似然函数

传统的统计方法基于贪婪原则，常以语料的似然函数或困惑度（perplexity）作为评价标准。

Conventional statistical clustering methods usually base on greedy principle . The common Metric for evaluating a clustering algorithm is the likelihood function or perplexity of the corpus .

引入平稳序列的线性AR模型与线性扰动模型（LPM）对HUP的先验分布与似然函数作了改进。

An autoregressive model and a linear perturbation model ( LPM ) were proposed to describe the Bayesian prior distribution and likelihood function of the HUP , respectively .

EM算法是参数估计的重要方法，其算法核心是根据已有的数据来迭代计算似然函数，使之收敛于某个最优值。

EM algorithm is an important method of parameter estimation .

Cox偏似然函数的不完全样本效率

The efficiency of cox 's partial likelihood function for incomplete samples

这里我们得到了原始似然函数的下界，EM算法的核心就是通过最大化这个下界来最大化原始似然函数。

The main idea of EM is to maximize this lower bound so as to maximize the original ( incompelte ) likelihood .

本文通过后验对数似然函数，提出了若干有偏估计的后验Fisher信息比和后验似然距离统计量。

By using a posterior distribution logarithmic likelihood function , this paper defines posterior Fisher imformation ratio statistic and posterior likelihood distance statistic .

该模型采用ARMA模型描述实测流量的先验分布，采用AR模型模拟预报残差的似然函数，并假定先验分布和似然函数均服从正态分布。

The ARMA model was used to describe the prior distribution of observed discharge and the AR model was adopted to simulate the likelihood function of forecasting error .

我们的方法类似于Cai，Fan和Li（2000）所用的，但是他们的结果是建立在方差函数已知的前提下，对独立的样本使用似然函数的方法来讨论的。

Our model is similar to that of Cai , Fan and Li ( 2000 ), but their results are established basing on known variance function and independent samples and their method is based on likelihood estimation .

本文以似然函数法分析F3家系资料，提出家系主基因型鉴别，主微基因效应和互作以及主基因显性度的估计和测验方法。

In this paper likelihood method is used to analyse F3 families from such cross . The method is proposed for genotype identification , estimation of major gene and polygene effects and the degree of dominance of the major genes .

改进的一个核心的思想就是：在共享EM算法良好性质（单调增加似然函数值和稳定收敛）的基础上，改善其收敛的速度。

The key conception is that those improvements should greatly share the essential properties of EM Algorithm ( the monotonic increase in the ML and the stable convergence ) and accelerate the speed of the convergence .

文中详细讨论了ψ（2S）扫描实验数据拟合过程中同一反应道不同能量点之间，以及同一能量点不同反应道之间的复杂的相关性问题.利用最大似然函数法得到拟合公式；

Maximum likelihood method is adopted to acquire the fitting formula , which could deal with the correlations between different points and different channels in ψ( 2S ) scan experiment .

针对当前的D-S证据模型未考虑或未充分考虑信息源可信度的问题，提出一种分步建模方法，利用开放框架下提出的似然函数折扣策略修正证据模型。

To solve the problem that the current evidence model does not or not fully consider the credibility , the sensor credibility is integrated into the evidence model by plausibility discount strategy .

其次，在TBM上定义一对Rough算子，并讨论其性质，然后通过这对Rough算子，对TBM中的信任函数和似然函数进行了Rough集解释。

Secondly , we define a pair of Rough operators on the TBM and give some of the properties of them . We then use the pair of Rough operators to interpret belief functions and plausibility functions on the TBM .

首先，从最简单的时间序列AR模型入手，分析了时间序列AR模型的统计结构及其条件似然函数，根据似然函数构造了模型参数的共轭先验分布。

Firstly , we begined with the simplest AR model , and analyzed its mathematical model and condition likelihood function . According to its statistical structure of likelihood function , constructed their Bayesian estimation under the normal-Gamma conjugate prior distribution .

EM算法的一般收敛理论认为，算法只能收敛到似然函数的一个局部极大解，无法保证能够收敛到与样本的真实参数相一致的解上。

It follows from the general convergence theory that the EM algorithm generally converge to a local maximum solution of the likelihood function and cannot be guaranteed to converge to a correct solution , i.e. , a consistent solution of the samples .

