Sampling Techniques (DP IB Psychology): Revision Note

Opportunity sampling is also known as convenience sampling

This is where the researcher selects participants who are available and willing at the time

• E.g., supermarket shoppers at 11am; students in a lecture; parents at a baby yoga group

The sample used in psychological research is taken from a target population

• A researcher who wishes to investigate the effects of being a single teen parent will require their sample to be drawn from that specific population

  • This is an example of a distinct target population

• A researcher is running an experiment on the duration of short-term memory (STM)

  • Generally, anyone from the age of 18 to 60 years old would suffice, i.e., a distinct target population is not required

The researcher draws the sample from the population to take part in the experiment and then generalises the findings across the target population

The 'convenience' aspect of opportunity sampling is a strength, as it is a quick and easy way of obtaining participants for a study

As people have been approached and agreed to take part, this is more likely to mean that the research process runs smoothly

• Having unwilling or resistant participants could damage the validity of the findings

It is not possible to generalise from an opportunity sample, as the sample only represents those who were available and willing to participate at the time

The researcher may be prone to unconscious bias when they approach people to take part in the study, e.g.,

• they may tend to approach people they feel comfortable with

• they may select only those participants who they think will be interested

• they may avoid some social groups that they are wary of, e.g., males aged 18-25

Self-selecting sampling (also known as volunteer sampling) involves people actively selecting themselves to participate in a study, i.e., they volunteer to take part

A researcher finds a specific way or ways in which to find their sample, e.g.,

• putting up posters and flyers around a university campus asking for volunteers to participate in a study

• posting an advert on various social media platforms

• running an advert in a print newspaper

The research will advertise when and where the study is taking place and how they can participate

The advert may specifically ask for people with certain characteristics, e.g.,

• first-time parents

• people with ADHD

• bilingual people

This method is quick, easy and cost-effective

• It is one of the most used (probably the most popular) sampling methods by psychologists

Participants are likely to be willing and enthusiastic about the research

• They have made a conscious decision to take part in the research, which means that they are less likely to jeopardise the study and its results

This method is prone to volunteer bias

• The results are not easy to generalise, as volunteer participants often have personality traits in common, e.g. sociable, outgoing, etc.

Volunteers may be prone to acquiescence bias

• This tendency to please the researcher may give rise to demand characteristics, which in turn affect the validity of the findings

Random sampling involves obtaining a sample taken from a population in way which has the least bias out of all of the sampling methods

With random sampling, every member of the population has an equal chance of being selected

How a random sample could be achieved includes:

• putting all the names of the population in a container and then drawing out one name at a time until the optimum sample size has been reached

  • e.g., a sample size of 50

• employing a computer name-generator software

  • this is more useful if a large sample is required, e.g., 2,000 participants

This sampling method eliminates researcher bias, as the researcher has no control over who is selected to be in the sample

Using a random sample means that the study results should be fairly representative

• This means that the findings can be generalised to the target population

Random sampling can be time-consuming and impractical

• It is not always possible to get access to all the information on a target population

• Additionally, not everyone selected for the sample may want to take part in the study

Random sampling can result in a non-representative sample

• Due to the nature of the method, the sample could be unbalanced

  • An all-male sample could be selected randomly, which may not be a true representation of the target population 

Stratified sampling generates a small-scale reproduction of the target population

• The target population is divided and categorised according to key characteristics required by the research, e.g.,

  • age

  • gender

  • education level

  • ethnicity

  • profession

The population is sampled within each category proportional to the overall total

• E.g., If the whole population has a total of 18% of males aged 30-40, then the representative sample will have 18% of males aged 30-40

The sample is representative of the target population as it is based on exact proportions of the target population

• This means that it is easy to generalise data from the sample to the wider population

Stratified sampling means that the researcher has control over the chosen categories, which can be selected according to how relevant they are in terms of the research aim

Stratified sampling can be difficult when researchers cannot confidently classify every member of the population into a subgroup

Gathering the sample population can be time-consuming

• It is not always possible to get access to all the information on a target population

Snowball sampling is used when the researcher wishes to gain access to a population that may be difficult to find for various reasons such as:

• they belong to an exclusive group or one which is tricky to access, e.g., ex-members of a cult, gang members

• they would be unlikely to respond to the usual type of advertisement asking for participants, e.g., people who are heroin users and people who have spent time in prison

• they may feel nervous or compromised if the researcher were to approach them directly, e.g., people who regularly shoplift and people who suffer from extreme post-natal depression

To get around the above problems, the researcher finds their first one (or a few) participants and asks them if they can recruit other, similar participants for the study

• Once the existing participant(s) start recruiting others, then these new participants may in turn recruit more participants

This type of sampling means that hard-to-reach populations can be represented in research

• Without this sampling method it would be difficult to understand the experiences of people who have unconventional lives

Being recommended to a researcher by someone in a similar situation (e.g., a fellow heroin user or ex-cult member) can instil feelings of trust in the participant

• Establish good rapport between researcher and participant is particularly important in qualitative research

The very specific choice of participants – who are likely to report similar experiences – means that the scope of the research is limited somewhat

The researcher has little control over who joins the sample, having to rely on recommendations and referrals from other people

• This may threaten the credibility of the findings