Methods Of Sampling In Social Work Research
Content Outline
- Introduction
- Sampling methods
- Methods of Sample Selection
- Summary
Introduction
Sampling is the process of selecting a particular number of individuals from a population in order to
better understand and observe the characteristics of that population. The determining factor is the
particular characteristic or behavior that the researcher wishes to study. The population would therefore
consist of the people or objects that possess or display this specific characteristic. The researcher would
need to clearly define the population and the inferences to be made from the study prior to selection of a
sample. For e.g. in a study that wishes to examine the causes of adolescent girls dropping out of school,
the sample population selected would basically be adolescent girls who have dropped out of school. The
sample group or population would therefore need to be representative of the population being studied.
When the population being studied is too large and the process to cover it in totality is both cumbersome and expensive for the study, a sample is selected as a representative of this population and studied. The sampled population may sometimes be required to be studied over a period of time in order to have a better understanding of the same. Defining the population and the sample as precisely as possible prior to the study is crucial as it lends clarity to the process of sample selection and eventually to the entire study. For e.g. In the case of adolescent girl drop-outs, specifying the age of the adolescent girls being studied, or the class they drop out would raise interesting questions which would further enrich the study.
When the population being studied is too large and the process to cover it in totality is both cumbersome and expensive for the study, a sample is selected as a representative of this population and studied. The sampled population may sometimes be required to be studied over a period of time in order to have a better understanding of the same. Defining the population and the sample as precisely as possible prior to the study is crucial as it lends clarity to the process of sample selection and eventually to the entire study. For e.g. In the case of adolescent girl drop-outs, specifying the age of the adolescent girls being studied, or the class they drop out would raise interesting questions which would further enrich the study.
Sampling methods
Sampling methods are classified as either probability sampling or nonprobability sampling.
- In probability sampling, each member of the population has a known non-zero probability of being
selected i.e. every unit in the population has a chance (greater than zero) of being selected in the sample,
and this probability can be accurately determined. The combination of these traits makes it possible to
produce unbiased estimates of population totals. Probability methods include random sampling,
systematic sampling, and stratified sampling and cluster sampling. These various ways of probability
sampling have two things in common:
1. Every element has a known nonzero probability of being sampled and
2. Involves random selection at some point. - Nonprobability sampling is any sampling method where some elements of the population have
no chance of selection or where the probability of selection can't be accurately determined. It involves the
selection of elements based on assumptions regarding the population of interest, which forms the criteria
for selection. Hence, because the selection of elements is non-random, nonprobability sampling does not
allow the estimation of sampling errors. In nonprobability sampling, members are selected from the
population in some nonrandom manner.
Nonprobability sampling methods include convenience sampling, judgment sampling, quota sampling, snowball sampling and cluster sampling. In addition, nonresponse effects may turn any probability design into a nonprobability design if the characteristics of nonresponse are not well understood, since nonresponse effectively modifies each element's probability of being sampled.
Methods of Sample Selection
- Random sampling is the purest form of probability sampling. Each member of the population has an equal and known chance of being selected. The variance between individual units within the sample is a good indicator of variance in the overall population, which makes it relatively easy to estimate the accuracy of results. When there are very large populations, it is often difficult or impossible to identify every member of the population, so the pool of available subjects becomes biased. A researcher with specific issue based questions may therefore veer towards a selection of respondents that may not necessarily reflect the characteristics of the target population. However, Simple Random Sampling can be vulnerable to sampling error because the randomness of the selection may result in a sample that doesn't reflect the makeup of the population. For example, in a study of adolescent girl dropouts, a school register may provide information on all adolescent dropouts, both girls and boys. Hence the researcher would need to be specific during the sampling process. Random sampling may also be cumbersome and tedious when sampling from a large target population e.g. children in Maharashtra who have dropped out of school.
- Stratified sampling is a commonly used probability method that is superior to random sampling because
it reduces the sampling error. A stratum is a subset of the population that shares at least one common
characteristic. Examples of stratums might be males and females, or rural and urban adolescents. The
researcher first identifies the relevant stratums and their actual representation in the population. Random
sampling is then used to select a sample size large enough to be a representative of the population.
This sampling method has many advantages. When a population is divided into distinct, independent
strata, a wealth of specific data can be garnered enabling researchers to draw inferences about specific
subgroups. This further enriches the study and prevents important data from getting lost as may happen in
a random sample.
When strata are selected based upon relevance to the criterion in question, using a stratified sampling method can lead to more efficient statistical estimates as compared to simple random sampling, provided that each stratum is proportional to the group's size in the population. There are, however, some potential drawbacks to using stratified sampling. First, identifying strata and implementing such an approach can increase the cost and complexity of sample selection, as well as leading to increased complexity of population estimates. Second, when examining multiple criteria, stratifying variables may be related to some, but not to others, further complicating the design, and potentially reducing the utility of the strata. In some cases stratified sampling may require a larger sample in comparison to other methods.
Advantages over other sampling methods:
1. Focuses on important subpopulations and ignores irrelevant ones.
2. Allows use of different sampling techniques for different subpopulations.
3. Improves the accuracy/efficiency of estimation.
4. Permits greater balancing of statistical power of tests of differences between strata by sampling equal numbers from strata varying widely in size.
