Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
1
Sampling Design
BAHIR DAR UNIVERSITY
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
2
Population and Sample
 Population is a group of any kind (human or non-human)
to which the researchers intend to apply their study
 At the outset of the sampling process, it is vitally important
to carefully define the target population so the proper
source from which the data are to collected can be
identified.
 Sample refers to any group drawn from a large population
in a research from which information or data is obtained.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
3
Sampling
 Sampling is a process of using a small number of items or
parts of a larger population to make conclusions about the
whole population.
 It is a selection process researchers use to define their
population, select samples and gather data or information,
which the researchers later use to make conclusions and
possible generalization that would work for the population
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
4
The Need for Sampling
 It is possible to take all individual members of a population
as subjects when the population
 is homogeneous,
 found in the same geographical area, and
 is small in number.
 However, this is very difficult and infeasible in terms of
time and cost when the population is
 large
 diverse,
 scattered over large geographical areas.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
5
Processes of selecting samples
 1. Determining the population
 2. Determining the sampling frame
 In actual practice the sample will be drawn from a
list of population elements that is often different
from the target population that has been defined.
A sampling frame is the list of elements from
which the sample may be drawn.
 3. Selecting a representative sample
 This is crucial to ensure valid conclusion or
generalizability, for a biased sample leads to
inappropriate conclusions
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
6
Sampling and Research Paradigms
 Positivists = probability sampling for two major reasons:
 1. Equal chance of being selected for every member
 2. To determine possible sample bias and sample error as
probability sampling allows thorough analysis
 Constructivists = non probability sampling for their dominant
method is qualitative one
 Critical theorists = either probability or non probability
sampling, not sticking to one type of sampling approach
because their choice depends on the type of research
method (quantitative or qualitative) they may decide to use
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
7
Probabilistic Sampling design
 Probabilistic sampling that relies on random processes
 It requires more work than nonrandom sampling.
 Random samples are most likely to yield a sample that
truly represents the population.
 In addition, random sampling lets a researcher statistically
calculate the relationship between the sample and the
population – that is the size of sampling error.
 A non-statistical definition of the sampling error is the
deviation between sample result and a population
parameter due to random process.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
8
Types of probability sampling design
 1. Simple random sampling
 A research develops an accurate sampling frame,
 selects elements from sampling frame according to mathematically
random procedure,
 then locates the exact element that was selected for inclusion in the
sample.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
9
Types of probability sampling design
 2. Systematic random sampling
 Systematic random sampling is simple random sampling with a
short cut for random selection.
 Again, the first step is to number each element in the sampling
frame.
 Instead of using a list of random numbers, researcher calculates a
sampling interval, and the interval becomes his or her own quasi-
random selection method.
 The sampling interval tells the researcher how to select elements
from a sampling frame by skipping elements in the frame.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
10
Types of probability sampling design
 3. Stratified sampling
 When the population is heterogeneous, the use of simple random
sample may not produce representative sample.
 Some of the bigger strata may get over representation while some
of the small ones may entirely be eliminated.
 Look at the variables that are likely to affect the results, and stratify
the population in such a way that each stratum becomes
homogeneous group within itself.
 Then draw the required sample by using the table of random
numbers.
 Hence in stratified random sampling a sub-sample is drawn utilizing
simple random sampling within each stratum.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
11
Types of probability sampling design
 4. Cluster random
 Purpose: to sample economically while retaining the
characteristics of a probability sample.
 A researcher draws several samples in stages in cluster
sampling. In a three-stage sample,
 Stage 1: random sampling of big clusters;
 Stage 2: random sampling of small clusters within each selected
big cluster; and
 Stage 3: finally sampling of group(s) of elements from within the
sampled small clusters.
 Addressing two problems:
 Researchers lack a good sampling frame for a dispersed
population and the cost to reach a sampled element is very high.
 A second advantage for geographically dispersed populations is
that elements within each cluster are physically closer to each
other. This may produce savings in locating or reaching each
element.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
12
Types of probability sampling design
 5. Multi-stage Sampling
 This is an extension or further development of the principle of
cluster sampling which requires the use of combination of
sampling techniques.
