Kuliah5 Sampling
-
Upload
jelita-kasih-adinda -
Category
Documents
-
view
217 -
download
0
description
Transcript of Kuliah5 Sampling
SamplingSampling
SamplingSamplingChapter SixChapter Six
What is a Sample?What is a Sample?
SamplingSampling is the process of selecting a is the process of selecting a number of individuals from a population, number of individuals from a population, preferably in a way that the individuals are preferably in a way that the individuals are representative of the larger group from representative of the larger group from which they were selected.which they were selected.
A A samplesample is any group on which information is any group on which information is obtained.is obtained.
Defining the PopulationDefining the Population A A populationpopulation refers to all the members of a refers to all the members of a
particular group.particular group. The first task in selecting a sample is to define The first task in selecting a sample is to define
the population of interest.the population of interest. In Educational Research, the population of In Educational Research, the population of
interest is a group of persons who possess certain interest is a group of persons who possess certain characteristics.characteristics.
A A target populationtarget population is the actual population that is the actual population that the researcher would like to generalize.the researcher would like to generalize. Considered rarely availableConsidered rarely available The The accessible populationaccessible population would be the group that would be the group that
is available (realistic choice)is available (realistic choice)
Representative vs. Non-representative Samples (Fig. 6.1)Representative vs. Non-representative Samples (Fig. 6.1)
Two Main Types of SamplingTwo Main Types of Sampling
Sampling may be either Sampling may be either randomrandom or or non-non-randomrandom
Random samplingRandom sampling is a method of selecting is a method of selecting subjects from a population by chance, so that subjects from a population by chance, so that biases do not alter the sample.biases do not alter the sample.
The 3 most common ways of obtaining this type The 3 most common ways of obtaining this type of sample are:of sample are: Simple Random SamplingSimple Random Sampling Stratified Random SamplingStratified Random Sampling Cluster SamplingCluster Sampling
Part of a Table of Random Numbers Part of a Table of Random Numbers (Table 6.1)(Table 6.1)
011723 223456 222167 032762 062281 565451912334 379156 233989 109238 934128 987678086401 016265 411148 251287 602345 659080059397 022334 080675 454555 011563 237873666278 106590 879809 899030 909876 198905051965 004571 036900 037700 500098 046660063045 786326 098000 510379 024358 145678560132 345678 356789 033460 050521 342021727009 344870 889567 324588 400567 989657000037 121191 258700 088909 015460 223350667899 234345 076567 090076 345121 121348042397 045645 030032 657112 675897 079326987650 568799 070070 143188 198789 097451091126 021557 102322 209312 909036 342045
Simple Random SamplingSimple Random Sampling A A Simple Random SamplingSimple Random Sampling is a sample selected from a is a sample selected from a
population in such a manner that all members have an population in such a manner that all members have an equal chance of being selectedequal chance of being selected
If the sample is large, it is the best method to obtain a If the sample is large, it is the best method to obtain a sample representative of the population from which it has sample representative of the population from which it has been selectedbeen selected
The larger the sample size, the more it is likely to represent The larger the sample size, the more it is likely to represent the populationthe population
Any differences that occur are the result of chance rather Any differences that occur are the result of chance rather than bias on the part of the researcherthan bias on the part of the researcher
Disadvantages of this method are: 1) the difficulty of Disadvantages of this method are: 1) the difficulty of performing the sampling and, 2) this method performing the sampling and, 2) this method does not does not ensureensure that subgroups are present in the sampling in the that subgroups are present in the sampling in the same proportion as they are in a populationsame proportion as they are in a population
Stratified Random SamplingStratified Random Sampling A A Stratified Random SamplingStratified Random Sampling is a sample is a sample
selected so that certain characteristics are selected so that certain characteristics are represented in the sample in the same proportion represented in the sample in the same proportion as they occur in the populationas they occur in the population
The term The term stratastrata refers to sub-groups refers to sub-groups The advantage of stratified random sampling is The advantage of stratified random sampling is
that it increases the likelihood of representation, that it increases the likelihood of representation, especially if the especially if the sample size is smallsample size is small
It virtually ensures that any key characteristics of It virtually ensures that any key characteristics of individuals in the population are included in the individuals in the population are included in the same proportions in the sample sizesame proportions in the sample size
The disadvantage is that it requires still more The disadvantage is that it requires still more effort on the part of the researchereffort on the part of the researcher
Selecting a Stratified Sample Selecting a Stratified Sample (Figure 6.2)(Figure 6.2)
Cluster Random SamplingCluster Random Sampling A A Cluster Random SamplingCluster Random Sampling is a sample obtained is a sample obtained
by using groups as the sampling unit (cluster), by using groups as the sampling unit (cluster), rather than individualsrather than individuals
There are instances where it is not possible to There are instances where it is not possible to select a sample of individuals from a populationselect a sample of individuals from a population
This is considered more effective with large This is considered more effective with large numbers of clustersnumbers of clusters
Advantages include more efficient and easier to Advantages include more efficient and easier to implement in schoolsimplement in schools
Its disadvantage is that there is a great chance of Its disadvantage is that there is a great chance of selecting a sample that is not representative of selecting a sample that is not representative of the populationthe population
Random Sampling Methods Random Sampling Methods (Figure 6.3)(Figure 6.3)
Two-Stage Random SamplingTwo-Stage Random Sampling
This method selects groups randomly and This method selects groups randomly and then chooses individuals randomly from then chooses individuals randomly from these groups.these groups.