Disadvantages:
1. Requires selection of relevant stratification variables which can be difficult.
2. Is not useful when there are no homogeneous subgroups.
3. Can be expensive and time consuming to implement. - Cluster sampling is a probability sampling in which each sampling unit is a collection of elements termed as
“clusters”. Here, the total population is divided into these groups (or clusters) and a simple random sample of the
groups is selected. The population within a cluster should ideally be as heterogeneous as possible, but there should
be homogeneity between clusters. Each cluster should be a small-scale representation of the total population. The
clusters should be mutually exclusive and collectively exhaustive. It is more cost-effective to select respondents in
groups or clusters which may be determined by geography or by time periods. For instance, if surveying households
within rural India, we might choose to select 50 villages and then interview every household within the selected
villages. Clustering can reduce travel and administrative costs. In the example above, an interviewer can make a
single trip to visit several households in one village, rather than having to go to a different village for each
household.
Since clusters can be chosen from a cluster-level frame, with an element-level frame created only for the selected clusters, the researcher does not require a sampling frame for the purpose. Cluster sampling may be commonly implemented as multistage sampling This is a complex form of cluster sampling in which two or more levels of units are embedded one in the other. The first stage consists of constructing the clusters that will be used to sample from. An example of this would be while studying the efficacy of the Pulse Polio Immunization Programme via Primary Health Centres. The researcher could select all rural health centres in the state for the study. In the second stage, a sample of primary units is randomly selected from each cluster (rather than using all units contained in all selected clusters). This would be all children less than five years of age in the example mentioned. In following stages, in each of those selected clusters, additional samples of units are selected, and so on. All ultimate units (children under 5 years, for instance) selected at the last step of this procedure are then surveyed. This technique, thus, is essentially the process of taking random subsamples of preceding random samples. - Quota sampling: In quota sampling, the population is first segmented into sub-groups. Then judgment is used to select the subjects or units from each segment based on a specified proportion. For example, an interviewer may be told to sample 400 boys and 300 girls between the ages of 1 to 5 years. This step makes the technique of quota sampling one of non-probability sampling. In quota sampling the selection of the sample is non-random. For example interviewers might be tempted to interview those who are easily accessible or who visit the Primary Health Centres. This would not cover the children who have no access to medical care or immunization in rural areas. The problem is that these samples may be biased because not everyone gets a chance of selection. This random element is its greatest weakness.
- Choice-based sampling is one of the stratified sampling strategies. In choice-based sampling, the data are stratified on the target and a sample is taken from each stratum so that the rare target class will be more represented in the sample. This sample is therefore a biased sample. The effects of the input variables on the target are often estimated with more precision with the choice-based sample even when a smaller overall sample size is taken compared to a random sample. The results usually must be adjusted to correct for the oversampling.
- Convenience sampling is used in exploratory research where the researcher is interested in getting an inexpensive approximation of the truth. As the name implies, the sample is selected because they are convenient. This nonprobability method is often used during preliminary research efforts to get a gross estimate of the results, without incurring the cost or time required to select a random sample.
- Judgment sampling is a common nonprobability method. The researcher selects the sample based on judgment. This is usually and extension of convenience sampling. For example, a researcher may decide to draw the entire sample from one "representative" city, even though the population includes all cities. When using this method, the researcher must be confident that the chosen sample is truly representative of the entire population.
- Snowball sampling is a special nonprobability method used when the desired sample characteristic is rare. It may be extremely difficult or cost prohibitive to locate respondents in these situations. Snowball sampling relies on referrals from initial subjects to generate additional subjects. While this technique can dramatically lower search costs, it comes at the expense of introducing bias because the technique itself reduces the likelihood that the sample will represent a good cross section from the population. Initial subjects tend to nominate people that they know well and may probably share particular characteristics or traits with. The sample would therefore not be representative of the population. An example would be a sample of transgender individuals with access to information on and protection from HIV/AIDS and other sexually transmitted diseases.
Summary
- The process of selecting a pre-determined number of individuals as being representative of a population, from that population, in order to better understand and observe the characteristics of that population is called sampling.
- Problems of sampling frames include missing elements, foreign elements, duplicate entries and cluster/ group listing.
- Sample size is determined by size of population and frequency of occurrence of trait, behavior or element being researched in the population.
- Sampling methods are classified as either probability sampling or nonprobability sampling.
- Probability methods include random sampling, systematic sampling, and stratified sampling and cluster sampling.
- Nonprobability sampling methods include convenience sampling, judgment sampling, quota sampling, snowball sampling and cluster sampling
Reference
- Bailey, Kenneth D. (1978), Methods of Social Research, The Free Press, London.
- Baker, L. Therese (1988), Doing Social Research, McGraw Hill, New York.
- Black, James A. and Champion, Dean J. (1976), Methods and Issues in Social Research, John Wiley, New York.
- Festinger. L. and Katz. D. (1953), (ed.) Research Methods in the Behavioural Sciences, The Dryden Press, New York.
- Galtung, John (1970), Theory and Methods of Social Research, George Allen and Unwin, London.
- Gelles, R.J. (1978), Methods for Studying Sensitive Family Topics, American Journal of Orthopsychiatry, 48, 408- 424.
Comments