Samples are selected from populations, and the term 'sample' has already been explained. In marketing research, use of the term 'population' refers to the whole group whose views are to be represented. For example, some surveys are interested in the views of the general population of the country. More commonly, marketing researchers are interested in the views of populations with characteristics of special relevance: the population of motorists, the population of housewives, the population of retail outlets for a particular type of goods, the population of suppliers of a particular type of industrial machinery, the population of professional groups such as architects, or users of social services, and so on.
Data collected from the sample are referred to as 'statistics' and these sample statistics are used to estimate the 'population parameter'. That is, results obtained from a sample are used to calculate the results that would have been obtained from the underlying population had a census been used. The degree to which it is possible to use sample statistics to estimate population parameters with an acceptable degree of accuracy depends on the sampling procedures used and on the size of the sample. The three main methods used in selecting samples are called random sampling, quota sampling and judgement sampling. The method whose statistical validity forms the foundation for the whole practice of survey research is random sampling, and for this reason it is the best known and most commonly described method of sampling. However, in practice, quota sampling has been found to give perfectly acceptable results for commercial purposes and at a cheaper cost than random sampling. Quota sampling is therefore the most commonly applied sample selection method in market research, despite its lack of statistical purity. Judgement sampling is also commonly applied in practice simply because, as its title suggests, it is often the most sensible way of approaching the sample selection problem, although it has theoretical limitations. Because of the lack of statistical purity in their manner of sample selection, quota and judgement sampling methods are sometimes referred to as 'non-probability' sampling procedures and, referring to the element of personal discretion used, they are also called 'purposive' sampling procedures.
Was this article helpful?
You won’t want to miss this. Get Paid Taking Surveys In Your Spare Time. I know what you’re thinking, ‘Oh great, another get rich quick scheme’. WRONG! This is your guide to making money from home by participating in paid surveys on the internet.