Linear mixed model for longitudinal data, has empirical best linear unbiased predictor of subpopulation total proposed under longitudinal model where temporal and spatial moving average models of profile specific random components are considered into account
	RAMACHANDRAN V; CHIDAMBARAM K; NAVEENCHANDRAN P; SUNDARARAJ M; HUSSAIN H J; BABU V R; SUNDARARAJAN M; RAJU V B K; SUDHA B
	2023-10-16
专利权人	BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
申请日期	2023-10-16
专利号	IN202341069499-A
成果简介	NOVELTY - The model has an empirical best linear unbiased predictor of a subpopulation total which is proposed under a longitudinal model where temporal and spatial moving average models of profile specific random components are considered into account and two estimators of mean square error of predictor. The smallest values of Akaike information criterion (AIC) and Bayesian information criterion (BIC) criteria are compared with other analyzed models. The accuracy of the proposed predictor and biases of A proposed mean squared error (MSE) estimators are analyzed in two Monte Carlo simulation studies based on the artificial and the real data. The simulation studies biases of the proposed MSE estimator is small. USE - Linear mixed model for longitudinal data. Can also be used in different areas e.g. genetics, insurance and statistical image analysis. ADVANTAGE - The model achieves sampling estimation or prediction of population characteristics, increases accuracy, defines profile as a vector of random variables for a population element in different periods and for observations of an element in some domain, changes population in time, considers super population models used for longitudinal data which are special cases of large language model (LMM) and analyzes accuracy of the proposed predictor and biases of the proposed MSE estimators in two Monte Carlo simulation studies.
IPC 分类号	G06F-017/18 ; G06N-020/00 ; G06N-005/00 ; G06Q-050/00 ; G09B-019/00
国家	印度
专业领域	信息技术
语种	英语
成果类型	专利
文献类型	科技成果
条目标识符	http://119.78.100.226:8889/handle/3KE4DYBR/19617
专题	中国科学院新疆生态与地理研究所
作者单位	BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
推荐引用方式 GB/T 7714	RAMACHANDRAN V,CHIDAMBARAM K,NAVEENCHANDRAN P,et al. Linear mixed model for longitudinal data, has empirical best linear unbiased predictor of subpopulation total proposed under longitudinal model where temporal and spatial moving average models of profile specific random components are considered into account. IN202341069499-A[P]. 2023.

条目包含的文件
条目无相关文件。

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。