对上肢力量类测验项目等值的实证研究
摘要
目的：在体育实践中，一些上肢力量测验常被采纳，如引体向上、屈臂悬垂、双杠屈臂，但相应的评分标准间的等价关系式还没被确定起来。本实验利用等值技术对三个上肢力量类测验项目作实证性研究，确定三者之间的等值关系式，并比较不同等值方法对它们进行等值的准确性和稳健性。
方法：453名大学男生分别进行了三项测验，每项测验间隔一周，测验项目顺序为均衡设计。等值方法包括线性等值、一般的等百分位等值和平滑的等百分位等值。测试数据随机分成两部分：等值样本、交互验证样本。三测验的等值关系式通过等值样本来确定，而各种等值方法的等值精确性和稳健性则由交互验证样本通过RMSD指标来评估。
结果：1)在进行平滑等百分位等值时，平滑模型的选取应视不同的测验项目而定。2)在对三种上肢力量类测验等值的方法中，线性等值方法的效果最好。3)根据本实验得出的三测验间的等值转换表，对照《国家体育锻炼标准》，发现其中的测验评分标准在部分成绩段等值性较好，部分成绩段等值性不太满意。
Objective: A number of upper body strength tests are being frequently employed in testing practice. The equivalence of the standards, however, has not been confirmed. Therefore, the purpose of this study was to determine the equivalence of three upper body strength tests, including pull-up, push-up and flexed-arm hang.
Methods: Three tests are administered to 453 male collegians. Each test was administered in a week apart, and the testing order was counterbalanced. The equating methods included the unsmoothed and smoothing equipercentile equating and linear equating. The collected data were randomly split into two samples: equating sample, cross-validation sample. The equivalent relationships of the tests were determined by equating sample, Using the cross-validation sample, the equating accuracy was evaluated by the index of Root Mean Squared Difference (RMSD).
Results: 1) In smoothing equipercentile equating, smoothing model should be chosen according to different tests. 2) Among the equating method of three upper body strength tests, the linear equating functioned the best. 3) Based on the equivalent relationship derived from this study, the equivalence of the stands was evaluated. It was found that, while the equivalence of some of the standards was well established, the equivalence of others was not satisfactory.
方法：453名大学男生分别进行了三项测验，每项测验间隔一周，测验项目顺序为均衡设计。等值方法包括线性等值、一般的等百分位等值和平滑的等百分位等值。测试数据随机分成两部分：等值样本、交互验证样本。三测验的等值关系式通过等值样本来确定，而各种等值方法的等值精确性和稳健性则由交互验证样本通过RMSD指标来评估。
结果：1)在进行平滑等百分位等值时，平滑模型的选取应视不同的测验项目而定。2)在对三种上肢力量类测验等值的方法中，线性等值方法的效果最好。3)根据本实验得出的三测验间的等值转换表，对照《国家体育锻炼标准》，发现其中的测验评分标准在部分成绩段等值性较好，部分成绩段等值性不太满意。
Objective: A number of upper body strength tests are being frequently employed in testing practice. The equivalence of the standards, however, has not been confirmed. Therefore, the purpose of this study was to determine the equivalence of three upper body strength tests, including pull-up, push-up and flexed-arm hang.
Methods: Three tests are administered to 453 male collegians. Each test was administered in a week apart, and the testing order was counterbalanced. The equating methods included the unsmoothed and smoothing equipercentile equating and linear equating. The collected data were randomly split into two samples: equating sample, cross-validation sample. The equivalent relationships of the tests were determined by equating sample, Using the cross-validation sample, the equating accuracy was evaluated by the index of Root Mean Squared Difference (RMSD).
Results: 1) In smoothing equipercentile equating, smoothing model should be chosen according to different tests. 2) Among the equating method of three upper body strength tests, the linear equating functioned the best. 3) Based on the equivalent relationship derived from this study, the equivalence of the stands was evaluated. It was found that, while the equivalence of some of the standards was well established, the equivalence of others was not satisfactory.
