Scribd
Upload
2 views7 pages

Understanding Statistical Dispersion

The document discusses the concept of dispersion in statistics, emphasizing its importance in understanding variability within a dataset. It outlines the purpose of measuring dispersion, the properties of a good measure, and different methods for calculating it, including range and quartile deviation. The document also highlights the merits and demerits of these methods, noting that dispersion provides crucial insights beyond just average values.

Uploaded by

simjyochhattani15
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as RTF, PDF, TXT or read online on Scribd
2 views7 pages

Understanding Statistical Dispersion

The document discusses the concept of dispersion in statistics, emphasizing its importance in understanding variability within a dataset. It outlines the purpose of measuring dispersion, the properties of a good measure, and different methods for calculating it, including range and quartile deviation. The document also highlights the merits and demerits of these methods, noting that dispersion provides crucial insights beyond just average values.

Uploaded by

simjyochhattani15
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as RTF, PDF, TXT or read online on Scribd

STATISTICS

DISPERSION
INTRODUCTION :
· It is measure of variation in the items.
· indicates spread of values
· indicates the facts of a given group ,which
lack uniformity in the size.
· without the knowledge of dispersion,once
cannot have a complete idea about the
population.
· for eg : if we know that avg income in a
locality consisting of 100 residents is
10,000. this knowledge is not sufficient to
have an idea about the wealth of society
unless we know the highest,lowest and
other aspects of the sociey ( it's safe to
say that dispersion provides knowledge of
variablity of data from its central value )

PURPOSE:
1. To determine the reliability of average
2. to compare two or more series with
regard to their variability
3. to serve as a basis for control of
variability
4. to facilitate use of other statistical
measures.

PROPERTIES OF A GOOD MEASURE OF


DISPERSION :
5. it should be simple to understand
6. easy to compute
7. not unduly affected by extreme items.
8. based on each and every item of
distribution
9. should be amendable to further algebraic
treatment.
10. should be rigidly defined
11. should have sampling stability
KINDS OF DISPERSION :
12. ABSOLUTE DISPERSION :
· it is expresed in the same unit,the original
data is expressed.
· if series is expressed in terms of marks
obtained then the dispersion would be in
"marks"
· here ,two or more series with diff units
cannot be compared on the basis of
dispersion.
b. RELATIVE DISPERSION / COEFFICIENT
OF DISPERSION :
· ratio of absolute dispersion to an apt avg
· two or more series of diff units can be
compared.

DIFFERENT METHODS OF
CALCULATING DISPERSION :
13. Range
14. Quartile deviation
15. Mean deviation
16. Standard deviation
17. Lorenz curve
1. Range :
· simplest measure of dispersion ,which
provides simple idea of variability.
· range = L- S ( L = greatest obs of data , S
= smallest obs of data )

· coefficient of range =
· if avg of two distributions are same , the
comparison of range indicates that the
distribution distribution with smaller
range has less dispersion, avg of that
distribution is more typical .
MERITS :
· simplest to understand
· easy to compute
· takes minimum time to compute
DEMERITS :
· it is not based on each and every item of
distribution
· not stable
· cannot be computed in case of open
ended distribution
2. Quartile deviation:
· location-based measure of dispersion
· calculates median
· it discards the upper and lower quarter of
items and measures the range in central
half of items.

· Quartile deviation (Q.D.) =


· it is half the diff between third and first
quartile.
· Coefficient of Q.D. =
MERITS:
· it is superior to range as measure of
dispersion ,in certain aspects
· not affected by presence of extreme
values
· has special utility in measuring variation
in case of open ended distribution .
DEMRITS:
· does not depend on every item of
distribution
· not capable of mathematical manipulation
· value is affected by sampling
fluctuatuations
· ignores 50% of items

You might also like