2. SAMPLING
The aggregate of all the units pertaining to a study is
called the population or universe.
A member of a population is an element / unit of study
A part of the population is called a sample
The process of drawing a sample from a population is
called sampling.
The list of sampling units from which a sample is
taken is called the sampling frame.
4. Characteristics of a Good Sample
True representative of the population.
Accurate – unbiased representation / free from
influence that may cause difference in sample
value & population value.
Precise – smaller the std error / std deviation
the higher the precision.
Adequate size – inference drawn from sample
are accurate to given level of confidence.
5. Steps in Sampling Process
Define Population
Specify Sampling Frame
Specify Sampling Unit
Specify Sampling Method
Determine Sample Size
Selection of the Sample
6. Advantages of sampling
Reduces time & cost of research studies
Saves labour
Quality of study is better
Provides quicker results than census surveys
It’s the only procedure possible if the
population is infinite.
7. Limitations of sampling
Thorough knowledge of sampling methods is
required.
When the characteristic occurs only rarely, a
very large sample is required to give reliable
info. Large sample has all drawbacks of a
census survey.
Complicated sampling require more labour
Not possible to ensure representative sample
always
8. SAMPLING TECHNIQUES/ METHODS
PROBABILITY SAMPLING NON- PROBABILITY SAMPLING
1. Simple random sampling 1. Convenience sampling method
2. Stratified random sampling 2. Purposive /Judgement
3. Systematic random sampling 3. Quota sampling
4. Cluster sampling 4. Snowball sampling
5. Area sampling
6. Multi-stage & Sub sampling
9. RANDOM SAMPLING PROCEDURES
To ensure true randomness the method of selection
must be independent of human judgement.
1. LOTTERY METHOD
- simplest & most familiar.
-Lottery method is useful for drawing small sample
from small population.
-It is time consuming & tedious if population is very
large.
10. 2.TABLE OF RANDOM NUMBERS
Developed by Kendall & Smith/ Fisher & Yates /
Tippett
Easy to use and ready accessibility
Ideal for selecting small sample from small
population.
11. How to use a random number table.
•Let's assume that we have a population of 185 students and each student has been assigned a number from 1 to 185. Suppose we wish to
sample 5 students (although we would normally sample more, we will use 5 for this example).
•Since we have a population of 185 and 185 is a three digit number, we need to use the first three digits of the numbers listed on the chart.
•We close our eyes and randomly point to a spot on the chart. For this example, we will assume that we selected 20631 in the first column.
•We interpret that number as 206 (first three digits). Since we don't have a member of our population with that number, we go to the next
number 899 (89990). Once again we don't have someone with that number, so we continue at the top of the next column. As we work down
the column, we find that the first number to match our population is 100 (actually 10005 on the chart). Student number 100 would be in our
sample. Continuing down the chart, we see that the other four subjects in our sample would be students 049, 082, 153, and 164.
12. 3. USE OF COMPUTERS
When the population is very large, one can print out a series of
random numbers.
13. Gives each element an equal & independent chance of being selected
Equal probability of selection – Epsem sampling
All elements must be included in the sampling frame for a random
sample.
Procedures
Enumeration of all elements in the population
Preparing list and assigning numbers
Drawing sample by using any three random sampling procedures
Suitability:
Homogenous group
Small population
Complete list of all elements is available.
14. Advantages:
All elements have equal chance
Simple & easiest method to apply for sample selection
Easy to understand
Doesn’t require a prior knowledge on the population.
Disadvantages:
Impractical due to non availability of population list
May be wasteful because we fail to use all of the known
information about the population
May be expensive-time and money
Do not ensure proportionate representation to various groups
constituting the population.
15. 2.STRATIFIED RANDOM SAMPLING
The population is sub-divided into
homogenous groups or strata and
sample is drawn from each ‘stratum’
Stratification ensures representation to
all relevant sub groups of the
population
16. THE PROCESS OF STRATIFICATION:
The stratification base to be used should b decided
The number of strata (larger the no. larger d representativeness.
STRATA SAMPLE SIZE :-
A. PROPORTIONATE STRATIFIED SAMPLING
- drawing a sample from each stratum in proportion to its share in the total
population.
Example:
Imagine you would like to interview schools that contract with different vendors
to bring food to their cafeteria. We would expect opinions about cafeteria food to
vary widely from school to school. Therefore, it makes sense to create school
strata to sample from. Suppose the schools are as follows:
School 1: 1050 students
School 2: 565 students
School 3: 1554 students
School 4: 306 students
Total students: 1050 + 565 + 1554 + 306 = 3475 students
The administrator wishes to take a sample of 150 students.
17. Step 1:
The first step is to find the total number of students (3475 above) and calculate
the percent of students in each stratum.
School 1: 1050 / 3475 = .30
School 2: 565 / 3475 = .16
School 3: 1554 / 3475 = .45
School 4: 306 / 3475 = .09
Step 2:
Next, to select a sample in proportion to the size of each stratum (in this case
school), the following number of students should be randomly selected:
School 1: 150 x .30 = 45
School 2: 150 x .16 = 24
School 3: 150 x .45 ~ 67
School 4: 150 x .09 ~ 14
This tells us that our sample of 150 students should be comprised of:
45 students randomly selected from School 1
24 students randomly selected from School 2
67 students randomly selected from School 3
14 students randomly selected from School 4
18. Advantages
Gives proper representation of each stratum, statistical
efficiency is high, easy process.