概述了GLM形式和假定，介绍了LARS-Lasso方法和GLM的似然函数Lasso惩罚估计。

This paper outlines GLM function form and its assumptions , introduces the LARS-Lasso method and the estimate method of ML based on Lasso punish of GLM .

该算法首先采用基于核函数的非参数方法估计SAR图像的统计分布，然后将此统计量作为图像分割的似然函数，利用马尔可夫上下文约束进行SAR图像分割。

First , a non-parametric density estimate method based on kernel function is adopted to estimate the statistic distribution of the SAR images , and then , the SAR images is segmented with Markovian contexture by maximizing a MAP estimator , taking the former estimation as its likelihood term .

描述了一种新的机动目标非线性跟踪算法（简称NLF算法），提出了合理了机动似然函数，导出了机动概率估值方程。

This paper describes a new nonlinear filtering algorithm ( NLF ) for tracking maneuvering targets , presents reasonable maneuvering likelihood function , derives estimating equations .

该方法在粒子滤波框架下，以可控波束形成（SBF，SteeredBeamForming）作为了观测信息，通过SBF函数来构建似然函数，从而实现了声源的跟踪和定位。

The method based on the particle filter framework , with steered beam forming ( SBF ) as the observation information , through the SBF function to construct the likelihood function , so as to realize the sound source tracking and positioning .

本文给出了PARMA模型的似然函数及模型参数的估计方法，引入了观测方程构成改进模型，并提出了偏态修正方法。

In this paper , the likelihood function and parameter estimation for periodic autoregressive-moving average ( PARMA ) model are given . An observation equation is added to constitute a modified PARMA model and the method for the skew-revision is also presented .

然而，Wishart自回归模型含有潜在状态变量，使得在参数估计过程中面临高维积分问题，难以得到似然函数的闭合表达式，导致一般的参数估计方法失效。

However , latent variables was contained in the models , what leads to high-dimensional integration , so we can not obtain closed form expressions of the likelihood function of Wishart regression model , thus many general parameter estimation methods result in failure .

本文基于贝叶斯理论的框架，联合应用似然函数及先验随机约束信息进行AVO地震参数反演，所获取的反演参数是后验概率分布函数（PPDF）的最可能解。

Based on the framework of Bayes theory , the paper combines application of likelihood function and prior stochastic constrain information to carry out the inversion of AVO seismic parameter , and acquired inversed parameter is probable solution of posterior probability distribution function ( PPDF ) .

文章针对股票市场的超高频持续期序列，提出了长记忆随机条件持续期模型（LMSCD），并给出了模型参数的极大谱似然函数估计方法。

This paper puts forward a long memory stochastic conditional durations ( LMSCD ) model for ultra-high frequency ( UHF ) durations series , and provides a kind of spectrum likelihood estimation method .

将Elston模型应用于质量数量性状分析，提出采用似然函数分析质量数量性状的尺度效应、主基因分离比例、主基因效应以及微基因效应的方法。

Elston 's model with some modifications and extensions was applied to genetic study of qualitative-quantitative traits . The likelihood methods were used for the analysis of scale effect , segregation ratio and effects of major genes , as well as effects of polygenes .

先验概率和似然函数未知时的分布式检测融合

Optimal distributed detection fusion with unknown priori probabilities and likelihood functions

定时截尾数据缺失场合下指数分布的似然函数的近似

Approximation for the Likelihood Function of Exponential Distribution under Multiply Type-I Censoring

一种新模糊似然函数在聚类分析中的应用

Application of a New Fuzzy Likelihood Function on Clustering Analysis

重指数族与推广的准似然函数间的关系

The relationship between double exponential family and extended quasi - likelihood function

基于似然函数的纵向数据线性混合模型影响分析

Likelihood-based influence analysis in linear mixed models for longitudinal data

模态参数的一种统计识别方法&极大似然函数估计法

A statistic method for identification of modal parameters & maximum likelihood estimation method