Semi-parametric mixture models: algorithms, prediction, fit assessment, model comparison

半参数混合模型：算法、预测、拟合评估、模型比较

• 批准号: RGPIN-2020-07079
• 负责人: Lesperance, Mary
• 金额: $ 1.53万
• 依托单位: University of Victoria
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=718672
• 关键词: Semi; parametric; mixture; models; algorithms

Generalized linear mixed models (GLMMs) are an extension of generalized linear models that introduce random effects to the linear predictor. They are widely used in various fields, from longitudinal data analysis, epidemiology to image processing, ecology and environmental sciences. GLMMs are useful models for analyzing repeated measurements and clustered observations, as the random effects can account for the heterogeneity between subjects and the correlations within clusters. The majority of estimation methods that have been developed for GLMMs are based on the normality assumption of random effects. This assumption provides a convenient way to estimate the fixed effects but may compromise estimation efficiency. This research plan proposes to investigate algorithms, inferential methods, predictions, goodness-of-fit, model selection and identification for GLMMs that do not impose parametric assumptions for the random effects.

广义线性混合模型（GLM）是广义线性模型的扩展，它将随机效应引入线性预测因子。它们广泛应用于各个领域，从纵向数据分析，流行病学到图像处理，生态学和环境科学。GLSTs是分析重复测量和聚类观察的有用模型，因为随机效应可以解释受试者之间的异质性和聚类内的相关性。 大多数已开发的GLP10的估计方法是基于随机效应的正态性假设。该假设提供了一种方便的方法来估计固定效应，但可能会损害估计效率。本研究计划提出了研究算法，推理方法，预测，拟合优度，模型选择和识别的GLCLT，不强加参数假设的随机效应。