 It involves selecting the sample in stages, that is, taking samples
from samples.
 Using the large community example in cluster sampling,
 one type of stage sampling might be to select a number of schools
at random, and
 from within each of these schools, select a number of classes at
random,
 and from within those classes select a number of students.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
13
Non-probability Sampling
 In non-probability sampling the probability of any particular
element of the population being chosen is unknown.
 The selection of units in non-probability sampling is quite
arbitrary, as researchers rely heavily on personal judgment.
 It should be noted that there are no appropriate statistical
techniques for measuring random sampling error from a non-
probability sample.
 Thus projecting the data beyond the sample is statistically
inappropriate.
 Nevertheless, there are occasions when non-probability
samples are best suited for the researcher’s purpose.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
14
Types of non-probability sampling
 1. Comprehensive Sampling
 Including all the elements of the population when the its size is
manageable
 2. Quota sampling
 A sampling procedure that ensures that certain characteristics of
a population sample will be represented to the exact extent that
the researcher desires.
 In this case the researcher first identifies relevant categories of
people (e.g. male and female; or under age 30, ages 30 to 60,
over 60, etc) then decides how many to get in each category.
 Thus the number of people in various categories of sample is
fixed.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
15
Types of non-probability sampling
 3. Convenience sampling (also called haphazard or
accidental sampling)
 refers to sampling by obtaining units or people who are
most conveniently available.
 For example, it may be convenient and economical to
sample employees in companies in a nearby area, sample
from a pool of friends and neighbors.
 4. Maximum variation sampling
 A strategy by which units are selected for the sample
because they provide the greatest differences in certain
characteristics
 5. Extreme case sampling
 A technique which uses a selection of cases on both ends
of a continuum, individuals that are unusual or unique in a
certain way
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
16
Types of non-probability sampling
 6.Typical case sampling
 Selecting cases that are assumed to be typical of the characteristics
under study
 7. Purposive sampling
 Depending upon the type of topic, the researcher lays down the criteria
for the subjects to be included in the sample.
 Whoever meets that criterion could be selected in the sample.
 The researcher might use his/her judgment for the actual selection of the
subjects.
 8. Theoretical sampling
 This is a feature of grounded theory. In grounded theory the
sample size is relatively immaterial, as one works with the data
that one has.
 Theoretical sampling requires the researcher to have sufficient
data to be able to generate and ‘ground’ the theory in the research
context, however defined, i.e. to create a theoretical explanation
of what is happening in the situation, without having any data that
do not fit the theory.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
17
Types of non-probability sampling
 9. Volunteer sampling
 In cases where access is difficult, the researcher may have to rely on
volunteers, for example, personal friends, or friends of friends, or
participants who reply to a newspaper advertisement, or those who
happen to be interested from a particular school, or those attending
courses.
 Sometimes this is inevitable (Morrison 2006), as it is the only kind of
sampling that is possible, and it may be better to have this kind of
sampling than no research at all.
 10. Snowball or Chain sampling
 Snowball sampling (also called network, chain referral, or reputational
sampling) is a method for identifying and sampling (or selecting) cases in
the network.
 This design has been found quite useful where respondents are difficult
to identify and are best located through referral networks.
 It begins with one or a few people or cases and spreads out on the basis
of links to the initial cases.
 This group is then used to locate others who possess similar
characteristics and who, in turn, identify others.
Haramaya University TEFL 703
Instructor: Mulugeta Teka (PhD)
18
Sample Size
 No clear-cut answer to the question how large the samples for the
research should be.
 Sample size is determined to some extent by the style of the research,
and by cost—in terms of time, money, stress, and resources.
 A survey style usually requires a large sample, particularly if inferential
statistics are to be calculated.
 In an ethnographic or qualitative style of research it is more likely that
the sample size will be small.
 Borg and Gall (1979:194–5) suggest that
 correlational research requires a sample size of no fewer than 30
cases,
 causal-comparative and experimental methodologies require a sample
size of no fewer than 15 cases, and
 survey research should have no fewer than 100 cases in each major
subgroup and twenty to fifty in each minor subgroup.

