You are on page 1of 16

Health care Statistics

By: Abdelfattah Elbarsha


Measures of Variation
• The purpose of the measures of variations is to know
the amount of dispersion in the variable. By dispersion,
we mean the degree to which the data are spread out.
• Several statistics are used to describe the variation of
data such as:
1. Range (R) 3. Standard deviation (S)
2. Variance ( 𝑆 2 ) 4. Coefficient of variation (C.V)
• The Range ( R )
It’s defined as the difference between the largest and
the smallest values.

• R= H – L

• Although it’s easy to calculate, it takes only into


account the largest and the smallest values, which
makes it a rough measure of variation.
The variance ( 𝑆 2 )
• Variance is based on the deviation from the mean.
The sum of all deviations from the mean must equal
to zero. That is :

The variance is suitable with symmetric data and takes


into account the whole values, but it is expressed in
square units; which is not practical.
Calculating the Variance

The variance in the case of ungrouped data is defined


as the sum of squared deviations from the mean,
divided by the number of observations minus 1 (n-1).
The standard deviation ( S )

• The standard deviation is the best measure of


variation for symmetric data.

• Standard deviation is the square root of the variance,


and its formula is:

𝑆= 𝑆2
Notes
• If a constant value is added or subtracted from the
studied observations, the standard deviation value will
not change.
• 2- If the studied observations are multiplied or divided by
a constant, the standard deviation will change by that
amount.
• 3- We use the standard deviation to compare two data
sets if the data sets have the same unit.
The coefficient of variation ( C.V )
• The coefficient of variation measure the
• percentage of variation in the data relative to the
mean of the data.
• The C.V is useful when we are comparing two data
sets that aren’t exactly alike, especially if the different
data sets aren’t measured using the same units.
• To calculate the C.V we use the formula below:
Uses of C.V

1. When one desires to compare the dispersion in two


sets of data measured in different units.

2. When one desires to compare the dispersion in two


sets of data measured in the same units, but the
two means are quite different.
Example 1

• If the duration of stay for 10 inpatients (in days) is:

3 4 5 7 8 8 9 6 2 14
• Compute the range, variance, standard deviation,
and C.V?
Solution

• The range of the duration of stay is R= H – L = 14 – 2


= 12 days.
• To find the variance, First we must find the mean:
𝑥𝑖 66
𝑋= = = 6.6
𝑛 10
2 2
2
𝑥𝑖 − 𝑥 2 − 6.6 + 3 − 6.6 2 + ⋯ + 14 − 6.6 2
𝑆 = =
𝑛−1 10 − 1
𝑆 2 = 12.04
• We can also use the other formula to find the
variance
𝑛 𝑥𝑖2 − 𝑥𝑖 2
𝑆2 =
𝑛 𝑛−1

𝑥𝑖2 = 22 + 32 + ⋯ + 142 = 544

𝑥 = 2 + 3 + ⋯ + 14 = 66

𝑛 𝑥𝑖2 − 𝑥𝑖 2
10 544 − 66 2
𝑆2 = = = 12.04
𝑛 𝑛−1 10(10 − 1)
• To find the standard deviation we simply take the
square root of the variance

𝑆 = 𝑆 2 = 12.04 ≅ 3.47

3.47
C. V = × 100 = 52.58%
6.6
Example 2
• Suppose two samples of human males have these
result:
Categories Sample 1 Sample 2

Age 35 years 14 years

Mean Weight 75 kg 40 kg

Standard Deviation 7 kg 7 kg

• Which is more variable the weights in sample 1 or


sample 2
Solution
7 7
𝐶. 𝑉(𝑆𝑎𝑚𝑝𝑙𝑒 1) = × 100 = 9.33% 𝐶. 𝑉(𝑆𝑎𝑚𝑝𝑙𝑒 2) = × 100 = 17.5%
75 40

It’s clear that the weights in sample 2 are more spread


than weights in sample 1.
Assignment 4 is posted
Due date is April 21st , 2022

You might also like