Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Entire DC Network
What Matter For Child Development?, Fali Huang
What Matter For Child Development?, Fali Huang
Research Collection School Of Economics
This paper estimates production functions of child cognitive and social development using a panel data of nine-year old children each with over two hundred home and school inputs as well as family background variables. A tree regression method is used to conduct estimation under various speci…cations. A small subset of inputs is found consistently important in explaining variances of child development results, including the number of books a child has at various ages and how often a mother reads to child by age …ve, while the e¤ects of race and maternal employment are negligible when detailed inputs are controlled.
Profile Likelihood Estimation Of Partially Linear Panel Data Models With Fixed Effects, Liangjun Su, Aman Ullah
Profile Likelihood Estimation Of Partially Linear Panel Data Models With Fixed Effects, Liangjun Su, Aman Ullah
Research Collection School Of Economics
We consider consistent estimation of partially linear panel data models with fixed effects. We propose profile-likelihood-based estimators for both the parametric and nonparametric components in the models and establish convergence rates and asymptotic normality for both estimators.
A Semi-Parametric Estimator For Censored Selection Models With Endogeneity, Myoung-Jae Lee, Francis Vella
A Semi-Parametric Estimator For Censored Selection Models With Endogeneity, Myoung-Jae Lee, Francis Vella
Research Collection School Of Economics
We propose a semi-parametric least-squares estimator for a censored-selection (type 3 tobit) model under the mean independence of the outcome equation error u from the regressors given the selection indicator and its error term ɛ. This assumption is relatively weak in comparison to alternative estimators for this model and allows certain unknown forms of heteroskedasticity, an asymmetric error distribution, and an arbitrary relationship between the u and ɛ. The estimator requires only one-dimensional smoothing on the estimate of ɛ. We generalize the estimator to allow for an endogenous regressor whose equation contains an error w related to u and discuss …