作者简介 莱尔·F. 巴曼(Lyle F. Bachman):国际语言测试学会前、语言测试研究终身成就奖获得者、世界知名语言测试专家,美国加州大学洛杉矶分校(UCLA)教授。
安东尼·J. 昆南(Antony J. Kunnan):新加坡南洋国立教育学院教授。
目录 Series Editors Preface Acknowledgements Abbreviations Part Ⅰ: Basic concepts and statistics 1 Basic concepts and terms 2 Describing test scores 3 Investigating relationships among different sets of test scores Part Ⅱ: Statistics for test analysis and improvement 4 Analyzing test tasks 5 Investigating reliability for norm-referenced tests 6 Investigating reliability for criterion-referenced tests Part Ⅲ: Statistics for test use 7 Stating hypotheses and making statistical inferences 8 Tests of statistical significance 9 Investigating validity 10 Reporting and interpreting test scores Bibliography Index Appendices Appendix 1: Statistical tables Table A: Proportions of area under the standard normal curve Table B: Critical values of t Table C: Critical values of F Table D: Critical values of the Pearson product-moment correlation coefficient Table E: Critical values of the Spearman rank-order correlation coefficient Appendix 2: Workbook
精彩内容 The counting approach is used most typically with tasks in which individuals select a response from among several choices that are given, respond along points on a scale, or with items that require completion or short-answers.The judging approach is used typically with tasks that require test takers to produce an extended sample oflanguage, such as in a composition test or an oral interview (see Alderson et al., 1995, Ch.5, and Bachman & Palmer, 1996, Ch.11, for discussions of scoring, or marking, procedures; see Alderson, 1991, and Pollitt, 1991, for discussions of counting and rating as scoring procedures). When we collect our data by observing, rather than by eliciting responses to tasks, we can assign numbers in two ways.One way is to assign numbers to members of groups that have different attributes, such as native language, occupation or academic major, in order to indicate the categories of attributes to which they belong.For example, if the individuals we observe belong to mutually exclusive groups on some attribute, such as native language, we could use numbers to represent the different values of this attribute.Thus, we might use a '1' to represent native speakers of Amharic, a '2' to represent native speakers of Arabic, and so on.Another way to assign numbers to observations is to count the number of occurrences of a particular attribute.
以下为对购买帮助不大的评价