Maximum likelihood estimation of limited and discrete dependent variable models with nested random effects

TY - JOUR

T1 - Maximum likelihood estimation of limited and discrete dependent variable models with nested random effects

AU - Rabe-Hesketh, S

AU - Skrondal, A

AU - Pickles, A

PY - 2005/10

Y1 - 2005/10

N2 - Gauss-Hermite quadrature is often used to evaluate and maximize the likelihood for random component probit models. Unfortunately, the estimates are biased for large cluster sizes and/or intraclass correlations. We show that adaptive quadrature largely overcomes these problems. We then extend the adaptive quadrature approach to general random coefficient models with limited and discrete dependent variables. The models can include several nested random effects (intercepts and coefficients) representing unobserved heterogeneity at different levels of a hierarchical dataset. The required multivariate integrals are evaluated efficiently using spherical quadrature rules. Simulations show that adaptive quadrature performs well in a wide range of situations.

AB - Gauss-Hermite quadrature is often used to evaluate and maximize the likelihood for random component probit models. Unfortunately, the estimates are biased for large cluster sizes and/or intraclass correlations. We show that adaptive quadrature largely overcomes these problems. We then extend the adaptive quadrature approach to general random coefficient models with limited and discrete dependent variables. The models can include several nested random effects (intercepts and coefficients) representing unobserved heterogeneity at different levels of a hierarchical dataset. The required multivariate integrals are evaluated efficiently using spherical quadrature rules. Simulations show that adaptive quadrature performs well in a wide range of situations.

U2 - 10.1016/j.jeconom.2004.08.017

DO - 10.1016/j.jeconom.2004.08.017

M3 - Article

SN - 0304-4076

VL - 128

SP - 301

EP - 323

JO - JOURNAL OF ECONOMETRICS

JF - JOURNAL OF ECONOMETRICS

IS - 2

M1 - N/A

ER -