引文
[1] Staples Jane G.,Luzzo,Darrell Anthony. Measurement comparability of paper-and-pencil and multimedia vocational assessment. ACT Research Report Series 1999(1)
[2] 谢小庆．关于HSK等值的试验研究．世界汉语教学，1998(3)：88
[3] 蔡建民．高中会考等值标准分及其应用．第五届全国教育考试科研讨论会论文集，高等教育出版社，1997
[4] 孙玉荣．英语水平考试客观性试题的等值方法．中国考试，1997，5
[5] Kolen M J, Harris D J. Comparison of item preequating and random groups equating using IRT and equipercentile method.JEM, 1990,27(1):27-29
[6] Livingston S A et al. What combination of sampling and equating methods works best ?Applied Measurement in Education, 1990,3(1):73-95
[7] 陈希镇．关于测验等值几个问题的研究．应用概率统计，2000，16(2)：213-219
[9] Zeng L, Kolen M J,et al. Random groups equating program(RAGE, Version 2.0).Iowa City.LA: American College Testing
[10] 许祖慰．项目反应理论及其在测验中的应用．上海：华东师范大学出版社，1992
[11] Cook L L, Peterson N S. Problem related to the use of conventional and item response theory equating methods in less than optimal circumstance. APM,1987,11 (3):225-244
[12] 国家教委考试管理中心统计处．在我国高教英语考试中应用IRT和CTT分数等值的比较研究．中国考试，1992，(3)：30—33
[13] Harris D J, Hoover H D. An application of the three-parameter IRT model to vertical equating. APM,1987,11(2):151-159
[14] Skaggs G, Lissitz R W. IRT test equating: relevant issues and a review of recent research.
Review of Educational Research,1986,56:495-529
[15] Lee.Guemin, Kolen, Michael J., et al. Equating test forms composed of testlets using dichotomous and polytomous IRT models. Annual Meeting of the American Educational Research Association,April, 1998
[16] Bolt DM. Evaluating the effects of multidimensionality on IRT true-score equating. Applied Measurement in Education, 1999,V 12,N4:383-407
[17] Huynh H, Ferrara S. A comparison of equal percentile and partial credit equating for performance-based assessment composed of free-response item.JEM, 1994,31 (2):125-141
[18] Hart T, Kolen M. A comparison among IRT true-and observed-score equating and traditional equipercentile equating. Applied Measurement in Education, 1997,10(2): 105-121
[19] Li Yuan H. An evaluation of multidimensional IRT equating methods by assessing the accuracy of transforming parameters onto a target test metric. Volume 58/11-A of Dissertation Abstracts International:4246
[20] Kolen M J, Brennan R L. Test equating, New York :Springer-Verlag,1995,105-209
[21] Hambleton R K. Item response theory, Boston: Kluwer N ijhoff Publishing,1985:207
[22] 漆书青，戴海崎．项目反应理论及其应用研究．南昌：江西高校出版社，1992：229-235
[23] Baker F B. Ali A. A comparison of two procedures for computer IRT equating coefficients. JEM, 1991,28(2): 147-162
[24] 谢小庆，对15种测验等值方法的比较研究，心理学报，2000，32(2)：217-223
[25] Parshall C G，et al．Equating error and statistical bias in small sample linear equating，JEM，1995,32(1)：37-54
[26] 罗照盛．经典测量理论等值的误差研究．心理科学，2000，23(4)：501
