Welcome to the World of Correlations!

Have you ever noticed that when the weather gets hotter, people seem to buy more ice cream? Or that as students spend more time revising, their exam stress might actually go down? These patterns are what psychologists call correlations. In this chapter, we will explore how we measure relationships between things without necessarily saying one "causes" the other. It’s like being a detective looking for patterns in the world!

1. What is a Correlation?

A correlation is a research method that looks for a relationship between two co-variables. Unlike an experiment, where we change one thing to see what happens to another, in a correlation, we simply measure two things that already exist and see if they link up.

Key Term: Co-variables
In experiments, we talk about Independent and Dependent Variables. In correlations, we use the term co-variables because both variables are simply measured; neither one is being "manipulated" or changed by the researcher.

Example: If we are looking at the relationship between "hours of sleep" and "test scores," both "hours of sleep" and "test scores" are our co-variables.

Quick Review: Remember, if you are asked to plan a correlation in Paper 2, never use the terms IV or DV! Always use "co-variables."

2. Direction of Correlations

Relationships can go in different directions. Think of these like the "slope" of a hill.

A. Positive Correlation

In a positive correlation, as one co-variable increases, the other co-variable also increases. They move in the same direction.

Example: The more hours you spend practicing a sport, the higher your skill level becomes. Both variables go \(up\).

B. Negative Correlation

In a negative correlation, as one co-variable increases, the other co-variable decreases. They move in opposite directions.

Example: The more often a student is absent from school, the lower their final grade might be. One goes \(up\), the other goes \(down\).

C. Zero Correlation

A zero correlation means there is no relationship at all between the two variables.

Example: There is likely a zero correlation between your shoe size and your ability to speak a second language. They just don't affect each other!

3. Visualizing Data: Scatter Graphs

We use scatter graphs (also called scatter plots) to show correlational data. Each dot on the graph represents one participant's score for both co-variables.

  • Positive: The dots flow from the bottom-left to the top-right.
  • Negative: The dots flow from the top-left to the bottom-right.
  • Strength: If the dots are very close to a straight line, it is a strong correlation. If the dots are spread out but still show a trend, it is a weak correlation.

Top Tip for Exams: When drawing a scatter graph, always remember to label your axes with the names of your operationalised co-variables!

4. The Golden Rule: Lack of Causality

This is the most important rule in psychology research methods: Correlation does NOT equal causation.

Just because two things are related doesn't mean one caused the other. There might be a third variable (an intervening variable) that is actually causing the change.

The Classic Analogy: Ice cream sales and shark attacks are positively correlated (they both go up at the same time). Does eating ice cream cause shark attacks? No! The third variable is warm weather. When it’s sunny, more people eat ice cream AND more people go swimming in the ocean where sharks are.

Key Takeaway:

In a correlation, we can only say the variables are related or associated. We can never say one caused the other.

5. Hypotheses in Correlations

Just like in experiments, we need to predict what will happen. However, the wording is slightly different.

Alternative Hypotheses

  • Directional (One-tailed): Predicts exactly which way the relationship will go.
    "There will be a significant positive correlation between the number of coffee cups drunk and heart rate."
  • Non-directional (Two-tailed): Predicts there will be a relationship, but doesn't say if it will be positive or negative.
    "There will be a significant correlation between age and reaction time."

Null Hypothesis

This predicts that any relationship found is just down to chance.
"There will be no significant relationship between variable A and variable B."

6. Evaluating Correlations

Don't worry if evaluation seems tricky! Just think about what is good and what is "missing" compared to an experiment.

Strengths:
  • Ethical approach: We can investigate things that would be unethical to manipulate. (e.g., We can't make people smoke to see if it causes lung cancer, but we can measure how much they already smoke and compare it to their health).
  • Good for starting research: If we find a strong correlation, it suggests that an experiment might be worth doing later to find the cause.
Weaknesses:
  • No Causality: As we discussed, we can't prove that one variable causes the change in the other.
  • Hidden Variables: A third, unmeasured factor might be influencing the results, making the relationship look more important than it is.

7. Operationalising Variables

In Paper 2, you may be asked to "operationalise" your co-variables. This just means explaining exactly how you will measure them so someone else could repeat your study.

Vague: "I will measure how much people exercise and how happy they are."

Operationalised: "I will measure exercise by the number of minutes spent in the gym per week, and happiness using a self-report scale from \(1\) (very sad) to \(10\) (very happy)."

Quick Tip: Always use numbers (quantitative data) for correlations so you can plot them on a scatter graph!

Summary Checklist

1. Do you have two co-variables? (Not an IV and DV!)
2. Is your hypothesis correctly worded for a correlation?
3. Can you identify if a relationship is positive or negative?
4. Have you remembered that you cannot claim one thing caused the other?

Next Step: You might want to look at Self-reports or Observations, as these are often the ways we gather the data used in a correlation!