欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
结构方程模型在社会学、教育学、医学、市场营销学和行为学中有很广泛的应用。在这些领域中，缺失数据比较常见，很多学者提出了带有缺失数据的结构方程模型，并对此模型进行过很多研究。在这一类模型的应用中，模型选择非常重要，本文将一个基于贝叶斯准则的统计量，称为L。测度，应用到此类模型中进行模型选择。最后，本文通过一个模拟研究及实例分析来说明厶，测度的有效性及应用，并在实例分析中给出了根据贝叶斯因子进行模型选择的结果，以此来进一步说明该测度的有效性。
英文摘要：
Structural equation models are widely used in social, educational, medical, marketing, and behavioral sciences. In these fields, missing data are commonly encountered. To deal with this problem, structural equation models with missing data have been proposed. In the application of this kind of models, one of the most important issues is model selection. In this paper, we proposed an alternative Bayesian criterion-based method called the Lv measure for model selection of structural equation models with missing data. A simulation study and a real example are presented to demonstrate the efficiency and the application of the Lv measure, and results based on Bayes factor in the real example are also presented to illustrate the performance of the Lv measure for model selection.
同期刊论文项目
同项目期刊论文
Empirical likelihood semiparametric nonlinear regression analysis for longitudinal data with respons
Bayesian analysis of nonlinear reproductive dispersion mixed models for longitudinal data with nonig
Asymptotic properties of maximum quasi-likelihood estimator in quasi-likelihood nonlinear models wit
Protein Sub-Nuclear Localization Based on Effective Fusion Representations and Dimension Reduction A
Research on Prediction of Protein Sub-cellular Location Based on KLDA with Combined Kernel Function.
Weighted Feature Dimensions According to Fisher’s Linear Discriminant Rate and Its Application on Pr
Local Empirical Likelihood Inference for Varying-Coefficient Density-Ratio Models Based on Case-Cont
The Effective Feature Representations by Integrating PseAAC and PSSM for Protein Sub-nuclear Locatio
Empirical likelihood-based inference in nonlinear regression models with missing responses at random
Strong consistency of the maximum quasi-likelihoodestimator in quasi-likelihood nonlinear models wit
A New Feature Extraction Method Based on the InformationFusion of Entropy Matrix and Covariance Matr
Consistency and asymptotic normality of the maximum quasi-likelihood estimator in quasi-likelihood n
Consistency and asymptotic normality of profilekernel and backfitting estimators in semiparametric r
Rate of strong consistency of the maximum quasi-likelihood estimator in quasi-likelihood nonlinear m
Statistical analysis of non-inferiority via non-zero risk difference in stratified matched-pair stud
期刊信息
位置：