统计 - 信度系数



通过对相同个体进行两次测量并计算两组测量的相关性来获得的测试或测量仪器准确性的度量。

信度系数的定义和计算公式如下:

公式

${信度系数,RC = (\frac{N}{(N-1)}) \times (\frac{(总方差 - 方差和)}{总方差})}$

其中:

  • ${N}$ = 任务数量

示例

问题陈述

一项任务由三个人 (P) 完成,他们被分配了三个不同的任务 (T)。求信度系数?

P0-T0 = 10 
P1-T0 = 20 
P0-T1 = 30 
P1-T1 = 40 
P0-T2 = 50 
P1-T2 = 60 

解答

已知,学生人数 (P) = 3,任务数量 (N) = 3。为了求信度系数,请按照以下步骤操作:

步骤 1

让我们首先计算人员及其任务的平均分数。

The average score of Task (T0) = 10 + 20/2 = 15 
The average score of Task (T1) = 30 + 40/2 = 35 
The average score of Task (T2) = 50 + 60/2 = 55 

步骤 2

接下来,计算方差。

Variance of P0-T0 and P1-T0: 
Variance = square (10-15) + square (20-15)/2 = 25
Variance of P0-T1 and P1-T1: 
Variance = square (30-35) + square (40-35)/2 = 25
Variance of P0-T2 and P1-T2: 
Variance = square (50-55) + square (50-55)/2 = 25 

步骤 3

现在,计算P0-T0和P1-T0,P0-T1和P1-T1,P0-T2和P1-T2的个体方差。为了确定个体方差值,我们需要将所有上述计算出的差异值相加。

Total of Individual Variance = 25+25+25=75 

步骤 4

计算总差异

Variance= square ((P0-T0) 
 - normal score of Person 0) 
 = square (10-15) = 25
Variance= square ((P1-T0) 
 - normal score of Person 0) 
 = square (20-15) = 25 
Variance= square ((P0-T1) 
 - normal score of Person 1) 
 = square (30-35) = 25 
Variance= square ((P1-T1) 
 - normal score of Person 1) 
 = square (40-35) = 25
Variance= square ((P0-T2) 
 - normal score of Person 2) 
 = square (50-55) = 25 
Variance= square ((P1-T2) 
- normal score of Person 2) 
 = square (60-55) = 25 

现在,将所有值相加并计算总差异。

Total Variance= 25+25+25+25+25+25 = 150  

步骤 5

最后,将这些值代入下面的公式中:

${信度系数,RC = (\frac{N}{(N-1)}) \times (\frac{(总方差 - 方差和)}{总方差}) \\[7pt] = \frac{3}{(3-1)} \times \frac{(150-75)}{150} \\[7pt] = 0.75 }$
广告