🔍

Correlation and Causation in Psychology

Sep 25, 2025

Overview

This lecture explains the difference between correlation and causation, common mistakes people make interpreting correlations, and how psychologists study and represent relationships between variables.

Correlation vs. Causation

  • Correlation means two variables are related, but it does not mean one causes the other.
  • Media headlines often misinterpret correlational findings as causal relationships.
  • The example of pizza and cancer risk illustrates why correlation does not imply causation.
  • Diets like the Mediterranean diet, not just pizza, are likely responsible for observed health benefits.

Third Variable Problem and Illusory Correlation

  • A third variable may explain the link between two correlated variables (third variable problem).
  • Example: Family violence could cause both youth violence and video game playing, not video games causing aggression.
  • Illusory correlation is when people perceive a relationship between variables that does not exist, like candy causing hyperactivity.
  • Sports superstitions are common examples of illusory correlations.

Conducting Correlational Research

  • Psychologists use correlational research to explore how well one variable predicts another.
  • Common relationships studied include GPA and attendance, money and happiness, or intelligence and income.
  • It's difficult to determine causality from correlational data.

Correlation Coefficient and Interpretation

  • The correlation coefficient (Pearson’s r) measures the strength and direction of a relationship, ranging from +1.0 to -1.0.
  • An r of 0 means no relationship exists.
  • Strong correlations are closer to ±1.0; weak correlations are closer to 0.
  • Positive correlation: as one variable increases, so does the other (e.g., treadmill use and calories burned).
  • Negative correlation: as one variable increases, the other decreases (e.g., alcohol use and judgment).

Graphing Correlations

  • Correlations are represented with scatter plots.
  • The slope shows direction; the tightness of data points shows strength.
  • Dots close to the line of best fit indicate a stronger correlation; scattered dots indicate weaker correlation.

Key Terms & Definitions

  • Correlation — a relationship or association between two variables.
  • Causation — when one variable directly causes a change in another.
  • Third Variable Problem — another variable explains the observed relationship between two variables.
  • Illusory Correlation — believing a relationship exists when it does not.
  • Correlation Coefficient (Pearson’s r) — a statistical measure of correlation strength and direction.
  • Scatter Plot — a graph representing data points for correlated variables.

Action Items / Next Steps

  • Brainstorm and list examples of positive and negative correlations.
  • Practice identifying the strength and direction of correlations given correlation coefficients.
  • Review definitions and ensure understanding of key terms before the next lesson.