SAMPLING

Meaning of Sampling Sampling Techniques GUIDELINES ON SAMPLING Sampling APPLICATION

Meaning of Sampling

It is the process of selecting a small portion of the population, and from their opinion of certain issues are sought. The sample is the group of individuals who will actually participate in the research.

SAMPLING TECHNIQUES

There are two broader types of sampling namely probability and non-probability P robability sampling means that every member of the population has a chance of being selected. Non-probability sampling means that individuals are selected based on non-random criteria, and not every individual has a chance of being selected. Probability sampling is mainly used in quantitative research, while non-probability is used more in qualitative research.

TYPES OF SAMPLING

TYPES OF SAMPLING

Probability Sampling Simple Random Systematic Cluster Stratified Multi-Stage

Non- Probability Sampling Quota Convenience Voluntary Purposive Snowball

PROBABILITY SAMPLING

SIMPLE RANDOM SAMPLING In a simple random sampling, the researche r includes the whole population in the sampling frame. For instance; You want to select a simple random sample of 100 students from X university with a population of 10,000 students . First assign every student assign a number from university database from 1 to 10,000 , and use a random number generator to select 100 numbers . Alternatively it can be done manually though very laborious

SYSTEMATIC SAMPLING It is also called an Nth name selection technique. After the required sample size has been calculated, every Nth record is selected from a list of population members . Assume a study has a population (N) of 100 people in it intends have a sample (n) 20 . The sampling fraction would be f = 20/100 = 20%. In this case, the interval size (k), is equal to N/n = 100/20 = 5 . Select a random integer from 1 to 5. If you choose 4, it means that every 4 th number will be selected ( 4 , 9, 14, 19) until 20 units (sample size) is achieved.

Probability Sampling

CLUSTER SAMPLING It involves dividing the population into subgroups (clusters), with similar characteristics. Assuming that you want collect data on criminal activities among the youth in Kenya. You may divide the country into 8 sub- groups based on the former provinces, with each province being a cluster. Simple random sampling is then used to select the clusters (say 5 Coast, Western, Nairobi, Eastern and Central) that forms the focus f the study. Simple random sampling is then used to select study participants from each of the clusters.

Probability Sampling

STRATIFIED SAMPLING It involves dividing the population into sub-groups called strata (such as gender, occupation. Calculation on sample size from each subgroup is done based on the study population. For instance take the case of a study on an organization that has 800 female and 200 male employees. To ensure that the sample reflects the gender balance in the organization, the population is divided into two strata based on gender. A random sampling is then used to select sample from each strata. Ensure that the sample reflects the numerical strength of each stratum in the population.

PROBABILITY SAMPLING

MULTI-STAGE SAMPLING It is a sampling methods that involves the use of multiple sampling techniques at different stages For instance, a researcher may use cluster sampling in the first stage, followed by stratified random sampling and then simple random sampling at the second and third stages respectively. It mostly used to enhance representativeness in the study sample.

Probability Sampling

QUOTA SAMPLING It entails segmentation of a population into mutually exclusive sub-groups. Then judgment is used to select the subjects or units from each segment based on a specified proportion. For example, a study may decide to include at least a third of either gender in the study sample. It means that a given sub-group must be included and representation in the sample capped at a given proportion.

NON-Probability Sampling

CONVENIENCE SAMPLING It refers to selection of a sample from individuals who happen to be most accessible to the researcher. This is an easy and inexpensive way to gather initial data. However, it raises questions about the representativeness of the population. For instance, you are researching on the prevalence of drugs and substance abuse in X university You then decide to collect data from the students that you happen to meet in the university streets or recreational centres.

NON-Probability Sampling

VOLUNTARY RESPONSE SAMPLING A voluntary response sample is based on ease of access of the participants. Participants volunteer themselves i nstead of the researcher choosing participants directly. Voluntary response samples are always at least somewhat biased, as some people will inherently be more likely to volunteer than others . This form of sampling is mainly used in medical studies such as vaccine trials.

NON-Probability Sampling

PURPOSIVE SAMPLING It entails the researcher using their expertise to select a sample that is most useful to the study. It is mainly used in qualitative research, where the researcher wants to gain detailed knowledge about a phenomenon rather than make statistical inferences. For instance, you want to know more about the experiences of students mothers on accommodation arrangements in X university. The researcher will purposefully select a number of student mothers with different accommodation arrangements in order to gather a varied range of data on their experiences.

NON-Probability Sampling

SNOWBALL SAMPLING It involves the selection of study participants via other participants. The researcher first identifies a few participants that are accessible. The accessible sample is then used by the researcher to help in the identification of other participants. The process is repeated until the desired sample is achieved. For instance, you want to research on the experiences of commercial sex workers in a major city. Since there is no record / list of CSWs in the city, y ou will identify a few of them who agree to participate in the research. You will then request them to help you identify and recruit other CSWs they know in the city.

NON-Probability Sampling

RESEARCH STRATEGY There are two broad strategies namely quantitative strategy and qualitative strategies. Quantitative research. Entails explaining phenomena using numerical data, which are analyzed using mathematical methods ( statistics ). Qualitative research. Involves understanding a social phenomena through careful and detailed descriptions of issues using words rather than numbers. Probability sampling methods are more appropriate for quantitative studies, while non-probability sampling methods are more relevant in qualitative studies

GUIDELINES IN SAMPLING

GUIDELINES IN SAMPLING

METHODOLOGICAL APPROACHES T here are two approaches to research namely single or mixed study approach. Single study approach is one that is either qualitative or quantitative strategy. Mixed study approach has significant components of both quantitative and qualitative aspects. A single study approach can utilize either probability or non-probability sampling methods (but not both). Mixed study method permits the use of both probability and non-probability sampling methods though not in equal proportion.

GUIDELINES IN SAMPLING

AVAILABILITY OF STUDY PARTICIPANTS Probability sampling methods is appropriate in studies where participants are readily available. This is because it permits the inclusion of a large pool of participants in the study. Non-probability is appropriate in studies where study participants are hard to find. It is thus possible to engage the few participants available and use their responses for generalization.

Identify the sampling method(s) most appropriate for the study State the key tenets of the sampling method(s) identified. Explain how each of the key tenets so identified fits the study population. Where more than sampling method is used, explain how the sampling methods complement each other in the study.

SAMPLING APPLICATION