[27] Suanthong, Surintorn. An investigation of factors affecting test equating in latent trait theory. Volume 59/07-A of Dissertation Abstracts International:2465
[28] Yang Wen-ling. The effects of content mix and equating method on the accuracy of test equating using anchor-item design. Annual Meeting of the American Educational Research Association, 1997
[29] Wiley, Andrew. An investigation into two models for equating examinations with multiple item formats.Dissertation Abstracts International: Section B: The Science & Engineering, 1999,Oct, V60(4-B): 1910,
[30] 戴海崎．等值误差理论与我国高考等值的误差控制．江西师范大学学报(哲社版)，1999，32(2)：29-34
[31] 漆书青，戴海崎等．现代教育与心理测量学原理．南昌：江西教育出版社，1998
[32] Livingston S A. Small-sample equating with log-linear smoothing. JEM, 1993,30(1):23-39
[33] Zeng L. Cope R T. Stand error of linear equating for the counterbalanced design, Journal of Educational and Behavioral Statistics, 1995,20(4):337-348
[34] Zeng L. A numerical approach for computing standard errors of linear equating. APM, 1993,17(2):177-186
[35] Zeng L,Hanson B A, Kolen M J. Standard error of a chain of linear equatings.APM, 1994,18(4):369-378
[36] Weimo Zhu. Test equating:what,why, how? Research Quarterly for Exercise and Sports, 1998,V69,N1:11-23
[37] Mchorney CA,Cohen AS. Equating heath status measures with item response theory illustrations with functional status items. Medical Care,2000,V38,N9,Sep:43-59
[38] 李晋裕．《国家体育锻炼标准》的性质、由来与发展．中国学校体育，1996，2：56
[39] 于道中．现行《国家体育锻炼标准》的研制过程与方法．中国学校体育，1996，2：58
[40] 国家体育锻炼标准手册．北京：人民体育出版社，1997，1
[41] 朱雅敏．《国家体育锻炼标准》中跳类项目评分标准差异性的分析．浙江体育科学，2000，22(3)：42-43
[42] 黄永良等．《国家体育锻炼标准》大学男生速度类评分表浅析．浙江体育科学，1998，20(6)：12-14
[43] 马晓东．对《国家体育锻炼标准》中身体素质部分项目评分标准的探讨．北京体育大学学报，1999，22(2)：74-75
[44] 田延等．实施《国家体育锻炼标准》选择项目依据的研究．四川体育科学，1999(1)：43-45
[2] 谢小庆．关于HSK等值的试验研究．世界汉语教学，1998(3)：88
[3] 蔡建民．高中会考等值标准分及其应用．第五届全国教育考试科研讨论会论文集，高等教育出版社，1997
[4] 孙玉荣．英语水平考试客观性试题的等值方法．中国考试，1997，5
[5] Kolen M J, Harris D J. Comparison of item preequating and random groups equating using IRT and equipercentile method.JEM, 1990,27(1):27-29
[6] Livingston S A et al. What combination of sampling and equating methods works best ?Applied Measurement in Education, 1990,3(1):73-95
[7] 陈希镇．关于测验等值几个问题的研究．应用概率统计，2000，16(2)：213-219
[9] Zeng L, Kolen M J,et al. Random groups equating program(RAGE, Version 2.0).Iowa City.LA: American College Testing
[10] 许祖慰．项目反应理论及其在测验中的应用．上海：华东师范大学出版社，1992
[11] Cook L L, Peterson N S. Problem related to the use of conventional and item response theory equating methods in less than optimal circumstance. APM,1987,11 (3):225-244
[12] 国家教委考试管理中心统计处．在我国高教英语考试中应用IRT和CTT分数等值的比较研究．中国考试，1992，(3)：30—33
[13] Harris D J, Hoover H D. An application of the three-parameter IRT model to vertical equating. APM,1987,11(2):151-159
[14] Skaggs G, Lissitz R W. IRT test equating: relevant issues and a review of recent research.