PPT 7 SAMPLING.ppt sampling an dsampling techniques

  • 1.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 1 Sampling Design BAHIR DAR UNIVERSITY
  • 2.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 2 Population and Sample  Population is a group of any kind (human or non-human) to which the researchers intend to apply their study  At the outset of the sampling process, it is vitally important to carefully define the target population so the proper source from which the data are to collected can be identified.  Sample refers to any group drawn from a large population in a research from which information or data is obtained.
  • 3.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 3 Sampling  Sampling is a process of using a small number of items or parts of a larger population to make conclusions about the whole population.  It is a selection process researchers use to define their population, select samples and gather data or information, which the researchers later use to make conclusions and possible generalization that would work for the population
  • 4.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 4 The Need for Sampling  It is possible to take all individual members of a population as subjects when the population  is homogeneous,  found in the same geographical area, and  is small in number.  However, this is very difficult and infeasible in terms of time and cost when the population is  large  diverse,  scattered over large geographical areas.
  • 5.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 5 Processes of selecting samples  1. Determining the population  2. Determining the sampling frame  In actual practice the sample will be drawn from a list of population elements that is often different from the target population that has been defined. A sampling frame is the list of elements from which the sample may be drawn.  3. Selecting a representative sample  This is crucial to ensure valid conclusion or generalizability, for a biased sample leads to inappropriate conclusions
  • 6.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 6 Sampling and Research Paradigms  Positivists = probability sampling for two major reasons:  1. Equal chance of being selected for every member  2. To determine possible sample bias and sample error as probability sampling allows thorough analysis  Constructivists = non probability sampling for their dominant method is qualitative one  Critical theorists = either probability or non probability sampling, not sticking to one type of sampling approach because their choice depends on the type of research method (quantitative or qualitative) they may decide to use
  • 7.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 7 Probabilistic Sampling design  Probabilistic sampling that relies on random processes  It requires more work than nonrandom sampling.  Random samples are most likely to yield a sample that truly represents the population.  In addition, random sampling lets a researcher statistically calculate the relationship between the sample and the population – that is the size of sampling error.  A non-statistical definition of the sampling error is the deviation between sample result and a population parameter due to random process.
  • 8.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 8 Types of probability sampling design  1. Simple random sampling  A research develops an accurate sampling frame,  selects elements from sampling frame according to mathematically random procedure,  then locates the exact element that was selected for inclusion in the sample.
  • 9.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 9 Types of probability sampling design  2. Systematic random sampling  Systematic random sampling is simple random sampling with a short cut for random selection.  Again, the first step is to number each element in the sampling frame.  Instead of using a list of random numbers, researcher calculates a sampling interval, and the interval becomes his or her own quasi- random selection method.  The sampling interval tells the researcher how to select elements from a sampling frame by skipping elements in the frame.
  • 10.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 10 Types of probability sampling design  3. Stratified sampling  When the population is heterogeneous, the use of simple random sample may not produce representative sample.  Some of the bigger strata may get over representation while some of the small ones may entirely be eliminated.  Look at the variables that are likely to affect the results, and stratify the population in such a way that each stratum becomes homogeneous group within itself.  Then draw the required sample by using the table of random numbers.  Hence in stratified random sampling a sub-sample is drawn utilizing simple random sampling within each stratum.
  • 11.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 11 Types of probability sampling design  4. Cluster random  Purpose: to sample economically while retaining the characteristics of a probability sample.  A researcher draws several samples in stages in cluster sampling. In a three-stage sample,  Stage 1: random sampling of big clusters;  Stage 2: random sampling of small clusters within each selected big cluster; and  Stage 3: finally sampling of group(s) of elements from within the sampled small clusters.  Addressing two problems:  Researchers lack a good sampling frame for a dispersed population and the cost to reach a sampled element is very high.  A second advantage for geographically dispersed populations is that elements within each cluster are physically closer to each other. This may produce savings in locating or reaching each element.
