The deviance information criterion (DIC) has been widely used for Bayesian model comparison. However, recent studies have cautioned against the use of the DIC for comparing latent variable models. In particular, the DIC calculated using the conditional likelihood (obtained by conditioning on the latent variables) is found to be inappropriate, whereas the DIC computed using the integrated likeli...

The Laplace likelihood method for estimating linear conditional quantile functions with right censored data proposed by Bottai and Zhang (2010) is demonstrated to be highly non-robust.

Barndorff-Nielsen’s formula (normed likelihood with constantinformation metric) has been proffered as an approximate conditional distribution for the maximum-likelihood estimate, based on likelihood functions. Asymptotic justifications are available and the formula coincides with the saddlepoint approximation in full exponential models. It is shown that the formula has wider application than is...

I show how to construct the likelihood function for the conditional maximum likelihood estimator in dynamic, unobserved effects models where not all conditioning variables are strictly exogenous. The method for handling the initial conditions problem appears to be novel, and offers a flexible, relatively simple alternative to existing methods.  2000 Elsevier Science S.A. All rights reserved.

This paper studies in particular an aspect of the estimation of conditional probability distributions by maximum likelihood that seems to have been overlooked in the literature on Bayesian networks: The information conveyed by the conditioning event should be included in the likelihood function as well.

Bartlett correction factors for likelihood ratio tests of parameters in conditional and unconditional logistic regression models are calculated. The resulting tests are compared to the Wald, likelihood ratio, and score tests, and a test proposed by Moolgavkar and Venzon in Modern Statistical Methods in Chronic Disease Epidemiology, (Wiley, New York, 1986).

This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and classification. We optimize hypernetworks to directly maximize the conditional likelihood of target variables given input. Using this approach we obtain competitiv...

It is well known that one of the obstacles to e ective forecasting of exchange rates is het eroscedasticity input dependent conditional variance The autoregressive conditional het eroscedastic ARCH model and its variants have been used to estimate a time dependent variance for many nancial time series However such models are essentially linear in form and we can ask whether a non linear model f...

This paper develops a general theory on rates of convergence penalized spline estimators for function estimation when the likelihood functional is concave in candidate functions, where interpreted broad sense that includes conditional likelihood, quasi-likelihood and pseudo-likelihood. The allows all feasible combinations degree, penalty order smoothness unknown functions. According to this the...

When used to learn high dimensional parametric probabilistic models, the classical maximum likelihood (ML) learning often suffers from computational intractability, which motivates the active developments of non-ML learning methods. Yet, because of their divergent motivations and forms, the objective functions of many non-ML learning methods are seemingly unrelated, and there lacks a unified fr...