Probablistic sampling group 3 assighnment

A Group Assignment on Probabilistic Sampling For
Business Research Methods Course Requirement
By Section Two Group 3 Members
5-2
Group Member’s
1. Sara Jemal
2. Shimelis Birhanu
3. Setegn Addisu
4. Selamawit Wolde
5. Solomon T/Markos
6. Sisay Tufa
Course Instructor Dr. Shimelis Z.
Feb12.2017
Addis Ababa/ Ethiopia
PROBABILISTIC
SAMPLING

 General Background
Sampling
 Sampling Terminologies
 Types Of Sampling
 Types Probabilistic
Sampling
1. Simple Random Sampling
2. Systematic Random Sampling
3. Cluster Sampling
4. Stratified Sampling
5. Multi Stage Sampling
 Summary on Selection
charts of Probabilistic
Sampling ?

1. Define basic sampling terminologies & Probabilistic Sampling.
2. Describe and discuss the different Probabilistic sampling
designs.
3. Discuss the factors to be taken into consideration for
determining types of Probabilistic Sampling.
4. Discuss the merit & a limitation of each Probabilistic Sampling
design.
5. To assist our colleague’s in order to utilize the concepts of
Probabilistic Sampling in there future projects Plan

Sampling method: is the process of selecting a small group to
representative the whole universe in order to:
 obtain accurate info. with minimum cost, time & energy
 To improve accuracy of such estimates
 Probability sampling : Every item of the universe has an
equal chance/ Same probabilities of being included in the
sample.

Probability sampling AKA
 Equal probability of selection (EPS) design.
 self-weighting design.
 Chance sampling or
 Random sampling
 Why Probability sampling Considered
we can measure the errors of estimation
we can measure the significance of results
It ensures the law of Statistical regularity

 Population: collection of all elements in universe
Sample: is a subset of the population
 Sampling: process used to determine the sample
Sampling units: collections of elements from the
population that cover the entire population
 Sampling frame is a list of sampling units

 Clusters: a group of similar things or people positioned or
occurring closely together.
Strata: an elements of homogeneous subgroups
Heterogeneous: is the state of being dissimilar.
Homogeneous: as the state of being similar.

• Achieving a representative sample
• Minimizing sampling bias
• Making statistical inferences
• Less knowledge of universe is sufficient.
• Sample representative of population
A) Advantages of
Probability
Sampling
• It takes time
• It is costly
• Chances of selecting specific class of
samples only
B) Limitation of
Probability
Sampling

1.5.1 Simple Random Sampling
 The purest form of probability sampling & EPS design
It used when the population of interest is
 Small, homogeneous & readily available
 If our sampling frame has a periodic pattern

1 .5.1 SimpleRandom
SamplingCont.…..
A. Tossing a coin
B. Throwing a dice
C. Lottery method
D. Blind folded method
E. Random number table
F. Random number generation
A. SRSWR
 SRS with replacement
 AKA Equal probability SRS
B. SRSWOR
 SRS without replacement
 AKA Varying probability SRS
Types of SRS
Techniques for Randomization

Step 3
Drawn the sample
Step 2
Prepare an exhaustive list (sampling frame) of all
member of the population
Step 1
Determine Types & Techniques of Randomization

1 .5.1 SimpleRandom
SamplingCont.…..
1. Easy to implement
2. Free from subjectivity &
personal error.
3. Requires the minimum
knowledge of population
4. provides appropriate data
for one’s purpose.
5. can be used for inferential
purpose
A. Imprecise for heterogeneous
B. It does not use the knowledge
about the population
C. Cannot ensure the
representativeness
D. Time taking & costly
procedures
E. Its inferential accuracy
depends upon the size of the
sample
F. Can be disruptive to isolate
members from a group
Advantages of SRS Limitation of SRS

Systematic Random Sampling:
 It involves you selecting the sample at regular intervals from the
sampling
 Each element has an equal probability of selection, but
combinations of elements have different probabilities.
 It requires the complete information about the population.
 There should be a list of information of all the individuals of the
population in any systematic way.
1.5.2 Systematic Random
Sampling

When to Use Systematic Random Sampling?
1. When no list of population exists
2. When the list is roughly of random order
3. Small area/population
Sampling

Sampling Procedures
Step 4
Sample drawn by Adding Kth unit to the randomly chosen number j+k, j+2k….
Step 3
Determine the first number randomly b/n 1st # and kth
Step 2
Determine Sampling interval K (k=Population Size/ Sample size or N/n)
Step 1
Number each of the cases in your sampling frame with a unique number

Sampling Procedures Cont.….

