You are on page 1of 13

Learning Objectives:

 To be able to describe the homogeneity or heterogeneity of the distribution or

scores.

 To be able to calculate common measures of dispersion from ungrouped and

grouped data.

 To calculate and interpret the coefficient of variation.

Measures of Dispersion

 Also known as Measures of Variability

 Describes how the sets of observation are dispersed, scattered or spread.

 The degree, to which the individual values of the distribution scatter away from

the the central value, is called dispersion.

I. Absolute Measure of Dispersion

 It gives an idea about the amount of dispersion/spread in a set of observations.

 These quantities measure the dispersion in the same units as the units of original

data.

 Absolute measures cannot be used to compare the variation of two or more

series/data set.

 A measure of absolute dispersion does not in itself, tell whether the variation is

large or small.

A. Range (R)

 Difference between the highest score and the lowest score.

Interpretation of Range:

 If the range is large, the scores are more dispersed or heterogeneous.

 If the range is small, the scores are less dispersed or less scattered or

homogeneous.

Properties of Range:

 used when the score distribution is normal

 used when the data are in interval or in ratio level of measurement

 used when quick answer is needed


 rough estimation of variation or dispersion

 easily affected by extreme scores

 quick and easy to understand

 only two scores are needed to compute the value of range

 very easy to compute

Range from Ungrouped Data

𝑹 = 𝑿𝑵 − 𝑿𝟏

Where:

𝑹 is the range

𝑿𝑵 is the highest score

𝑿𝟏 is the lowest score

Range from Grouped Data

𝑹 = 𝑿𝑼 − 𝑿𝑳

Where:

𝑹 is the range

𝑿𝑼 is the upper boundary of highest score class

𝑿𝑳 is the lower boundary of lowest score class

B. Inter-Quartile Range (IQR)

 It refers to the distance between the third quartile and the first quartile.

a. First Quartile (Q1)

 Also known as lower quartile

 The middle number between the smallest number and the median of the data set

(25th Percentile).

First Quartile from Grouped Data

𝟏
𝑵−𝑭
𝑸𝟏 = 𝑳 + (𝟒 )𝒊
𝒇
Where:

𝑸𝟏 is the First Quartile 𝒇 is the frequency of the class median

𝑵 is the total frequency 𝒊 is the class interval

𝑭 is the cumulative frequency before 𝑳 is the lower boundary of the class

class median median

b. Second Quartile (Q2)

 The median of the data that separates the lower and upper quartile (50 th

Percentile).

c. Third Quartile (Q3)

 Also known as upper quartile

 The middle value between the median and the highest value of the data set (75 th

Percentile).

Third Quartile from Grouped Data

𝟑
𝑵−𝑭
𝑸𝟑 = 𝑳 + (𝟒 )𝒊
𝒇

Where:

𝑸𝟑 is the First Quartile 𝒇 is the frequency of the class median

𝑵 is the total frequency 𝒊 is the class interval

𝑭 is the cumulative frequency before 𝑳 is the lower boundary of the class

class median median

Interpretation of Inter-Quartile Range:

 The larger the value of IQR, the more dispersed the scores are from the median

value.

 The smaller the value of IQR, the more clustered the scores are from the median

value.

Properties of Inter-Quartile Range:

 used when the data are in ordinal level of measurement

 used when the frequency distribution is irregular or skewed


 reduces the influence of the extreme scores

 considers only the middle 50% of the scores of distribution

 not easy to calculate as compared to range

 the point of dispersion of the scores is the median value

Inter-Quartile Range

𝑰𝑸𝑹 = 𝑸𝟑 − 𝑸𝟏

Where:

𝑰𝑸𝑹 is the inter-quartile range

𝑸𝟑 is the third quartile

𝑸𝟏 is the first quartile

C. Quartile Deviation (QD)

 It refers to the average deviation of the third quartile and the first quartile from the

value of the median

Interpretation of Quartile Deviation:

 The larger the value of QD, the more dispersed the scores are from the median

value.

 The smaller the value of QD, the more clustered the scores are from the median

value.

Properties of Quartile Deviation:

 used when the data are in ordinal level of measurement

 used when the frequency distribution is irregular or skewed

 reduces the influence of the extreme scores

 considers only the middle 50% of the scores of distribution

 not easy to calculate as compared to range

 the point of dispersion of the scores is the median value

Quartile Deviation

𝑸𝟑 − 𝑸𝟏
𝑸𝑫 =
𝟐
Where:

𝑸𝑫 is the quartile deviation

𝑸𝟑 is the third quartile

𝑸𝟏 is the first quartile

D. Mean Deviation (MD)

 Also known as Average Deviation

 It is the sum of absolute deviations of the arithmetic mean divided by the number

of cases or students.

Interpretation of Mean Deviation:

 The larger the value of MD, the more dispersed the scores are from the mean

value.

 The smaller the value of MD, the more clustered the scores are from the mean

value.