Disadvantages:
knowledge of traits of population is required,
expensive, time consuming, classification errors may
affect the results.
19. B. DISPROPORTIONATE STRATIFIED SAMPLING
Does not give proportionate representations to strata
It involves overrepresentation to some strata and under
representation to others
Advantages:
Less time consuming compared with proportionate sampling
It facilitates giving appropriate weightage to particular groups ,
which are small but more important
Disadvantages:
Does not give each stratum proportionate representation
Requires prior knowledge of the composition of the population
Subject to classification error
20. 3. SYSTEMATIC SAMPLING / FIXED INTERVAL METHOD
Involves taking of every K th
item in the population
after a random start from 1 to k
Also called Quasi or psuedo-random sampling
Advantages: simpler then random sampling & easy to
use, requires less time & also cheaper, sample is
spread over the population,.
Disadvantages: ignores all elements b/w two k’th
elements, not truly probability sampling technique,
may give a biased sample if by chance every k th
item represent a particular group.
21. Adopted when population
elements are scattered over a wide
area & list of elements is not
readily available.
Cluster has to be heterogeneous in
nature
A few sample clusters will be
selected by unrestricted random
sampling method. These are the
primary sampling units.
4.CLUSTER SAMPLING
22. Single-stage sampling - All elements of these cluster units
are selected for study.
Two-stage sampling - a random sample items are selected
from each cluster.
Multi-stage sampling – extend the above method to more
stages.
Convenient to use when population is scattered or large
Sampling error is greater in this method
23. 5. AREA SAMPLING
. An important form of cluster sampling
clusters are formed on the basis of
geographical areas like districts, taluks,
villages, or blocks etc.
Speed, reliable and complete
enumeration
Expensive and requires complete
listing of households, areas, etc.
24.
25. 6.MULTI STAGE SAMPLING
Another from of cluster sampling
Refers to sampling procedure carried out in several
stages
Population is distributed into a number of first stage
sampling units, and a sample is taken from them
Each of these first sample units is further subdivided
into second stage units, for which sample elements are
selected…….contd….
26. NON- PROBABAILITY SAMPLING
NPS – no equal chance of being selected
Selection probability is unknown
Not representative sample
Suffers from sampling bias
27. 1.CONVENIENCE SAMPLING
Selecting sample in “hit and miss” fashion
Selecting sample unit according to convince
also know as accidental sampling
28. ADVANTAGES
Cheapest and simplest
• Does not require a list of population
• Does not require any statistical expertise
DISADVANTAGES
• Highly biased, because of the researcher’s subjectivity, and so it
does not yield a representative sample
• It is the least reliable sampling method
• The findings cannot be generalized
29. This method means deliberate selection of sample units that
conform to some pre-determined criteria
This involves selection of cases which we judge as the most
appropriate ones for the given study
The chance that a particular case to be selected for the sample
depends on the subjective judgement of the researcher
•
2. JUDGEMENT SAMPLING/ PURPOSIVE SAMPLING
30. Advantage
• It is less costly & more convenient
• It guarantees inclusion of relevant elements in the sample
Disadvantages
• Does not ensure the representativeness of the sample
• Less efficient for generalizing when compared with random
sampling
• Requires more prior extensive information about the population
31. 3.Quota Sampling
This is a form of convenient sampling involving selection of
quota groups of accessible sampling units by traits such as
gender, age, social class
Is therefore a method of stratified sampling
32. • Advantages
• It is considerably less costly than probability sampling
• It takes less time
• There is no need for list of population
• Disadvantages
• It may not yield a precise representative sample
• Interviewers may tend to choose the most accessible persons;
they may ignore areas difficult to reach
• Subject to high degree of classification errors
33. 4.Snow Ball Sampling
A special non-probability method used when the desired sample
characteristic is rare.
Snowball sampling relies on referrals from initial subjects to
generate additional subjects.
Advantages
1 it is very useful in studying social groups, informal group
in a formal organization, and diffusion of information among
professionals of various kinds.
2 it is useful for smaller populations for which no frames are
readily available
34. Disadvantages
1 The major disadvantages of snowball sampling are
that it does not allow the use of probability statistical
methods. Elements included are dependent on the
subjective choice of the original selected respondents
2 It is difficult to apply this method when the population
is large.
3 It does not ensure the inclusion of all elements in the
list.
35. Errors may be classified as:
1. Sampling Errors
2. Sampling Biases
3. Non-Sampling Errors
4. Non-Sampling Biases
Errors in sample surveys
36. .
Arises because of studying only a part of the
population
Due to non-representativeness of the sample
Due to inadequacy of sample size
Sampling errors
37. Specific problem selection
Intensive study and verification of biases
Systematic documentation
Proper enumeration of population
Effective Pre-Testing
Methods of Reducing Sampling Errors
38. Choosing a non-random method of
sampling
Incomplete or inaccurate sampling
frame
Sections of the population are not
available or refuse to co-operate
Sampling bias may arise due to:
39. Non Sampling Errors
Errors which arise from sources other than sampling
are known as Non-Sampling errors.
Egs: a) Errors in observation or interviews
b) Errors in measurement
c) Errors in responses and noting responses
d) Errors in processing data
e) Errors in printing and presenting results
f) Vague questionnaires
g) Vague définition of population
.
40. Consist of bias of observation and non-
observation,
response biases
process biases(during coding, tabulating and
computing)
non-coverage and non-responses
Non sampling bias