本书的目的在于为教育实践者在考试数据分析中应该使用哪种方法以及如何使用该方法提出具体化和合理化的建议。研究结果有助于提高多组被试测量结果比较的可靠性和有效性，避免在应用传统方法时对参数指数的错误选择所带来的影响，发挥Benjamini Hochberg法和校准法在这方面的潜在优势。

张明才，博士，现为齐鲁师范学院教师教育学院副教授。2020年获美国密歇根州立大学哲学博士学位，专业为测量与数量方法。曾参与美国国家科学基金会和美国教育部等机构的研究项目，并在密歇根州立大学统计培训与咨询中心担任统计分析咨询员。研究方向为项目反应理论和结构方程模型在教育测量中的应用。在Structural Equation Modeling-A Multi-disciplinary Journal、 Reading andWriting、Genetica等SSCI/SCI 学术期刊发表论文多篇。

List of Tables
List of Figures
Chapter 1 An Overview
1.1 Introduction
1.2 Statement of the Problem
1.3 Purpose and Significance of the Study
1.4 Organization of the Book
Chapter 2 Theoretical Background of Measurement N0ninvariance
2.1 Introduction
2.2 The Concept of MI in LVM
2.3 Levels of MI
2.4 Violations of MI
2.5 Methods of Detecting Measurement Noninvariance
2.6 Chapter Summary
Chapter 3 Detection of Measurement Noninvarianee in a Simulated Study
3.1 Introduction
3.2 Simulation Design
3.3 Data Generation
3.4 Data Analysis Procedure
3.5 Evaluation Criteria
3.6 Results of the Simulation Study
3.7 Chapter Summary
Chapter 4 Detection of Measurement Noninvariance in an Empirical Study
4.1 Introduction
4.2 Empirical Dataset
4.3 Data Analysis Procedure
4.4 The Choice of an RI for the FR Method
4.5 Results of the Empirical Study
4.6 Chapter Summary
Chapter 5 Conclusions and Recommendations
5.1 Introduction
5.2 Summary of Findings
5.3 Comments on the Performances of the Three Methods
5.4 Implications and Recommendations
5.5 Limitations
Appendix A Technical Details for the B-H Method
Appendix B Technical Details for the AM Method
References
Postscript