A new method for estimating the optimal sample size in generalizability theory based on evolutionary algorithm
Comparisons with three traditional methods
Bibliographic Data
| ID | 19407354 |
|---|---|
| Authors | Guangming Li (0000-0002-2526-8682, South China Normal University), Yue Qin (0000-0002-6480-8311, South China Normal University) |
| Year | 2022 |
| Volume | 54 |
| Issue | 10 |
| Pages | 1262 |
| Publication date | 2022-01-01 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Acta Psychologica Sinica (JOURNAL) |
| Journal identifiers | ISSN: 0439-755X |
| Publisher | China Science Publishing & Media Ltd (PUBLISHER) |
| DOI | 10.3724/sp.j.1041.2022.01262 |
| OpenAlex | W4292857613 |
| Language | EN |
| References cited | 6 |
摘要: 概化理论在心理与教育测量领域应用较广。如何使测量程序在预算限制的情况下达到较优的可靠性是研究者需要考虑的重要问题, 这个问题可以转换为最佳样本量估计的问题。提出了一种基于进化算法的估计概化理论下最佳样本量的新方法——约束进化算法, 并采用模拟研究的方法比较了微分优化法、拉格朗日法、柯西不等式法等三种传统方法与约束进化算法的优劣。结果表明:在两侧面交叉设计、两侧面嵌套设计和三侧面交叉设计中都证明了约束进化算法更具优越性, 建议研究者在今后的研究中优先使用
Algorithm · Data mining · Generalizability theory · Sample size determination · Statistics · Computer Science · Evolutionary Algorithms and Applications · Mathematics · Metaheuristic Optimization Algorithms Research · Neural Networks and Applications
The Dependability of behavioral measurements
Expanding G-Theory Models to Incorporate Congeneric Relationships
The Optimization of Generalizability Studies with Resource Constraints
A Practical Solution to Optimizing the Reliability of Teaching Observation Measures Under Budget Constraints
Maximizing the Coefficient of Generalizability in Decision Studies
The Optimal Size of Material in Psychological Experiment
| Highly cited | No |
|---|