Properties of Mean Deviation:

 It takes its minimum value when the deviations are taken from the median

 It remains unchanged due to unchanged of origin but it changes in the same ratio

due to a change in scale

 It is easy to understand and compute

 It is less affected by extreme values as compared to standard deviation

 The signs of deviation are taken as positive

 It tells us how far, on average, all values or scores are from the average

 The deviation can be taken from the mean or median.

Steps in Getting the Mean Deviation from Ungrouped Data

Step 1: Calculate the Mean of the scores

Step 2: Find the absolute difference between each score and the mean

Step 3: Find the sum of all the absolute differences of each score and mean (add the

result in step 2)

Step 4: Apply the formula of getting mean deviation from ungrouped data
Mean Deviation from Ungrouped Data

̅|
∑|𝑿 − 𝑿
𝑴𝑫 =
𝑵

Where:

𝑴𝑫 is the Mean Deviation 𝑵 is the number of cases or students

̅ | is the sum of deviations of scores from the mean regardless of algebraic signs
∑|𝑿 − 𝑿

Steps in Getting the Mean Deviation from Grouped Data

Step 1: Calculate the Mean of the scores

Step 2: Look for the Midpoint of each class limit

Step 3: Find the absolute difference between midpoint and the mean

Step 4: Multiply frequency by the absolute difference of midpoint and mean (multiply the

result in step 3 to the frequency)

Step 5: Find the sum of all the product of frequency and differences of midpoint and

mean (add the results in step 4)

Step 4: Apply the formula of getting mean deviation from grouped data

Mean Deviation from Grouped Data

∑ 𝒇|𝑿̇ − 𝑿
̅|
𝑴𝑫 =
𝑵

Where:

𝑴𝑫 is the Mean Deviation 𝑵 is the number of cases or students

∑ 𝒇|𝑿̇ − 𝑿
̅ | is the sum of the difference of the midpoints and mean times the frequency

E. Variance

 It is the square of Standard Deviation

Steps in Getting Variance from Ungrouped Data Using Machine Formula

Step 1: Calculate the square of each score

Step 2: Find the sum of all the scores

Step 3: Find the sum of the squares of the score (add the results in step 1)
Step 4: Calculate the Correction Factor (𝒀) using the formula

(∑ 𝑿)𝟐
𝒀=
𝑵

Where, 𝒀 is the correction factor; ∑ 𝑿 is the sum of all scores; and 𝑵 is the number of

cases (or student).

Step 5: Apply the formula for getting the variance for ungrouped data using machine

formula

Variance from Ungrouped Data (Machine Formula)

∑ 𝑿𝟐 − 𝒀
𝑺𝟐 =
𝑵−𝟏

Where:

𝑺𝟐 is the Variance 𝒀 is the correction factor

∑ 𝑿𝟐 is the sum of the squares of scores 𝑵 is the number of cases

Steps in Getting Variance from Ungrouped Data Using Working Formula

Step 1: Calculate the Mean of the scores

Step 2: Find the difference between the scores and the mean

Step 3: Find the square of the difference between the scores and the mean (find the

square of the results in step 2)

Step 4: Find the sum of the squares of the difference between the scores and the mean

(find the sum of the results in step 3)

Step 5: Apply the formula for getting the variance for ungrouped data using working

formula

Variance from Ungrouped Data (Working Formula)

̅ )𝟐
∑(𝑿 − 𝑿
𝑺𝟐 =
𝑵−𝟏

Where:

𝑺𝟐 is the Variance

̅ )𝟐 is the sum of the squared difference of the score and mean


∑(𝑿 − 𝑿

𝑵 is the number of cases


Steps in Getting Variance from Grouped Data Using Midpoint Method

Step 1: Look for the midpoint of each classes of scores

Step 2: Find the square of the midpoint

Step 3: Multiply the frequency by the midpoint

Step 4: Multiply the frequency by the squares of the midpoint

Step 5: Find the sum of the products of the frequency and midpoint (add the results in

step 3)

Step 6: Find the sum of the products of frequency and squares of the midpoint (add the

results in step 4)

Step 7: Apply the formula for getting the variance for grouped data using midpoint

method

Variance from Grouped Data (Midpoint Method)


𝟐
𝟐
𝑵(∑ 𝒇𝑿̇𝟐 ) − (∑ 𝒇𝑿̇)
𝑺 =
𝑵𝟐 − 𝑵

Where:

𝑺𝟐 is the Variance

∑ 𝒇𝑿̇𝟐 is the sum of the products of frequency and square of the midpoints

∑ 𝒇𝑿̇ is the sum of the products of frequency and midpoints

𝑵 is the number of cases

Steps in Getting Variance from Grouped Data Using Class Deviation Method

Step 1: Choose an arbitrary temporary origin in any of the class limits either at the

bottom, center or top

Step 2: Assign coded values to the class limit, starting with zero at the origin and with

positive values above zero deviation and negative values below the origin

Step 3: Find the square of the coded values

Step 4: Multiply the coded values by the frequency

Step 5: Multiply the squares of coded values by the frequency


Step 6: Find the sum of all the products of coded values and frequency (add the results

in step 4)

Step 7: Find the sum of all the products of the square of coded values and frequency

(add the results in step 5)

Step 8: Apply the formula for getting the variance for grouped data using class deviation

method

Variance from Grouped Data (Class Deviation Method)

∑ 𝒇𝒅𝟐 (∑ 𝒇𝒅)𝟐
𝑺𝟐 = 𝒊𝟐 −
𝑵 − 𝟏 𝑵𝟐 − 𝑵

Where:

𝑺𝟐 is the Variance

∑ 𝒇𝒅𝟐 is the sum of the products of frequency and square of the midpoints

∑ 𝒇𝑿̇ is the sum of the products of frequency and midpoints

𝑵 is the number of cases

F. Standard Deviation

 It refers to the average distance that deviates from the mean value.