This becomes a combination of a cluster This becomes a combination of a cluster random sampling with individual random random sampling with individual random sampling.sampling.
Considered less time consuming but Considered less time consuming but allows for a good representation of the allows for a good representation of the groups at random.groups at random.
Nonrandom Sampling MethodsNonrandom Sampling Methods There are 3 main types of nonrandom sampling methods There are 3 main types of nonrandom sampling methods
used in Educational Researchused in Educational Research A A Systematic SampleSystematic Sample is a sample obtained by selecting is a sample obtained by selecting
every every nthnth name in a population name in a population A A Convenience SampleConvenience Sample is any group of individuals that is is any group of individuals that is
conveniently available to be studiedconveniently available to be studied Are not considered representative of the population and should be Are not considered representative of the population and should be
avoided, if possibleavoided, if possible
A A Purposive SamplePurposive Sample is a sample selected because the is a sample selected because the individuals have special qualifications of some sort, or individuals have special qualifications of some sort, or because of prior evidence of representationbecause of prior evidence of representation
Personal judgment is used for selection purposes Personal judgment is used for selection purposes A major disadvantage is that the researcher’s judgment could be in A major disadvantage is that the researcher’s judgment could be in
errorerror
Convenience Sampling Convenience Sampling (Figure 6.4)(Figure 6.4)
Nonrandom Sampling Method Nonrandom Sampling Method (Figure 6.5)(Figure 6.5)
Sample SizeSample Size The question remains as to what constitutes an adequate The question remains as to what constitutes an adequate
sample size. sample size. Samples should be as large as a researcher can obtain with Samples should be as large as a researcher can obtain with
a reasonable expenditure of time and energy.a reasonable expenditure of time and energy. The recommended minimum number of subjects are as The recommended minimum number of subjects are as
follows for the following types of studies:follows for the following types of studies: 100 for a Descriptive Study100 for a Descriptive Study 50 for a Correlational Study50 for a Correlational Study 30 in each group for Experimental and Causal-Comparative 30 in each group for Experimental and Causal-Comparative
StudyStudy
The use of 15 subjects per group should probably be replicated
External Validity, a.k.a. External Validity, a.k.a. GeneralizabilityGeneralizability
The whole notion of science is built on The whole notion of science is built on generalizing.generalizing. External ValidityExternal Validity refers to the extent that the refers to the extent that the
results of a study can be generalized from a results of a study can be generalized from a sample to a population.sample to a population.
Population generalizabilityPopulation generalizability is the degree to which a is the degree to which a sample represents the population of interest.sample represents the population of interest. Obtaining a representative sample becomes very importantObtaining a representative sample becomes very important
Ecological generalizabilityEcological generalizability refers to the extent to refers to the extent to which the results of a study can be generalized to which the results of a study can be generalized to conditions or settings other than those that conditions or settings other than those that prevailed in the study.prevailed in the study.
Population as Opposed to Ecological Generalizing Population as Opposed to Ecological Generalizing (Figure 6.6)(Figure 6.6)