ABSTRACT

The purpose of this study is to address the necessity of subscore equating and to evaluate the performance of various equating methods for subtests. Assuming the random groups design and number-correct scoring, this paper analyzed real data and simulated data with four study factors including test dimensionality, subtest length, form difference in difficulty, and sample size. The results indicated that reporting subscores without equating provides misleading information in terms of score profiles and that reporting subscores without a pre-specified test specification brings practical issues such as constructing alternate subtest forms with comparable difficulty, conducting equating between forms with different lengths, and deciding an appropriate score scale to be reported.

摘要

这项研究的目的是解决子计分的必要性，并评估用于子测试的各种计算方法的性能。假设随机分组的设计和正确的评分，本文使用四个研究因素分析真实数据和模拟数据，其中包括测试维度，子测试长度，难度形式差异和样本量。结果表明，不使用等分形式报告子分数会在分数分布方面提供误导性信息，而没有预先指定的测试规范的报告子分数会带来一些实际问题，例如构造难度相当的替代子测试形式，在不同长度的形式之间进行均等并决定适当的分数量表进行报告。