NPMLENon-Parametric Maximum Likelihood Estimator
Copyright 1988-2018, All rights reserved.
References in periodicals archive ?
The NPMLE of the Joint Distribution Function with Right-Censored and Masked Competing Risks Data." Journal of Nonparametric Statistics 24(3):75364.
The mixing distribution for the unobserved heterogeneity is estimated using the Heckman and Singer (1984) nonparametric maximum-likelihood estimator (NPMLE), which is consistent under very general conditions and is robust to misspecification of the functional form for the unobservables.
This type of heterogeneity is modeled in NPMLE by allowing for the possibility of point mass at [theta] = -[infinity].