Sampling and sampling methods

There are a number of sampling methods that sociologists can use, some are more likely to provide a representative sample than others.

Representative samples:

• Random sample
• Stratified sample
• Quota sample
• Systematic sample

Non-representative samples:

• Snowball sample
• Volunteer sample
• Purposive and opportunity sample

A random sample is also known as a simple random sample. If this method is being used then each member of the target population has exactly the same chance of being picked. A simple method would be to pick a name from a hat, more sophisticated ways involve computer generated random numbers. 

Despite the apparent fairness of this method, there's the possibility that the sample may not be representative, e.g. if taking a random sample inside a school this method could produce a sample that's disproportionately male or female.

This way of selecting a sample avoids the problem that occurs in random samples. Instead of having one sample from the target population as a whole, the population is divided up and then each section is sampled. It can be ensured that the correct proportions are selected. A sample frame is still used, but it needs to be one that includes the relevant information about the population's characteristics.

A quota sample is similar to a stratified sample, it doesn't require a sample frame. Instead of named indiviudals being identified for the sample, the reseacher calculates how many people from each group are required. The reseacher approaches people who match the characteristics. This is the method used by market researchers who collect data in public places like shopping centres.

Systematic sampling involves having a systematic approach to selecting participants; e.g. every 10th name on a list. This is clearly not random as not everyone has an equal chance of being selected, it's seen as a fair way of proceeding.

Systematic sampling involves having a systematic approach to selecting participants; e.g. every 10th name on a list. This is clearly not random as not everyone has an equal chance of being selected, it's seen as a fair way of proceeding.

For some research topics there won't be an easily avaialble sample frame which leads to respondents. In these cases a reseacher may rely on a gatekeeper to gain access to a group. This gatekeeper then introduces the reseacher to another person and from there the snowball starts to roll and get bigger. Hard to reach groups or those who wish to avoid attention might be approached in this way. This method isn't random, the sample is unlikely to be representative.

In the absence of a sample frame, another approach is to invite people to volunteer for the research. Such self-selecting samples are very unlikely to be representative of the target population, only those with a strong interest are likely to come forward to take part. With the development of online research and software, more studies make use of volunteer samples. This can be seen as an example of opportunity or purposive sampling.

When a reseacher has a limited time and/or there's no sampling frame available, they might simply set out to find people with characteristics that are relevant to the purpose of the study. This saves time in approaching those who are unsuitable, it won't be a representative sample.

This method is also known as convenience sampling. The sample is made up of those who are readily avaialble, willing to take part and suitable for the aim of the research. It's the method that's most likely to be used by students who lack the time and resources available to professional researchers.