Sampling methods
- 2. NB! Students studying the Cambridge syllabus will only be asked questions about random, stratified and quota sampling – the other methods are included for comparison purposes and to show the range of possible alternatives.
- 3. Probability Sampling This involves the selection of a sample from a population based on the principle of random chance. It is more complex, more time-consuming and usually more costly than non-probability sampling. However, because the sample is selected randomly and the probability of each unit’s inclusion in the sample can be calculated, very reliable estimates can be made about both the whole target market (the ‘statistical population’) and about the chances of errors occurring. Following are the most common probability sampling methods.
- 4. 1. Simple Random Sampling This makes sure that every member of the population has an equal chance of selection. Each member of the target population has an equal chance of being included in the sample.To select a random sample the following are needed: • a list of all of the people in the target population • sequential numbers given to each member of this population • a list of random numbers generated by computer. If a sample of 100 is required, then the first 100 numbers on the random number list are taken and the people who had these numbers allocated to them will form the sample. Advantages: Simple to design and interpret; can calculate both estimate of the population and sampling error. Disadvantages: Need a complete and accurate population listing; may not be practical if the sample requires lots of small visits over the country.
- 5. 2. Systematic Sampling After randomly selecting a starting point from the population between 1 and *n, every nth unit is selected. *n equals the population size divided by the sample size. In this method, the sample is selected by taking every nth item from the target population until the desired size of sample is reached. For example, suppose a supermarket wants to study the buying habits of its customers.The sample could be chosen by asking every tenth customer entering the supermarket until the required sample size had been reached.The researcher must ensure that the chosen sample does not hide a regular pattern, and a random starting point must be selected. Advantages: Easier to extract the sample than via simple random; ensures sample is spread across the population. Disadvantages: Can be costly and time-consuming if the sample is not conveniently located.
- 6. 3. Stratified Sampling This method recognises that the target population may be made up of many different groups with many different opinions.These groups are called strata or layers of the population and for a sample to be accurate it should contain members of all of these strata – hence the term, stratified sampling. For example, if you were asked to sample 100 fellow students in your school about soft drink preferences for the school shop, it would be more accurate if, instead of asking 100 friends, you split the school up into certain strata, such as class groups, ages or gender. So if the whole school contains 1,000 students of whom 50 are girls inYear 8, an accurate sample of 100 would contain five girls fromYear 8 (50/1,000 × 100).This process would be repeated with all year groups until the total required sample of 100 was reached.The people to be surveyed in each stratum should be selected randomly. Stratified sampling may also be used when a product is designed to appeal to just one segment of the market. So if a computer game is aimed at 16−24-year-olds, only people from this stratum of the population will be included in the market research sample.
- 7. 4. Quota Sampling The aim is to obtain a sample that is "representative" of the overall population. The population is divided ("stratified") by the most important variables such as income, age and location.The required quota sample is then drawn from each stratum. This is similar to stratified sampling. By this method, interviewees are selected according to the different proportions that certain consumer groups make up of the whole target population. For instance, if it is already known that out of all consumers of denim jeans: • 65% are male • 35% are female • 35% are aged 14–20 • 35% are aged 21–30 • 20% are aged 31–40 • 10% are aged over 41 then the sample selected would conform to the same proportions.Therefore, if there were a sample of 200 people, 130 would be male, 70 female, 70 between 14 and 20 years old and so on.The interviewer could then choose the quotas by questioning the right number of people in the high street. However, the interviewer might be biased in their selection of people in each quota – preferring to ask only very attractive people, for example.This makes quota sampling less probability-based than the other methods and more open to individual bias. Advantages: Quick and easy way of obtaining a sample. Disadvantages: Not random, so some risk of bias; need to understand the population to be able to identify the basis of stratification.
- 8. 5. Cluster Sampling Units in the population can often be found in certain geographic groups or "clusters" for example, primary school children in Derbyshire. A random sample of clusters is taken, then all units within the cluster are examined. When a full sampling frame list is not available or the target population is too geographically dispersed, then cluster sampling will take a sample from just one or a few groups – not the whole population.This might be just one town or region and this will help to reduce costs – but it may not be fully representative of the whole population. Random methods can then be used to select the sample from this group. A multinational company wanting to research global attitudes towards its product would save time and money by concentrating on just a few areas for its research. Advantages: Quick and easy; doesn't need complete population information; good for face-to-face surveys. Disadvantages: Expensive if the clusters are large; greater risk of sampling error.
- 9. Non- Probability Sampling This approach to sampling cannot be used to calculate the probability of any particular sample being selected. Non- probability sample results cannot be used to make inferences or judgements about the total population.Any general statements that are made as a result of this method of sampling must be analysed very carefully and filtered by the researcher knowledge of the topic being researched. Following are the most common methods of non- probability sampling.
- 10. 1. Convenienc e Sampling Uses those who are willing to volunteer and easiest to involve in the study. Members of the population are chosen based on their relative ease of access. Sampling friends, fellow workers or shoppers in just one location are all examples of convenience sampling. Advantages: Subjects are readily available; large amounts of information can be gathered quickly Disadvantages: The sample is not representative of the entire population, so results can't speak for them - inferences are limited; prone to volunteer bias.
- 11. 2. Snowball Sampling The first respondent refers a friend who then refers another friend… and so the process continues.This is a cheap method of sampling and is often used by companies in the financial services sector, such as health- and motor-insurance companies. It is likely to lead to a biased sample, as each respondent’s friends are likely to have a similar lifestyle and opinions.
- 12. 3. Judgement Sampling A deliberate choice of a sample - the opposite of random. The researcher chooses the sample based on who they think would be appropriate to study.This could be used by an experienced researcher who may be short of time as they have been asked to produce a report quickly. Advantages: Good for providing illustrative examples or case studies. Disadvantages: Very prone to bias; samples often small; cannot extrapolate from sample.
- 13. 4. Ad Hoc Quotas A quota is established (say 55% women) and researchers are told to choose any respondent they wish up to the pre-set quota.
- 14. In Conclusion • All of these samples are likely to lead to less accurate results – which are less representative of the whole population – than probability sampling techniques. • Each method of sampling has its own advantages and limitations – so which is best?This depends on the size and financial resources of the business and how different consumers are in their tastes between different age groups and so on.Cost-effectiveness is important in all market research decisions.
- 15. Sources • Simpson, P. & Farquharson,A. 2014. Cambridge International AS and A Level Business Coursebook with CD-ROM (Cambridge International Examinations). Cambridge University Press. • Tutor2u. Market Research: Sampling.Available: https://www.tutor2u.net/business/reference/marketing -research-sampling