Sampling Methods » Strengths and Weaknesses of Sampling

What you'll learn this session

Study time: 30 minutes

The strengths and weaknesses of different sampling methods
How to evaluate random, systematic, stratified, opportunity and volunteer sampling
When to use different sampling techniques in psychological research
How sampling affects the validity and reliability of research
Real-world applications of sampling methods in psychology studies

Sampling Methods: Strengths and Weaknesses

When psychologists conduct research, they rarely have the time or resources to study everyone in a population. Instead, they select a smaller group (a sample) to represent the larger population. How they choose this sample can make or break their research!

Key Definitions:

Population: The entire group of people that researchers are interested in studying.
Sample: A smaller group selected from the population to participate in the research.
Sampling: The process of selecting participants from a population for a study.
Representativeness: How well the sample reflects the characteristics of the wider population.
Sampling bias: When certain groups are more likely to be selected than others, creating a skewed sample.

Types of Sampling Methods

🎲 Random Sampling

Every member of the population has an equal chance of being selected.

Strengths:

Reduces researcher bias as selection is completely random
Highly representative if done properly
Results can be generalised to the wider population
Statistical tests can be applied to the data

Weaknesses:

Requires a complete list of the population (sampling frame)
Can be time-consuming and expensive
May still miss certain groups by chance
Not practical for very large populations

Example: Using a random number generator to select 200 students from a school of 1,000 for a study on exam stress.

📊 Systematic Sampling

Selecting participants at regular intervals from an ordered list.

Strengths:

Simpler and quicker than true random sampling
Evenly spreads the sample across the population
No need for random number generation
Can be more representative than simple random sampling

Weaknesses:

Can introduce bias if there's a pattern in the list
Still requires a complete sampling frame
If the interval coincides with a pattern, the sample will be biased
Less random than true random sampling

Example: Selecting every 10th person from a school register to participate in a survey about school lunches.

📆 Stratified Sampling

Dividing the population into specific groups (strata) and then randomly sampling from each group.

Strengths:

Ensures representation from all important subgroups
Reduces sampling error
Allows comparison between different strata
More precise than simple random sampling

Weaknesses:

Requires knowledge of the proportion of each stratum in the population
More complex and time-consuming
Difficult if people belong to multiple categories
Can be expensive to implement

Example: For a study on gender differences in maths anxiety, ensuring your sample has the same proportion of boys and girls as the school population.

👫 Opportunity Sampling

Selecting whoever is available and willing to participate at the time of the study.

Strengths:

Quick and easy to organise
Inexpensive to implement
No need for a sampling frame
Convenient for pilot studies or small-scale research

Weaknesses:

Highly likely to be biased and unrepresentative
Limited generalisability to the wider population
May over-represent certain groups who are more available
Lacks scientific rigour

Example: A researcher studying shopping habits by interviewing people who happen to be at a shopping centre on a Tuesday afternoon.

✋ Volunteer Sampling

Participants self-select by volunteering to take part in the study.

Strengths:

Easy to recruit participants
Participants are usually motivated and engaged
Can reach specific groups through targeted advertising
Useful for sensitive topics where willing participants are needed

Weaknesses:

Self-selection bias - volunteers may differ from non-volunteers
Often attracts people with strong opinions or interests in the topic
Not representative of the general population
May lead to skewed results

Example: Posting an advert for participants to take part in a study about social media usage on social media platforms.

Choosing the Right Sampling Method

Selecting the appropriate sampling method depends on several factors:

💲 Resources

Time, money and access to participants will influence your choice. Random and stratified sampling require more resources than opportunity sampling.

🎯 Research Aims

If generalisability is crucial, probability methods like random or stratified sampling are better. For exploratory research, non-probability methods might be sufficient.

👥 Population

The characteristics of your target population and how easy they are to access will affect which method is most practical and effective.

Case Study Focus: Milgram's Obedience Study

Stanley Milgram's famous obedience study used a volunteer sample of 40 males recruited through newspaper adverts. This sampling method has been criticised because:

Only included men from New Haven, Connecticut
Participants were self-selected (volunteer bias)
The sample was small and not representative of the general population
People who respond to newspaper adverts may differ from those who don't

This raises questions about whether Milgram's findings can be generalised to women, different cultures, or different time periods. Later replications with more diverse samples have helped address some of these concerns.

Sampling in Real Psychological Research

Balancing Ideal vs. Practical

While random and stratified sampling are often considered the 'gold standard' in research, many psychological studies use opportunity or volunteer sampling due to practical constraints. Researchers must acknowledge the limitations of their sampling method when discussing their findings.

When evaluating psychological research, always consider:

How were participants selected?
Is the sample representative of the population being studied?
What biases might the sampling method have introduced?
Can the findings be generalised beyond the sample?

Sampling in Action: The UK Household Longitudinal Study

This major UK study (also known as Understanding Society) uses a complex stratified sampling method to ensure representation across different regions, socioeconomic groups and ethnicities. It follows over 40,000 households to track changes in people's lives over time.

The study demonstrates how careful sampling can create a "mini UK" that allows researchers to make valid generalisations about the wider population. However, even with this sophisticated approach, the study still faces challenges with participant dropout (attrition) over time.

Summary: Strengths and Weaknesses of Sampling Methods

👍 Best for Scientific Rigour

Random and Stratified Sampling

These methods provide the most representative samples and allow for statistical generalisation to the wider population. They're essential for research that aims to establish broad psychological principles or test theories.

🕐 Best for Practical Research

Opportunity and Volunteer Sampling

These methods are quicker, cheaper and easier to implement. They're suitable for pilot studies, exploratory research, or when studying specific groups that are hard to access through random methods.

Remember: No sampling method is perfect! Good researchers acknowledge the limitations of their sampling approach and consider how it might affect their findings.

🧠 Test Your Knowledge!