散布的度量表示数据集中的散布量。也就是说,围绕中心值的数据集的值分布得如何(例如,均值/众数/中位数)。它表明数据点趋于与中心值相距多远。
- 价差度量的较低值反映了数据点接近中心值。在这种情况下,数据集中的值更加一致。
- 此外,数据点距中心值的距离,扩展范围越大。但是这里的值并不一致。
使用上面的图,我们可以推断出窄分布表示较低的价差,而宽分布表示较高的价差。
范围
范围是最简单的变化量度。它被定义和计算为数据集的最大值和最小值之间的差。
Range = largest value – smallest value |
- 范围的小值表示数据非常一致,并且大多数数据点都位于均值附近。
- 而较高的范围意味着数据非常不一致,并且数据具有极高的值,并且数据点不位于均值附近。
- 范围未考虑数据集的每个值。因此,它给出了数据集及其可变性的粗略概念。
例子
示例1:给定的数据为:8、10、4、1、15。计算给定数据的范围?
解决方案:
The data in ascending order is = 1 4 8 10 15.
Range = largest – smallest
= 15 – 1
Range = 14
示例2:这些整数的范围是多少?
14,-18、7、0,-5,-8、15,-10、20
解决方案:
The data in ascending order is = -18, -10, -8, -5, 0, 7, 14, 15, 20
Range = largest – smallest
= 20 – (-18)
Range = 38
示例3:计算给定数据的范围:
8、10、5、14、42、3566
解决方案:
The data in ascending order is = 5, 8, 10, 14, 42, 3566
Range = largest – smallest
= 3566 – 5
Range = 3561
中档
中间范围是数据集的最大值和最小值之间的中间值。它被计算为数据集的最大值和最小值的平均值。
Mid-Range = (largest value + smallest value)/2 |
例子
示例1:给定的数据为8、10、5、9、11。计算给定数据的中间范围?
解决方案:
The data in ascending order is = 5 8 9 10 11
Mid-Range = (largest value + smallest value)/2
= (5 + 11)/2
= 16/2
mid-range = 8
示例2:您在一个学期中进行了7次统计测试。您得分94、88、74、84、91、87和79。您的得分中位数是多少?
解决方案:
The scores in ascending order is = 74 79 84 87 88 91 94
Mid-Range = (largest value + smallest value)/2
= (94 + 74)/2
= 168/2
mid-range = 84
示例3:以厘米为单位的8个学生的高度分别为120、132、117、126、110、135、150和143。计算给定数据的中间范围吗?
解决方案:
The scores in ascending order is = 110 117 120 126 132 135 143 150
Mid-Range = (largest value + smallest value)/2
= (150 + 110)/2
= 260/2
mid-range = 130
平均绝对偏差(MAD)
数据集的平均绝对偏差(MAD)是数据集的每个数据点与数据平均值之间的平均距离。即,它表示围绕数据集中的平均值发生的变化量。这也是变化的量度。它被计算为数据集的每个值与平均值之间的绝对差之和的平均值。
MAD = (∑ |xi – mean| ) ÷ n |
其中1
例子
示例1:数据集为11,15,18,17,12,17。计算给定数据集的平均绝对偏差?
解决方案:
Step 1: Calculating the mean
x̅ = (x1 + x2 + x3 + …… + xn) / n
x̅ = (11 + 15 + 18 + 17 + 12 + 17 ) / 6
x̅ = 15
The mean of the given data = 15
Step 2: Calculating the absolute difference between each data-point and mean.
Data-Point |
Absolute Difference from mean |
---|---|
11 |
|11 – 15| = 4 |
12 |
|12 – 15| = 3 |
15 |
|15 – 15| = 0 |
17 |
|17 – 15| = 2 |
17 |
|17 – 15| = 2 |
18 |
|18 – 15| = 3 |
Step 3: Adding the Absolute Difference together
(∑ |xi – mean| ) = 4 + 3 + 0 + 2 + 2 + 3
(∑ |xi – mean| ) = 14
Step 4: Dividing the sum of absolute difference and the number of data-points.
MAD = (∑ |xi – mean|) ÷ n
MAD = 14/6
MAD = 2.33
Hence, we can conclude that, on average, each data-point is 2 distance away from the mean.
示例2:下表显示了每个季节在南希的橙树上生长的橙子的数量
Season |
Number of Oranges |
---|---|
Winter |
5 |
Summer |
17 |
Spring |
24 |
Fall |
10 |
查找数据集的平均绝对偏差(MAD)?
解决方案:
Step 1: Calculating the mean
x̅ = (x1 + x2 + x3 + …… + xn) / n
x̅ = (5 + 17 + 24 + 10) / 4
x̅ = 56/4
The mean of the given data = 14
Step 2: Calculating the absolute difference between each data-point and mean
Data-Point |
Absolute Difference from mean |
---|---|
5 | |5 – 14| = 9 |
17 | |17 – 14| = 3 |
24 | |24 – 14| = 10 |
10 | |10 – 14| = 4 |
Step 3:Adding the Absolute Difference together
(∑ |xi – mean| ) = 9 + 3 + 10 + 4
(∑ |xi – mean| ) = 26
Step 4: Dividing the sum of absolute difference and the number of data-points
MAD = (∑ |xi – mean| ) ÷ n
MAD = 26 / 4
MAD = 6.5
示例3:考虑以下数据集
Name of the student |
Marks in Maths |
---|---|
Chetan | 90 |
Shubham | 74 |
Riya | 80 |
Manu | 92 |
计算给定数据的平均绝对偏差?
解决方案:
Step 1: Calculating the mean
x̅ = (x1 + x2 + x3 + …… + xn) / n
x̅ = (90 + 74 + 80 + 92) / 4
x̅ = 336/4
The mean of the given data = 84
Step 2: Calculating the absolute difference between each data-point and mean
Data-Point |
Absolute Difference from mean |
---|---|
90 | |90 – 84| = 6 |
74 | |74 – 84| = 10 |
80 | |80 – 84| = 4 |
92 | |92 – 84| = 8 |
Step 3: Adding the Absolute Difference together
(∑ |xi – mean| ) = 6 + 10 + 4 + 8
(∑ |xi – mean| ) = 28
Step 4: Dividing the sum of absolute difference and the number of data-points
MAD = (∑ |xi – mean|) ÷ n
MAD = 28 / 4
MAD = 7