1 .5.2 Systematic Random
SamplingCont.…..
1. Sample easy to select
2. Simple to implement
3. Sample evenly spread over
entire reference population
4. Provides a better random
distribution than SRS
5. Can be started without a
complete listing frame
6. It reduces the field cost.
7. Inferential statistics may be
used.
8. Conclusions & generalizations is
possible
9. It is not costly design
10. Required minimal expertise
knowledge
Advantages of SyRS Advantages of SyRS Cont.…

1 .5.2 Systematic Random
SamplingCont.…..
1. Not fit for periodical sample
2. Difficult to assess precision of
estimate from one survey.
3. linear trend
4. This is not free from error
5. Knowledge of population is
essential
6. Information of each individual is
essential.
7. Only for optimal size of
population
8. Population distribution should be
natural degree of randomness
9. There is a greater risk of data
manipulation
Limitation of SyRS Limitation of SyRS Cont.…

Cluster Sampling:
AKA block sampling.
A Cluster sampling is a form of sampling divided the
population in to groups or clusters.
Cluster sampling usually geographic or organizational.
Cluster sampling is an exampling of two stage sampling.
The cluster are homogeneous units.
Sampling units are groups rather than individuals.
1.5.3 Cluster Sampling

Cluster Sampling:
A sample of such cluster is then selected.
In pure cluster sampling whole cluster is sampled.
In simple multi stage cluster randomly chosen .
 Types Cluster Sampling Methods:
1. One-stage sampling.
All of the elements within selected clusters are included in
the sample.
2. Two-stage sampling.
A subset of elements within selected clusters are randomly
selected for inclusion in the sample
1.5.3 Cluster Sampling Cont.…

1.5.3 Cluster Sampling
Procedures
Step 4
Sample of such clusters is then selected & all units from the selected clusters
are studied..
Step 3
Population divided into clusters of homogeneous units & geographical
contiguity
Step 2
A sample of respondents within those areas is selected.
Step 1
A sample of areas is chosen

1.5.3ClusterSamplingCont.…
1. Most economical/ Cheaper
2. Larger sample for a similar fixed
cost
3. Less time for listing &
implementation
4. Also suitable for survey of
institutions
5. Reduced cost of personal
interviews
6. It may be a good representative
of the population.
7. It is an easy method.
8. It is practicable & highly
applicable in education.
9. Observations can be used for
inferential purpose.
10. Feasible
11. Reduced variability
Advantages of Cluster S. Advantages of Cluster S.

1.5.3ClusterSamplingCont.…
1. Cluster sampling is not free from
errors.
2. It is not comprehensive.
3. Higher sampling error
4. Biased samples
5. May not reflect the diversity of
the community.
6. Other elements in the same
cluster may share similar
characteristics.
7. Provides less information per
observation than an SRS
Limitation of Cluster S.
Limitation of Cluster S.

Stratified Sampling:
 A sampling method applied to extract a representative
sample from a heterogeneous population
 Adequate representation of minority subgroups of interest
can be ensured by stratification & varying sampling fraction
between strata as required
 Finally, since each stratum is treated as an independent
population, different sampling approaches can be applied to
different strata
1.5.4 Stratified Sampling

Post Stratification:
 Stratification is sometimes introduced after the sampling
phase in a process called "post stratification“.
 This approach is typically implemented due to :
 Lack of prior knowledge of an appropriate stratifying
variable
 when the experimenter lacks the necessary
information to create a stratifying variable during the
sampling phase.
1.5.4 Stratified Sampling Cont..

 In SS Design:
1. Stratum variables are mutually exclusive (non-over lapping)
2. The population (elements) homogenous within-stratum
3. the population (elements) heterogeneous between the strata.
When we use SS:
A. Population groups may have different values for the
responses of interest.
B. If we want to improve our estimation for each group
separately.
C. To ensure adequate sample size for each group.
1.5.4 Stratified Sampling Cont..

