Sample & Sampling

M Sc Zoology
Semester – II
PAPER – III: QUANTITATIVE BIOLOGY AND COMPUTER
APPLICATION
Unit III.3
 Terms used
• Sample
– is a smaller subset of a larger population.
• A population
– Is the total collection of elements about which we
wish to make some conclusion .
– Any complete group of
• People
• Sales territories
• Stores
 Terms used

• Population Or Universe
– Denotes aggregate of the group of people or items from which the
sample is to be taken.
– the larger group from which individuals are selected to participate
in a study
• A census
– is a count of all the elements in a population.
• In biostatistics “ A group of organism of one species, occupying a
definite and vast area” is known as population.
• Sampling
– The process of using a small number of items or parts of larger
population to make a conclusions about the whole populatio
• Target Population
– The specific , complete group to research project
 Sample
• A sample is“a smaller (but hopefully representative) collection of units
from a population used to determine truths about that population”
(Field, 2005)

• A sample is a smaller unit of group, but containing the properties of

whole population or group.

• A sample is the small collection of the population selected for the

study.

• Sample: a collection consisting of a part or subset of the objects or

individuals of population which is selected for the purpose,
representing the population
 Sampling
• The methodology of sample is known as sampling.
• a collection consisting of a part or subset of the objects or
individuals of population which is selected for the purpose,
representing the population.
• Sampling Frame
– A sample frame is the listing of all population elements from
which the sample will be drawn.
• Sampling Units
– The limited number of the population selected for sampling .
– Group selected for the sample
• Primary Sampling Units (PSU) S
• Secondary Sampling Units
• Tertiary Sampling Units
 Why sampling
• The purpose of sampling :
– The basic objective of the sampling is to draw inference
about the population.
• Sampling- a valid alternative to a census when
– A survey of the entire population is impracticable
– Budget constraints restrict data collection
– Time constraints restrict data collection
– Results from data collection are needed quickl
• Sampling is only tool by which the characteristics of whole
population or universe can be studied by examining a small
part.
• Such values for the population are called parameters.
 Why sampling
• Get information about large populations in
– Lower cost
– More accuracy of results
– High speed of data collection
– Availability of Population elements.
– Less field time
– When it‟s impossible to study the whole
population
 A Good Sample
• The sample must be:
– representative of the population;
– appropriately sized (the larger the better);
– unbiased;
– random (selections occur by chance);
 How to sampling
• The process of sampling
1. Selecting the sample
2. Collecting the information
3. Making a inference about the population
 fundamentals of sampling
• For the good results of study the sampling process
should have following essentials
– Representativeness
• Sample should represent the characteristics of population
• For representativeness random selection of sample should be used.
– Adequate
• The sample should be more enough to make result more reliable.
– Independence
• All the items of the population should be equal chance to selected
as sample.
– Homogeneity
• The sample or selected item should be similar characteristics as
other items in the population.
 Methods of Sampling
• All methods of sampling can be grouped
1. Random or Probability Sampling
a. Simple Random Sampling
b. Restricted Random Sampling
I. Systematic random sample
II. Stratified random sample
III. Cluster sample
2. Non-Random Sampling
a. Convenience samples (ease of access) sample is selected from
elements of a population that are easily accessible
b. Purposive sample (Judgmental Sampling) You chose who you think
should be in the study
c. Quota Sampling
d. Snowball Sampling (friend of friend….etc.)
 Define Population
Determine Sampling Frame

Determine Sampling Procedure

Probability Sampling
1.Simple Random Non Probability Sampling
Sampling 1.Convenient
2.Stratified Sampling 2.Judgmental
3.Cluster Sampling 3. Quota
4.Systematic Sampling 4.Snow Ball Sampling
5.Multistage sampling

Determine Appropriate Sample Size

Execute Sampling Design

 Random Sampling
• Random sampling is
– a method of sampling that uses of random selection so that
all units/ cases in the population have an equal probability of
being chosen
– The law of probability can be applied.
– Selection should be made without deliberate
discrimination.
a. Simple Random Sampling
b. Restricted Random Sampling
• Simple Random Sampling/chance sampling :
– In this method every individual of the population
have an equal chance to be taken as a sample.
– The selection is free from bias.
– There is no preference in choice of items.
– Selection of items as sample depends on chance.
• Sample obtained by following methods in simple
random sampling :
– Lottery
– Table of random number
• Lottery Method :
– Simplest and most popular method
– All the items of population are numbered or named on
slips.
– Folded slips mixed up in a container.
– A blindfold selection is made to choose the slips.
– All the items have an equal chance to be taken as
sample.
– This method is useful for small size population.
• Table of random numbers
– Three type of random number tables are
1. Tippets table of random number
– Table was published by L.H.C. Tippett in 1927.

