 0.05. In other words, the estimates provide local average treatment effect, similar to instrumental variables and regression discontinuity designs (for an extended discussion see Millimet and Tchernis (2013)). Thus the MB-NIPW estimates may be different from the other estimates, simply because they provide estimates for a sub population.…”

Section: (3) Conceptual and Empirical Frameworkmentioning

confidence: 99%

“…2) For the column (1), the interest variable=grandparents' education dummy, dummy =1 if at least one of grandparents more than primary schooling, 0=otherwise; 3) For all columns, the control variables are parents' age, parents' age squared, grandmother's age, grandmother's age squared, grandfather's age, grandfather's age squared; 4) For the columns (2) -(4), the interest variable is grandparents' education and occupation status dummy. The dummy equals 1 if household belongs to 'treatment' group, and 0 otherwise; the base group is parents (farm, low edu) 5) A-I matching=Abadie and Imbens (2002) 6) BC-RM = Biased corrected radius matching; 7) NIPW = normalized inverse probability weighted propensity score estimator of Hirano and Imbens (2001); 8) MB-NIPW = minimum-biased normalized inversed probability weighted estimator; 9) The computation uses STATA program written by Millimet and Tchernis (2013); 10) For NIPW and MB-NIPW, 90% confidence interval is given in parentheses, which is boostrapped using 250 replications; 11) "high edu" stands for more than primary schooling, "low edu" stands for primary schooling or less; 12) ***, **, and * Denotes statistical significance at 1%, 5%, and 10% level. 2) For the column (1), the interest variable=parents' education dummy, dummy =1 if at least one of parents more than junior middle school, 0=otherwise 3) For all columns, the control variables are children's age, children's age squared, mother's age, mother's age squared, father's age, father's age squared; 4) For the columns (2) -(4), the interest variable is parents' education and occupation status dummy.…”

Section: Grandparents In Generalmentioning

confidence: 99%

“…9 This framework allows us to use appropriate subsamples as "treatment" and "comparison" groups to explore a set of important questions related to the role of family background in children's schooling using recently developed matching and propensity score weighted estimators (Millimet and Tchernis (2013), Huber et al (2013)). 10 First, we provide evidence of substantial heterogeneity.…”

Section: (1) Introductionmentioning

confidence: 99%

“…, the dependent variable is years of schooling of children generation, the regression includes the family background occupation dummy, family education dummy, the interaction of the two dummies, and the controls; but the table only reports the coefficient of the interaction of two dummies; 2) For the column (1), family background occupation dummy = 1 if off-farm, =0 otherwise, family background education dummy = 1 if more than primary schooling, 0=otherwise; 3) For all columns, the control variables are children's age, children's age squared, mother's age, mother's age squared, father's age, father's age squared; 4) Column (2) and (3) break the full sample into two subsamples based on family occupation background, for each subsample, the treatment is family education background high, which is more than primary schooling; 5) A-I matching=Abadie and Imbens (2002) 6) BC-RM = Biased corrected radius matching; 7) NIPW = normalized inverse probability weighted propensity score estimator of Hirano and Imbens (2001); 8) MB-NIPW = minimum-biased normalized inversed probability weighted estimator; 9) The computation uses STATA program written by Millimet and Tchernis (2013); 10) For NIPW and MB-NIPW, 90% confidence interval is given in parentheses, which is boostrapped using 250 replications; 11) ***, **, and * Denotes statistical significance at 1%, 5%, and 10% level; …”

mentioning

confidence: 99%

See 4 more Smart Citations

Are the Children of Uneducated Farmers Doubly Doomed? Farm, Nonfarm and Intergenerational Educational Mobility in Rural China