1.5.4 Stratified Sampling
Procedures
• The basis of common characteristic(s) of the items to be
put in each stratum
• Strata are purposively formed and are usually based on
past experience and personal judgment of the researcher.
Form of strata
• Simple random sampling
• Systematic sampling can be used if it is considered
more appropriate in certain situations
Selection of
items in each
stratum
• Proportional allocation
• Optimum allocation (with equal cost)
• Optimum allocation (with unequal cost)
Allocate of
sample size of
each
stratum?

1.5.4 Sample Allocation for
Stratified Sampling Design
• is more effective for comparing strata which have
different error possibilities
• is less efficient for determining population
characteristics.
Disproportionate
• It refers to the selection from each sampling unit of
a sample that is proportionate to the size of the unit
• variables used as the basis of classifying categories
and increased chances of being able to make
comparisons between strata
Proportionate
• It refers to selecting units from each stratum
• Each stratum should be in proportion to the
corresponding stratum the population.
Optimum
allocation

1 .5.4StratifiedSampling
DesignCont.…..
It is a good representative of the
population.
It is an improvement over the earlier
technique of sampling.
It is an objective method of
sampling.
Observations can be used for
inferential purpose
Estimate could be made for each
stratum
It have a smaller variance
Reduce survey costs.
1. It is difficult to decide the relevant
criterion for stratification.
2. Sampling frame is needed for each
stratum
3. There is a risk of generalization.
4. It is costly and time consuming
method
Advantages of SS Limitation of SS

1 .5.4Stratification
Vs.Clustering
BASIS FOR
COMPARISON
STRATIFIED SAMPLING CLUSTER SAMPLING
Meaning
Population is divided into
homogeneous segments, and
then the sample is randomly
taken from the segments.
The members of the population are
selected at random, from naturally
occurring groups called 'cluster'.
Sample
Randomly selected individuals
are taken from all the strata.
All the individuals are taken from
randomly selected clusters.
Selection Individually Collectively
Homogeneity Within group Between groups
Heterogeneity Between groups Within group

1 .5.4Stratificationvs.Cluster
Cont.…
BASIS FOR
COMPARISON
STRATIFIED SAMPLING CLUSTER SAMPLING
Cost
It is costly and time
consuming method.
Cheaper
Representative
Sample more representative Usually not representative of whole
population
Bifurcation Imposed by the researcher Naturally occurring groups
Objective To increase precision and
representation.
To reduce cost and improve efficiency.

1 .5.4Stratificationvs. Cluster
Cont.…

Video PresentationMultistage Sampling
final_setegn_presentation.mp4
1.5.5 Multistage Sampling

1.5.6Summaryof PresentationHowWe Select
D/t Typesof SamplingMethod

1. C.R Kothari 1990, Research Methods & Techniques: Sampling Design, Second
Edition, New Age International (P) Ltd., Publisher, New Delhi.55-66.
2. Dr. Prabhat Pandey and Dr. Meenu Mishra Pandey 2015, RESEARCH
METHODOLOGY: TOOLS AND TECHNIQUES: Research Design: Published by
Buzau, Al. Marghiloman 245 bis, 120082 , Romania.18-23.
3. GeoffreyM., David D and David F. 2005,Essential of Research Design and
Methodology: Planning and Designing a Research Study, Published by John
Wiley & Sons, Inc., Hoboken, New Jersey.26-65.
4. Mark Saunders,Philip Lewis and Adrian Thornhill 2009,Research Methods for
Business Students: Selection Sample,Fifth edition, Published by Pearson
Education Limited Edinburgh Gate Harlow, England.210-256.
5. U university of Bhojanna 2007, Research Methods for Management School of
Distance Education Bharathiar University,Sampling Design, EXCEL BOOKS
PRIVATE LIMITED A-45, Naraina, Phase-I,, New Delhi. 73-88.
6. Uma sekaran 2003, Research Methods for Business: Sampling, Fourth Edition,
Published by John Wiley & Sons, Inc., Hoboken, New Jersey.263-276.
REFERENCE

Probablistic sampling group 3 assighnment

More Related Content

What's hot (18)

Viewers also liked (9)

Similar to Probablistic sampling group 3 assighnment (20)

More from Shimelis Birhanu (6)

Recently uploaded (20)

Probablistic sampling group 3 assighnment