2. Fisher and Yates numbers

3. Kendall and Babington Smith numbers
• Tippets table of random number
– in this method first to numbered all in population.
– A page of Tippetts table be consulted.
– Desired number of sample may be selected from the
table.
– The selected numbered individuals are the sample.
• Exercies :
» If the total population has 6000 individual and
sampler has to choose forty individual as sample by
random sampling, find out the sample using Tippetts
Table.
– Lets find :
1. Number all individual of population from 01 to 6000.
2. Consult A page from Tippetts table.
3. Select the forty numbers randomly from table.
4. If the numbers are 2592, 2673,5999,4567, 6831,
4321, 1057, 2034, 4386, 1876, 4361, 5386, 5813,
2351, 0137, 4164, 3571, 6351, 6813, 1891, 3468,
4315, 1354, 5326, 1352, 4621, 3621, 1362, 0325,
3623, 0113, 3603, 5340, 3201, 3521, 5034, 5310,
1035,2035,4301.
5. The individual bearing abovr selected numbers will
be the sample.
 Merits and Limitations of random sampling

• Merits • Limitations
– Less cost – Not used in Small
– Best for Infinitive Population.
Population – Chance of inaccurate and
– More reliable results Misleading sampling.
– May biased.
– The destructive nature
of certain tests.
Restricted Random Sampling

1. Systematic Sampling

2. Stratified Sampling

3. Cluster Sampling
 Restricted Random Sampling

• Systematic Sampling :
– Used in the population with complete sampling unit or
Total size of population or list are available.
– every KTh item from list is to be selected.
– K refers to sampling interval calculeted by
K = Size of the universe / Sample Size
K=N/n
• Exercise :
– Find out the 50 sample, from a cage containing 500
rabbits population.
• Find out the value of
– K = Size of the universe / Sample Size
K=N/n
– K = 500 / 50 = 10
– K = 10 it means we must take every 10th item as sample.
– Than the first item between 1 to 10 should be selected
at random.
– Suppose its 4th.
– Now go on adding 10 on 4 and obtain numbers of next
sample.
– It will be 14th
– And next will be 24th , 34th, and so on.
 Limitation of systematic sampling
• If the population are sufficiently large,
homogeneous and each unit is numbered
then the systematic sampling can give
accurate result.
• But when the population is not homogeneous
we should go through Stratified Sampling.
 Stratified sampling
• Used for non homogeneous group data.
• Firstly divide the population in homogeneous
groups.
• The groups are Called class or Stratas.
• Then draw the sample from each strata by
random selection in proportion to size of
strata.
• If a population is divided in to four strata
of
1. 15 %
2. 10%
3. 20% and
4. 55%
the total size of sample is 1000 to be
drawn.
• The desired proportional sample for each strata is
to be
– From strata 01, 15 % of 1000 is = 150 (15/100 x 1000)
– From strata 02, 10 % of 1000 = 106
– From strata 03, 20% of 1000 = 200
– From strata 04, 55% of 1000 = 550
total 1000
 Cluster sampling
• A cluster is randomly selected group.
• Used when units of population are natural.
– Such as
• Hospital wards
• Slums of a town
• Schools of fishes
• First the sampling frame is broken up into groups.
• The population is divided into subgroups (clusters) like
families.
• Then a sample of groups is randomly picked out of all the
groups.
• the people or individual in those groups are randomly
sampled.
 Non Random Sampling
• An item has unequal chance to being selected in the sample.
• The sample are selected for specific purpose with pre
determined basis of selection.
• The sample is not a proportion of the population.
• There is no system in selection of sample, the selection
depends upon the situation.
• No assurance to each item has a chance to being selected as
sample.
• The choice of item to be selected as sample depends
exclusively on the judgment of investigator.
• This method is not applied in scientific research.
 Non Random Sampling
• Non-Random Sampling can be divided into

– Judgement Sampling,

– Convenience Sampling and

– Quota Sampling as detailed below.

– Snow Ball Sampling

– Purposive Sampling
• JUDGEMENT SAMPLING
– In this method, the selection of sample is done by
the researcher according to his judgement.
– For example -
– if a manufacturer wants to study the
performance of the dealers of his product in a
State, and fixes the sample size at 50, he may
select any 50 dealers who in his opinion
represent the total number of dealers in the
State.
• Convenience sampling
– Most easily available (Workplace, Students, Wards of
hospital, etc.)
– In this case, the researcher selects the sample according to
his convenience.
– For example, a marketer who wants to study the behavior of
buyers on the basis of a sample study may pick up the
sample from the nearby market.
– Another example is when you see someone on a
street corner randomly stopping people by your
convenience to do a survey.
– In Convenience sampling it is difficult to make
inferences to the population at large.
– Quota Sampling
• Sample is selected according to a quota
system.
• Sample taken from different places such as 5
students from each class of a school.
• For example, in a study on the impact of Smart
phone, and fixed the sample size at 100, he
may contact 30 housewives, 20 working
women, 30 men and 20 college students.
–Purposive Sampling
• For any specific purpose the investigator
has selected the items.
• i.e. To finding out the occurrence of Pied
Starling, Common Myna and Brahmini
Starling the investigator will select the
only three birds as sample not other birds
on the same field.
–Snow Ball Sampling
• Investigator wants to study of people in a
city who have a lots of power in the area
of educational policy making.
• Researcher asks participants to identify
others to become member of the sample.
THANK YOU