Emran

Sun

2014

SSRN Journal

View full text Add to dashboard Cite

This paper relaxes the single factor model of intergenerational educational mobility standard in the literature, and develops a research design to study the effects of parents' education and occupation on children's schooling. We use survey data from rural China that cover three generations and are not subject to coresidency bias. The evidence from recently developed matching and propensity score weighted estimators shows that the mean effects of parents education from the standard model miss substantial heterogeneity. Within the low education subsample, a son (girl) attains about 0.80 (0.60) years of additional schooling when born into a non-farm household compared to a farm household, and among the farming households, a child gains a one year of schooling when at least one parent has more than primary schooling. Having nonfarm parents, however, does not confer any advantages over the farmer parents if the farmers are relatively more educated, even though nonfarm households have significantly higher income. This suggests that income plays a secondary role to parental education. Estimates of cross-partial effects without imposing functional form show little evidence of complementarity between parental education and non-farm occupation. The role of family background remains stable across generations for girls, but for boys, family background has become more important after the market reform.Key Words: Educational Mobility, Inequality, Rural China, Nonfarm, Education and Occupation, Family Background, Heterogeneity, Complementarity, Market Reform, Gender Gap JEL Codes: O12, J621 We would like to thank Li Shi, Zhan Peng, and Song Jin for help with the CHIP survey data, and Matthew Lindquist and Forhad Shilpi for helpful comments and/or discussions. (1) IntroductionIncreasing inequality despite sustained economic growth and poverty reduction in last few decades has become a central policy issue in both developed and developing countries (Stiglitz (2012), Rajan (2010), Picketty (2014)). Inequality and its negative effects have also been high on the agenda of the Chinese policymakers in recent years. 2 There is a broad consensus among the policy makers and academic economists that education is one of the most important policy instruments to make the playing field level for children from the poor socio-economic background, and moderate the inequality generated by market reform. It is thus important to understand potential disadvantages faced by children from a poor socio-economic background in attaining the education and skills required in an increasingly globalized and skill-based labor market.The economics literature on intergenerational educational mobility has focused on parental education as the relevant indicator of family background for understanding intergenerational linkages (see Bjorklund and Salvanes (2011) for a recent survey, and on China, see, among others, Knight et al. (2013), Sato and Li (2007), Emran and Sun (2011)). This emphasis on parental education is eminently appropriate when the goal is...

show abstract

Section: (3) Conceptual and Empirical Frameworkmentioning

confidence: 96%

Section: (3) Conceptual and Empirical Frameworkmentioning

confidence: 99%

Section: Grandparents In Generalmentioning

confidence: 99%

Section: (1) Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Are the Children of Uneducated Farmers Doubly Doomed? Farm, Nonfarm and Intergenerational Educational Mobility in Rural China

Emran

Sun

2014

SSRN Journal

View full text Add to dashboard Cite

show abstract

Early child development and parents' labor supply

Lafférs

Schmidpeter

2021

J of Applied Econometrics

View full text Add to dashboard Cite

Summary The impact of children's early development status on parental labor market outcomes is not well established in the empirical literature. We combine an instrumental variable approach to account for the endogeneity of the development status with a model of nonrandom labor force participation to identify its impact. A one‐unit increase in our poor child development index reduces long‐term maternal weekly hours worked by 9 h and weekly income by A$215. We provide evidence that mothers substitute working time with childcare to compensate for early disadvantages. We do not find any responses of fathers to early child development.

show abstract

Informal search, bad search?: the effects of job search method on wages among rural migrants in urban China

2017

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Any opinions expressed in this paper are those of the author(s) and not those of IZA. Research published in this series may include views on policy, but IZA takes no institutional policy positions. The IZA research network is committed to the IZA Guiding Principles of Research Integrity. The IZA Institute of Labor Economics is an independent economic research institute that conducts research in labor economics and offers evidence-based policy advice on labor market issues. Supported by the Deutsche Post Foundation, IZA runs the world's largest network of economists, whose research aims to provide answers to the global labor market challenges of our time. Our key objective is to build bridges between academic research, policymakers and society. IZA Discussion Papers often represent preliminary work and are circulated to encourage discussion. Citation of such a paper should account for its provisional character. A revised version may be available directly from the author. what are the underlying mechanisms. We empirically examine these issues specifically for rural migrants in urban China, a country where one of the largest domestic migration in human history has occurred over the past decades. We find that there exists a significant wage penalty for those migrant workers who have conducted their search through informal channels, despite their popularity. Our further analysis suggests two potential reasons for the wage penalty: 1) the informal job search sends a negative signal (of workers' inability to successfully find a job in a competitive market) to potential employers, resulting in lower wages; and 2) there exists a trade-off between wages and search efficiency for quicker entry into local labor market. We also find some evidence that the informal job search may lead to low-skilled jobs with lower wages. We do not find strong evidence supporting alternative explanations. Terms of use: Documents in JEL

show abstract

Estimation of Treatment Effects Without an Exclusion Restriction: With an Application to the Analysis of the School Breakfast Program

Cited by 69 publications

References 61 publications

Are the Children of Uneducated Farmers Doubly Doomed? Farm, Nonfarm and Intergenerational Educational Mobility in Rural China

Are the Children of Uneducated Farmers Doubly Doomed? Farm, Nonfarm and Intergenerational Educational Mobility in Rural China

Early child development and parents' labor supply

Informal search, bad search?: the effects of job search method on wages among rural migrants in urban China

Contact Info

Product

Resources

About