应答条目的级数及条目数对量表内部一致性信度影响的研究

A Study on Effects of Numbers of Scale Steps and Items on Internal Consistency Reliability

目的 探讨不同分布下 ,应答条目的级数和条目数对量表的内部一致性信度Cronbach’α系数的影响 ,以期为实践中量表的设计提供参考。方法 用自编程序模拟各种情形下的量表得分 ,进而研究信度变化规律。所有研究均在MATLAB和SPSS10 .0软件上进行。结果 模拟出来的各种情形下的量表得分经过检验 ,与预期设计目的相符。对应于 3、4、5、6、7级式量表 ,满足下列条件 ,可使信度损失不超过 2 % :若为正态分布 ,其条目数分别大于 3 0、2 5、15、10、5 ;若为偏态分布 ,其条目数分别大于 3 5 0、3 5 0、3 5、2 0、10 ;若为均匀分布 ,其条目数分别大于 90、2 5、10、5、5。结论 建立了模拟量表测量结果的方法。可通过选择合适的条目数或级数以获得较高信度。

Objective Explore the effects of the numbers of response items and scale steps on Cronbach' α coefficient under different distributions for giving references to scale design in practice.Methods Scale scores were simulated by programs of MATLAB. Software packages MATLAB and SPSS10.0 were employed in the study.Results The simulated scale scores coincided with the expectations. Changes of reliability under positive and negative skewness distributions showed little differences. To keep the reliability loss less than 2% for 3,4,5,6 and 7-point scales, the numbers of items should be higher than 30,25,15,10 and 5 respectively if the distribution is normal; higher than 350,350, 35,20 and 10 respectively if the distribution is skewed; and higher than 90,25,10,5 and 5 respectively if the distribution is uniform.Conclusion A method of simulating scale scores was proposed. The higher reliability can be obtained by selecting numbers of scale steps and items properly.