4.7.4 Sampling Technique
Sampling method can be divided into two broad categories: probability (representative or random) sampling and non probability (Judgmental) sampling (Saunders et al., 2003; Cooper & Schindler 2006).
Non-probability sampling is a technique which elements of the population do not have a known zero chance of being selected depending on researcher subjective judgment. Thus non-probability sampling is arbitrary and selection of the sample is not necessarily made with the intention of being statistically representative of the population. Rather the researcher uses subjective methods such as personal experience, expert judgment and convenience.
In contrast, Probability sampling is a type of sampling which every member of a population has an equal chance of selection and it is mostly used for survey based research were emphasis is placed on making inferences of a population from a sample. Probability sampling ensures that the sample is representative (Saunders, et al., 2003).
Probability sampling can be categories into five groups; simple random, systematic, stratified random, cluster and multi stage (Saunders, et al., 2003).
Simple random sampling:- involves selecting the sample at random from the sampling frame using a purely random process (eg. Random-number tables and computer programming).
Systematic Sampling: is a sampling technique where every Kth element in the population is sampled, beginning with a random start of an element in the range of 1 to k. it entails selecting the sample at regular intervals from the sampling frame by every 1/k case (Cooper & Schindler, 2006).
Stratified sampling: involves creating a sampling frame for each categories of cases normally referred to as strata. A random sample is drawn from each of the strata after which they are put together to form the sample.
Cluster sampling: similar to stratified sampling, it involves creating a sampling frame for larger cluster units prior to sampling. With cluster sampling the sampling frame is the complete list of clusters rather than a complete list of individual cases within the population (Saunders, et al., 2003).
Multi stage sampling: it is a complex form of cluster sampling and mostly employed when the study involves a geographically dispersed population. It involves randomly sampling a series of clusters.
In selecting the sample of 103 respondents a systematic sampling was used. Systematic sampling is a statistical method involving the selection of elements from an ordered sampling frame. In this method, instead of using list of random numbers the researcher calculates a sampling interval and the interval becomes the quasi-random method. The sampling interval k is calculated as;
k =
where n is the sample size and N is the population or sampling frame size. The sampling interval tells the researcher how to select elements from the sampling frame by skipping elements in the frame before selecting one for the sample (i.e., selecting every kth element). After calculating the sampling interval the starting point must be selected at random and from the starting point choices thereafter are at regular intervals.
This technique was chosen because the sampling frame consisted of a list of hotels that have web sites and the list was formed without any kind of cycle or pattern, thereby eliminating any fear of non representativeness or bias. Also considering the sample size of one hundred and three (103) and a sampling frame of two hundred and six (206), the method can be easily applied to achieve the desire results.
The sampling interval was calculated and the resulting sampling interval was 2 using the formula (k= ) (i.e., k=). With a sampling interval of 2 we randomly picked a starting point which was between the 1st and 2nd element which eventually turn out to be the second element. Starting from the second element every 2nd count was selected to participate in the research to finally arrive at the sample size of 103 respondents.
|