 It is the square root of the variance.

Interpretation of Standard Deviation:

 If the value of standard deviation is large, on the average, the scores in the

distribution will be far from the mean. Therefore, the scores are spread out

around the mean value. The distribution is also known as heterogeneous.

 If the value of standard deviation is small, on the average, the scores in the

distribution will be close to the mean. Hence, the scores are less dispersed or the

scores in the distribution are homogeneous.

Properties of Standard Deviation:

 used when the data are in interval or in ratio level of measurement

 used when the frequency distribution is regular, symmetrical, or normal

 the most important measure of variation or dispersion


 the most commonly used measure of variation, particularly in research

 shows variation of the individual scores about the mean

Standard Deviation from Ungrouped Data (Machine Formula)

∑ 𝑿𝟐 − 𝒀
𝑺=√
𝑵−𝟏

Where:

𝑺 is the Standard Deviation

∑ 𝑿𝟐 is the sum of the squares of scores

𝒀 is the correction factor which is equal to the square of the sum of scores divided by

the number of cases

(∑ 𝑿)𝟐
𝒀=
𝑵

𝑵 is the number of cases

Standard Deviation from Ungrouped Data (Working Formula)

̅ )𝟐
∑(𝑿 − 𝑿
𝑺=√
𝑵−𝟏

Where:

𝑺 is the Standard Deviation

̅ )𝟐 is the sum of the squared difference of the score and mean


∑(𝑿 − 𝑿

𝑵 is the number of cases

Standard Deviation from Grouped Data (Midpoint Method)

𝟐
√ 𝑵(∑ 𝒇𝑿̇𝟐 ) − (∑ 𝒇𝑿̇)
𝑺=
𝑵𝟐 − 𝑵

Where:

𝑺 is the Standard Deviation

∑ 𝒇𝑿̇𝟐 is the sum of the products of frequency and square of the midpoints

∑ 𝒇𝑿̇ is the sum of the products of frequency and midpoints

𝑵 is the number of cases


Standard Deviation from Grouped Data (Class Deviation Method)

∑ 𝒇𝒅𝟐 (∑ 𝒇𝒅)𝟐
𝑺=𝒊√ −
𝑵 − 𝟏 𝑵𝟐 − 𝑵

Where:

𝑺 is the Standard Deviation

∑ 𝒇𝒅𝟐 is the sum of the products of frequency and square of the midpoints

∑ 𝒇𝑿̇ is the sum of the products of frequency and midpoints

𝑵 is the number of cases

Measures of Dispersion for Ungrouped Data (Using Excel)

Step 1: Open Microsoft Excel

Step 2: Type the Data

Example:

CELL A

1 80

2 77

3 79

4 75

5 75

Step 3: Highlight the data. On the Menu Bar, click Data

Step 4: Under Data, click Data Analysis

Step 5: Wait until the computer displays Data Analysis Window. Click Descriptive

Statistics. Then, click OK

Step 6: Wait until the computer displays Descriptive Statistics. Look for Input. In Input

Range, type $A1:$A5 (as per example above). Click Summary Statistics. Then, click

OK
The computer must display as follows:

Column1

Mean 71.36364

Standard Error 2.014821

Median 73

Mode 75

Standard Deviation 6.682406

Sample Variance 44.65455

Kurtosis -1.07106

Skewness -0.40208

Range 20

Minimum 60

Maximum 80

Sum 785

Count 11

II. Relative Measure of Dispersion

A. Coefficient of Variation (CV)

 It shows a variation relative to the mean.

 It is used to compare two or more groups of distribution of scores.

 It is usually expressed in percent.

 The smaller the value of coefficient of variation, the more homogeneous the

scores are. On the other hand, the higher the value of coefficient of variation, the

more dispersed the scores are in that particular distribution.

The formula for computing the coefficient of variation is.

𝑺
𝑪𝑽 = × 𝟏𝟎𝟎%
̅
𝑿

Where:

𝑺 is the standard deviation ̅ is the mean value


𝑿
Marikina Polytechnic College
Sta.Elena, Marikina

CPE

ASSESSMENT OF LEARNING

MEASURES OF DISPERSION

Prepared and Presented by:


NELIA RIVERA
st
1 SEM / 2017-12018

Submitted to:
MARLON C. ALTICHE

You might also like