RESEARCH METHODOLOGY
3.3 SAMPLING DESIGN
CHAPTER 3
Cooper and Schindler (2003:179) reinforces the preceding statement when they say, "the basic idea of sampling is that by selecting some of the elements in a population, we may draw conclusion about the entire population.
Cooper and Schindler (2003:179) summaries the following as compelling reasons for sampling:
• lower cost
• greater accuracy of results
• greater speed of data collection
• availability of population elements 3.3.1 Population and Sample
Cooper and Schindler (2003:179) define population as the total collection of elements upon which inferences are wished to be made. They further define a sample as the elements selected from a population and from which conclusions about the entire population may be drawn. It should be noted that drawing conclusions about the population based on a sample depends on the representativeness of the sample. The population for the study is made up all petrol attendants working at the twenty five service stations of the oil company within the Durban Metro. The number of the population elements is estimated at 400 by the oil company. The sample for the study comprises 1 70 petrol attendants drawn from seventeen service stations. This sample size was seen to be acceptable based on Cooper and Schindler (2003)'s advocacy that in reality the size of the sample is a function of the variation in the population parameters under the study.
3.3.2 Sampling Techniques
There are a number of sampling techniques available and are classified as probability
and non-probability sampling. According to Cooper and Schindler (2003), probability
sampling is based on random selection - a controlled procedure that ensures each
population element to be given a known non-zero chance of selection. Non-probability
sampling is not random but the probability of selecting population elements is unknown.
They assert that the probability sampling has technical superiority over non-probability sampling. Cooper and Schindler (2003:199-203) list and define the different forms of probability and non-probability sampling as follows:
3.3.2.1 Probability Sampling:
• The simplest type of probability approach is simple random sampling. In this design, each member of the population has an equal chance of being included in the sample. In developing a probability sample, the researcher has to consider the relevant population, the parameters of interest, the sampling frame, the type of sample, the size of sample and the cost that will be incurred. The specification of the researcher and the nature of the population determine the size of a probability sample. Cost considerations are also often incorporated into the sample size decision.
• Complex sampling is used when conditions make simple random samples impractical or uneconomical. The four major types of complex random sampling are systematic, stratified, cluster and double sampling.
• Systematic sampling involves the selection of every 'k'th element in the population by beginning with a random start between elements from 1 to k. Its simplicity in certain cases is its greatest value.
• Stratified sampling is based on dividing a population into sub-populations and then randomly sampling from each of these strata. Stratified samples may be proportionate or disproportionate.
• In Cluster sampling, the population may be divided into convenient groups first and then randomly select the groups to study. It is typically less efficient from a statistical viewpoint than the simple random because of high degree of homogeneity within the clusters but has a great advantage of cost saving if the population is dispersed geographically or in time.