Results 1  10
of
1,116
Dirichletmultinomial loglikelihood function
, 2014
"... An efficient algorithm for accurate computation of the ..."
On tests for global maximum of the loglikelihood function
 IEEE Trans. Inform. Theory
, 2004
"... Abstract — Given the location of a relative maximum of the loglikelihood function, how to assess whether it is the global maximum? This paper investigates a statistical tool, which answers this question by posing it as a hypothesis testing problem. A general framework for constructing tests for glo ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
Abstract — Given the location of a relative maximum of the loglikelihood function, how to assess whether it is the global maximum? This paper investigates a statistical tool, which answers this question by posing it as a hypothesis testing problem. A general framework for constructing tests
Improving predictive inference under covariate shift by weighting the loglikelihood function
 JOURNAL OF STATISTICAL PLANNING AND INFERENCE
, 2000
"... ..."
An Efficient Algorithm for Accurate Computation of the DirichletMultinomial LogLikelihood Function
"... Summary: The Dirichletmultinomial (DMN) distribution is a fundamental model for multicategory count data with overdispersion. This distribution has many uses in bioinformatics including applications to metagenomics data, transctriptomics and alternative splicing. The DMN distribution reduces to th ..."
Abstract
 Add to MetaCart
to the multinomial distribution when the overdispersion parameter ψ is zero. Unfortunately, numerical computation of the DMN loglikelihood function by conventional methods results in instability in the neighborhood of ψ = 0. An alternative formulation circumvents this instability, but it leads to long runtimes
A Negative Log Likelihood FunctionBased Nonlinear Neural Network Approach
"... The most commonly used objective function in Artificial Neural Networks (ANNs) is the sum of squared errors. This requires the target and forecasted output vector to have the same dimension. In the context of nonlinear financial time series, both conditional mean and variance (volatility) tend to ev ..."
Abstract
 Add to MetaCart
to evolve over time. It is therefore of interest to consider neural networks with twodimensional output even though the target data are onedimensional. The idea of the backpropagation algorithm can be extended to this situation. For example, the negative loglikelihood based on a parametric statistical
1. Loglikelihood Functions and Scores for VGLMs with Different Data Types 1.1 VGLMs for Correlated Continuous Outcomes
"... When the margins are all continuous, the loglikelihood function for parameter θ = (β,ϕ,α) takes the form ℓ(θ;y) = −n 2 ln Γ+ n∑ i=1 m∑ j=1 log g(yij;β, ϕj) + 1 2 n∑ i=1 qTi (yi;β,ϕ) Im − Γ−1 qi(yi;β,ϕ), where qi(yi;β,ϕ) = (qi1,..., qim) T with components qij = Φ −1(Gij(yij)) and Gij is the marg ..."
Abstract
 Add to MetaCart
When the margins are all continuous, the loglikelihood function for parameter θ = (β,ϕ,α) takes the form ℓ(θ;y) = −n 2 ln Γ+ n∑ i=1 m∑ j=1 log g(yij;β, ϕj) + 1 2 n∑ i=1 qTi (yi;β,ϕ) Im − Γ−1 qi(yi;β,ϕ), where qi(yi;β,ϕ) = (qi1,..., qim) T with components qij = Φ −1(Gij(yij)) and Gij
BoxFunctions and Mismatched LogLikelihood Ratios
, 2000
"... Abstract  The inputoutput relationship of an aposteriori probability decoder often can not be made explicit. When the outputs of such an decoder are represented as loglikelihood ratios, the inputoutput relationship can be regarded as a loglikelihood function. The boxfunction is an example of a ..."
Abstract
 Add to MetaCart
Abstract  The inputoutput relationship of an aposteriori probability decoder often can not be made explicit. When the outputs of such an decoder are represented as loglikelihood ratios, the inputoutput relationship can be regarded as a loglikelihood function. The boxfunction is an example
Asymptotic Characterization of LogLikelihood Maximization Based Algorithms and Applications
, 2003
"... The asymptotic distribution of estimates that are based on a suboptimal search for the maximum of the loglikelihood function is considered. In particular, estimation schemes that are based on a twostage approach, in which an initial estimate is used as the starting point of a subsequent local ..."
Abstract
 Add to MetaCart
The asymptotic distribution of estimates that are based on a suboptimal search for the maximum of the loglikelihood function is considered. In particular, estimation schemes that are based on a twostage approach, in which an initial estimate is used as the starting point of a subsequent
Asymptotic Distribution of LogLikelihood Maximization Based Algorithms and Applications
"... Abstract. The asymptotic distribution of estimates that are based on a suboptimal search for the maximum of the loglikelihood function is considered. In particular, estimation schemes that are based on a twostage approach, in which an initial estimate is used as the starting point of a subsequent ..."
Abstract
 Add to MetaCart
Abstract. The asymptotic distribution of estimates that are based on a suboptimal search for the maximum of the loglikelihood function is considered. In particular, estimation schemes that are based on a twostage approach, in which an initial estimate is used as the starting point of a subsequent
Results 1  10
of
1,116