  • 12.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 12 Types of probability sampling design  5. Multi-stage Sampling  This is an extension or further development of the principle of cluster sampling which requires the use of combination of sampling techniques.  It involves selecting the sample in stages, that is, taking samples from samples.  Using the large community example in cluster sampling,  one type of stage sampling might be to select a number of schools at random, and  from within each of these schools, select a number of classes at random,  and from within those classes select a number of students.
  • 13.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 13 Non-probability Sampling  In non-probability sampling the probability of any particular element of the population being chosen is unknown.  The selection of units in non-probability sampling is quite arbitrary, as researchers rely heavily on personal judgment.  It should be noted that there are no appropriate statistical techniques for measuring random sampling error from a non- probability sample.  Thus projecting the data beyond the sample is statistically inappropriate.  Nevertheless, there are occasions when non-probability samples are best suited for the researcher’s purpose.
  • 14.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 14 Types of non-probability sampling  1. Comprehensive Sampling  Including all the elements of the population when the its size is manageable  2. Quota sampling  A sampling procedure that ensures that certain characteristics of a population sample will be represented to the exact extent that the researcher desires.  In this case the researcher first identifies relevant categories of people (e.g. male and female; or under age 30, ages 30 to 60, over 60, etc) then decides how many to get in each category.  Thus the number of people in various categories of sample is fixed.
  • 15.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 15 Types of non-probability sampling  3. Convenience sampling (also called haphazard or accidental sampling)  refers to sampling by obtaining units or people who are most conveniently available.  For example, it may be convenient and economical to sample employees in companies in a nearby area, sample from a pool of friends and neighbors.  4. Maximum variation sampling  A strategy by which units are selected for the sample because they provide the greatest differences in certain characteristics  5. Extreme case sampling  A technique which uses a selection of cases on both ends of a continuum, individuals that are unusual or unique in a certain way
  • 16.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 16 Types of non-probability sampling  6.Typical case sampling  Selecting cases that are assumed to be typical of the characteristics under study  7. Purposive sampling  Depending upon the type of topic, the researcher lays down the criteria for the subjects to be included in the sample.  Whoever meets that criterion could be selected in the sample.  The researcher might use his/her judgment for the actual selection of the subjects.  8. Theoretical sampling  This is a feature of grounded theory. In grounded theory the sample size is relatively immaterial, as one works with the data that one has.  Theoretical sampling requires the researcher to have sufficient data to be able to generate and ‘ground’ the theory in the research context, however defined, i.e. to create a theoretical explanation of what is happening in the situation, without having any data that do not fit the theory.
  • 17.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 17 Types of non-probability sampling  9. Volunteer sampling  In cases where access is difficult, the researcher may have to rely on volunteers, for example, personal friends, or friends of friends, or participants who reply to a newspaper advertisement, or those who happen to be interested from a particular school, or those attending courses.  Sometimes this is inevitable (Morrison 2006), as it is the only kind of sampling that is possible, and it may be better to have this kind of sampling than no research at all.  10. Snowball or Chain sampling  Snowball sampling (also called network, chain referral, or reputational sampling) is a method for identifying and sampling (or selecting) cases in the network.  This design has been found quite useful where respondents are difficult to identify and are best located through referral networks.  It begins with one or a few people or cases and spreads out on the basis of links to the initial cases.  This group is then used to locate others who possess similar characteristics and who, in turn, identify others.
  • 18.
    Haramaya University TEFL703 Instructor: Mulugeta Teka (PhD) 18 Sample Size  No clear-cut answer to the question how large the samples for the research should be.  Sample size is determined to some extent by the style of the research, and by cost—in terms of time, money, stress, and resources.  A survey style usually requires a large sample, particularly if inferential statistics are to be calculated.  In an ethnographic or qualitative style of research it is more likely that the sample size will be small.  Borg and Gall (1979:194–5) suggest that  correlational research requires a sample size of no fewer than 30 cases,  causal-comparative and experimental methodologies require a sample size of no fewer than 15 cases, and  survey research should have no fewer than 100 cases in each major subgroup and twenty to fifty in each minor subgroup.