Current location - Education and Training Encyclopedia - Education and training - CVI experts agree, and some scholars put forward Kappa value. 10 How do people realize Kappa with SPSS? The expert's evaluation is level 4.
CVI experts agree, and some scholars put forward Kappa value. 10 How do people realize Kappa with SPSS? The expert's evaluation is level 4.
The first question is generally evaluated by CVI (Content Validity Index).

I-CVI should be greater than 0.78, and S-CVI/Ave should be greater than 0.9.

It is said that Kappa value can be used to evaluate the reliability of retest, and Kappa can be calculated from analysis → descriptive statistics → crosstab → statistics.

The second question, you use it to evaluate the reliability between people, of course.

Concept: Different evaluators use the same tool to evaluate the same object and calculate the correlation coefficient of the results.

Features: The research tool includes two parts: scale and evaluator; The correlation coefficient is between 0 and 1, and the closer to 1, the higher the reliability. It is generally required to be at least greater than 0.6.

Calculation method (see "Reliability Analysis between Evaluators: From Theory to Practice" for details).

Two evaluators; Fixed distance/ratio data; normal distribution

Pearson correlation coefficient (r value)

Two evaluators; Fixed distance/ratio data; Abnormal distribution

Spearman correlation coefficient

Two evaluators; Ordered data

Spearman correlation coefficient

More than three people; Fixed distance/ratio data; normal distribution

Parameter test: ICC

More than three people; Other types of data

Friedman's two-way rank variance analysis

kendall's coefficient of concordance

Relevant literature and teaching material recommendation for reliability and validity test;

Wu. SPSS Statistical Application Practice [M]. Beijing Science Press, 2003:63- 109.

Gui Bao. Reliability analysis between evaluators: from theory to practice [J]. Foreign Language Audio-visual Teaching, 20 10, (132): 2 1-25.

Cohen RJ, Svedik m, Smith DK. Psychological testing and evaluation: an introduction to testing and measurement [M]. California: mayfield tavern,1992:161-168.

Xu Zhijing, Xia Haiou. Application of Delphi method in nursing research [J]. Journal of Nursing Science, 2008,23 (6): 78-80.

Liu Ke. How to check the validity of the content [J]. Journal of Nurse Training, 20 10/0,25 (1): 37-39.

Shi Jing, Mo Xiankun, Sun Zhenqiu. The Application of Content Validity Index in Scale Compilation [J]. Journal of Central South University, 2012,37 (2):152-155.

, Fu. Cultural Trap of Foreign Self-report Scale [J]. Psychological Science, 2000,23 (6): 729-731.

Jiang Yan, Shen Ning, Zou Shufang. Scale development and evaluation method of measurement characteristics in nursing research [J]. China Nursing Education, 2005,2 (4):174-175.

Zhang minqiang. Educational metrology [M]. Beijing: People's Health Publishing House,1998:104-1/kloc-0.

Sun Zhenqiu. Medical statistics [M]. Second edition. Beijing: People's Health Publishing House, 2007: 532-536.

Rod M, Norvik R. Statistical theory of psychological test scores [M]. Fuzhou: Fujian Education Press, 1992:225.

Zhao. Nursing research. Beijing: People's Health Publishing House, 2003:7 1-84.

Fang Jigan. Medical statistics and computer experiments [M]. Second edition. Shanghai: Shanghai Publishing House, 200 1, 239-250.

Dai Haiqi, Zhang Feng, Chen Xuefeng. Psychological education measurement [M]. Guangzhou: Jinan University Press, 2003: 56-68.