教育测量

教育测量是评估学习与能力的理论与实践——涵盖教育测验的设计、评分与效度验证。

Scope

本领域涵盖测验理论（经典测验理论与项目反应理论）、信度与效度、量表化与标准设定，以及测验设计与公平性。

Sub-topics

• Testing Accommodations
• Test Selection
• Test Length
• Achievement Rating
• Educational Indicators
• Growth Models
• Alternative Assessment
• Informal Assessment
• Scoring Rubrics
• Writing Evaluation
• Scoring
• Test Construction
• Failure
• Predictive Measurement
• Criticism
• Observation
• Test Results
• Test Use
• Personality Assessment
• Risk Assessment
• Parent Surveys
• Causal Models
• Control Groups
• Experimental Groups
• Matched Groups
• Sample Size
• Statistical Bias
• Auditory Evaluation
• Success
• Measurement Techniques
• Grade Point Average
• Hypothesis Testing
• Classroom Observation Techniques
• Interaction Process Analysis
• Naturalistic Observation
• Benchmarking
• Comparative Analysis
• Bibliometrics
• Cluster Grouping
• Synthesis
• Correlation
• Predictor Variables
• Cohort Analysis
• Audits (Verification)
• Evaluation Criteria
• Evaluation Utilization
• Data Analysis
• Lesson Observation Criteria
• Replication (Evaluation)
• Transcripts (Written Records)
• Cognitive Measurement
• Task Analysis
• Accuracy
• Measurement
• Network Analysis
• Evaluation
• Comparative Testing
• Multitrait Multimethod Techniques
• National Norms
• Test Format
• Vocational Evaluation
• Standard Setting (Scoring)
• Educational Testing
• Systems Analysis
• Monte Carlo Methods
• Identification
• Confidence Testing
• Guessing (Tests)
• Testing Problems
• Construct Validity
• Content Validity
• Factor Structure
• Semi Structured Interviews
• Structured Interviews
• Test Content
• Critical Incidents Method
• Delphi Technique
• Hierarchical Linear Modeling
• Scores
• Policy Analysis
• Cutting Scores
• Skill Analysis
• Equated Scores
• Raw Scores
• Online Surveys
• Prediction
• Adaptive Testing
• Computer Assisted Testing
• Individual Testing
• Response Style (Tests)
• Test Items
• Testing Programs
• Grade Equivalent Scores
• Error Patterns
• Evaluation Needs
• Evaluation Problems
• Measurement Objectives
• Focus Groups
• Pretesting
• Assessment Centers (Personnel)
• Grade Prediction
• Holistic Evaluation
• Group Testing
• Selection Criteria
• Intelligence Quotient
• Local Norms
• Norms

Core questions

• 如何准确测量学习成效与能力水平？
• 教育测验的信度与效度如何保障？
• 测验应如何评分与量化？
• 如何实现公平的教育评估？

Key concepts

• 信度
• 效度
• 项目反应理论
• 标准设定
• 量化
• 测验公平性

Key theories

心理测量理论

Thorndike奠定了对教育成果进行定量测量的学科基础。

信度

Cronbach的α系数标准化了测验信度的估计方法。

构念效度

Cronbach与Meehl将教育和心理测验的效度理论加以系统化，形成构念效度框架。

History

教育测量从Thorndike的心理测量理论出发，历经经典测验理论（信度、效度）与项目反应理论的发展，现已成为大规模教育评估的核心方法论基础。

Debates

测验分数意味着什么？

构念效度理论将测验分数的诠释重新定义为一种依赖理论、以证据为基础的论证过程。

Key figures

• Edward Thorndike
• Lee Cronbach
• Paul Meehl

Seminal works

• thorndike-1904
• cronbach-1951
• cronbach-meehl-1955

Frequently asked questions

信度与效度有何区别？

信度是测量结果的一致性；效度是测量工具是否真正测量了其所意图测量的内容。