In: Statistics and Probability
The following sample data reflect electricity bills for ten households in Istanbul in April 2020
$118.20 |
$67.88 |
$133.40 |
$88.42 |
$110.34 |
$76.90 |
$144.56 |
$127.89 |
$89.34 |
$129.10 |
Q3a.)
Determine three measures of central tendency for these sample data. Then, based on these measures, determine whether the sample data are symmetric or skewed.
Q3b.)
Compute the range, variance, and standard deviation for these sample data. Discuss which of these three measures you would prefer to use as a measure of variation.
x | Arrange x | x -mean | (x -mean)2 | |
118.2 | 67.88 | -40.723 | 1658.36273 | |
67.88 | 76.9 | -31.703 | 1005.08021 | |
133.4 | 88.42 | -20.183 | 407.353489 | |
88.42 | 89.34 | -19.263 | 371.063169 | |
110.34 | 110.34 | 1.737 | 3.017169 | |
76.9 | 118.2 | 9.597 | 92.102409 | |
144.56 | 127.89 | 19.287 | 371.988369 | |
127.89 | 129.1 | 20.497 | 420.127009 | |
89.34 | 133.4 | 24.797 | 614.891209 | |
n= | 129.1 | 144.56 | 35.957 | 1292.90585 |
10 | Sum= | 1086.03 | 6236.89161 | |
Mean= | 108.603 | 623.689161 | ||
Median= | (5th +6th)/2 | |||
Median= | (110.34+118.2)/2 | |||
Median= | 114.27 | |||
3Median= | 342.81 | |||
2Mean= | 217.206 | |||
Mode = | 3 Md-2Mean | |||
Mode = | 125.604 | |||
sample data are symmetric if | ||||
Mean= | Median= | Mode | ||
Skewed positive if | ||||
Mean > | Median. > | Mode | ||
Skewed Negative if | ||||
Mean < | Median < | Mode | ||
108.603. < | 114.27 < | 125.604 | ||
so sample data are negative skewed | ||||
Range = | Max - Min | |||
Range = | 144.56 -67.88 | |||
Range = | 76.68 | |||
Variance= | Sum of (x -mean)2 /n | |||
Variance= | 623.689 | |||
Standard deviation =sqrt (variance) | ||||
24.97376624 |
A measure of variability is a summary statistic that represents the amount of variation in a dataset.
Measures of Variability: Range, Interquartile Range,Mean deviation , Variance, and Standard Deviation .
For best measure of dispersion we know that
It should be rigidly defined.
For the same data, all the methods should produce the same result.
It should be based on all the items so as to be more representative.
It should be amenable to further algebraic treatment.
It should have sampling stability
Range is not fit for the above properties
So
Standard deviation is considered to be the best measure of dispersion or variation and is thereore, the most widely used measure of dispersion.