Review of Educational Research,1986,56:495-529
[15] Lee.Guemin, Kolen, Michael J., et al. Equating test forms composed of testlets using dichotomous and polytomous IRT models. Annual Meeting of the American Educational Research Association,April, 1998
[16] Bolt DM. Evaluating the effects of multidimensionality on IRT true-score equating. Applied Measurement in Education, 1999,V 12,N4:383-407
[17] Huynh H, Ferrara S. A comparison of equal percentile and partial credit equating for performance-based assessment composed of free-response item.JEM, 1994,31 (2):125-141
[18] Hart T, Kolen M. A comparison among IRT true-and observed-score equating and traditional equipercentile equating. Applied Measurement in Education, 1997,10(2): 105-121
[19] Li Yuan H. An evaluation of multidimensional IRT equating methods by assessing the accuracy of transforming parameters onto a target test metric. Volume 58/11-A of Dissertation Abstracts International:4246
[20] Kolen M J, Brennan R L. Test equating, New York :Springer-Verlag,1995,105-209
[21] Hambleton R K. Item response theory, Boston: Kluwer N ijhoff Publishing,1985:207
[22] 漆书青，戴海崎．项目反应理论及其应用研究．南昌：江西高校出版社，1992：229-235
[23] Baker F B. Ali A. A comparison of two procedures for computer IRT equating coefficients. JEM, 1991,28(2): 147-162
[24] 谢小庆，对15种测验等值方法的比较研究，心理学报，2000，32(2)：217-223
[25] Parshall C G，et al．Equating error and statistical bias in small sample linear equating，JEM，1995,32(1)：37-54
[26] 罗照盛．经典测量理论等值的误差研究．心理科学，2000，23(4)：501
[27] Suanthong, Surintorn. An investigation of factors affecting test equating in latent trait theory. Volume 59/07-A of Dissertation Abstracts International:2465
[28] Yang Wen-ling. The effects of content mix and equating method on the accuracy of test equating using anchor-item design. Annual Meeting of the American Educational Research Association, 1997
[29] Wiley, Andrew. An investigation into two models for equating examinations with multiple item formats.Dissertation Abstracts International: Section B: The Science & Engineering, 1999,Oct, V60(4-B): 1910,
[30] 戴海崎．等值误差理论与我国高考等值的误差控制．江西师范大学学报(哲社版)，1999，32(2)：29-34
[31] 漆书青，戴海崎等．现代教育与心理测量学原理．南昌：江西教育出版社，1998
[32] Livingston S A. Small-sample equating with log-linear smoothing. JEM, 1993,30(1):23-39
[33] Zeng L. Cope R T. Stand error of linear equating for the counterbalanced design, Journal of Educational and Behavioral Statistics, 1995,20(4):337-348
[34] Zeng L. A numerical approach for computing standard errors of linear equating. APM, 1993,17(2):177-186
[35] Zeng L,Hanson B A, Kolen M J. Standard error of a chain of linear equatings.APM, 1994,18(4):369-378
[36] Weimo Zhu. Test equating:what,why, how? Research Quarterly for Exercise and Sports, 1998,V69,N1:11-23
[37] Mchorney CA,Cohen AS. Equating heath status measures with item response theory illustrations with functional status items. Medical Care,2000,V38,N9,Sep:43-59
[38] 李晋裕．《国家体育锻炼标准》的性质、由来与发展．中国学校体育，1996，2：56
[39] 于道中．现行《国家体育锻炼标准》的研制过程与方法．中国学校体育，1996，2：58
[40] 国家体育锻炼标准手册．北京：人民体育出版社，1997，1
[41] 朱雅敏．《国家体育锻炼标准》中跳类项目评分标准差异性的分析．浙江体育科学，2000，22(3)：42-43
[42] 黄永良等．《国家体育锻炼标准》大学男生速度类评分表浅析．浙江体育科学，1998，20(6)：12-14
[43] 马晓东．对《国家体育锻炼标准》中身体素质部分项目评分标准的探讨．北京体育大学学报，1999，22(2)：74-75
[44] 田延等．实施《国家体育锻炼标准》选择项目依据的研究．四川体育科学，1999(1)：43-45