导语

  

内容提要

  

    本研究的主要目的是：1）完成计算机自适应测试的大型题库的构建，该题库包括以下三种题型：完形填空、语法选择题、词汇选择题。在内容方面，该题库涵盖英语专业四级考试（TEM-4）要求的所有语法知识点和考试大纲所要求的所有词汇。2）在题库的基础上设计一个计算机自适应英语测试系统，并采用“评估使用论证”（Assessment Use Argument,简称AUA）对该测试进度效度验证。

List of Symbols and Abbreviations
Chapter 1  Introduction
  1.1  Research Background
  1.2  Research Objective
  1.3  Research Questions
  1.4  Research Methods
Chapter 2  Literature Review
  2.1  Item Response Theory
    2.1.1  History ofIRT
    2.1.2  Basic Assumptions of IRT
    2.1.3  Dichotomous IRT Models
    2.1.4  Polytomous IRT models
    2.1.5  A Comparison between IRT and CTT
  2.2  Computerized Adaptive Testing
    2.2.1  Introduction
    2.2.2  Working Procedure
    2.2.3  IRT Model
    2.2.4  Item Pool
    2.2.5  Item Selection
    2.2.6  Ability Estimation
    2.2.7  Stopping Rule
  2.3  Validation of both PPLT and CALT
    2.3.1  PreviouS Research on Test Validation
    2.3.2  New AUA Framework
  2.4  Current Research on CALT
    2.4.1  Studies Abroad
    2.4.2  Domestic Studies
  2.5  Implication for This Study
Chapter 3  Item Bank Construction
  3.1  Introduction
  3.2  Methods
    3.2.1  Original Data Analysis
    3.2.2  Instruments
    3.2.3  Procedures
    3.2.4  Data Analysis
  3.3  Results and Discussions
    3.3.1  Uni-dimensionality Assumption
    3.3.2  Local Independence Assumption
    3.3.3  Item Calibration
    3.3.4  DIF Analysis
    3.3.5  Resuhs for Item Bank Distribution
    3.3.6  Discussion under the AUA Framework
  3.4  Conclusion
Chapter 4  Design, Operation and Validation of a CALT System
  4.1  Introduction
  4.2  Methods
    4.2.1  CALT Design Overview
    4.2.2  Participants
    4.2.3  Instruments
    4.2.4  Procedures
    4.2.5  Data Analyses
  4.3  Results and Discussions
    4.3.1  Construct Measured by the CALT and CBLT
    4.3.2  Influence of Computer Familiarity
    4.3.3  Factorial Invariance of the CALT across Gender
  4.4  Discussion in the Context of the AUA
  4.5  Conclusion
Chapter 5  Conclusions
  5.1  Findings
  5.2  Implications
    5.2.1  Theoretical Implications
    5.2.2  Practical Implications
  5.3  Suggestions for Future Research
References
Appendix 1
  A sample paper of the Computer-based English proficiency test
  Part Ⅰ  Cloze
  Part Ⅱ  Grammar Multiple Choice
  Part Ⅲ  Vocabulary Multiple Choice
Appendix 2
  A sample score report of the Computer—adaptive English proficiency test
  考试成绩报告
  分数解释
Appendix 3
Appendix 4