🧠 Correlational and Descriptive Research
📌 Key terms
| Term | Definition |
|---|---|
| Correlation | A statistical relationship between two or more variables, showing how one changes with the other. |
| Positive Correlation | When both variables increase or decrease together (e.g., stress and blood pressure). |
| Negative Correlation | When one variable increases as the other decreases (e.g., exercise and anxiety). |
| Zero Correlation | When there is no relationship between two variables. |
| Correlation Coefficient (r) | A numerical value (from -1.0 to +1.0) that expresses the strength and direction of a relationship. |
| Descriptive Research | Research that observes and describes behaviour without manipulating variables. |
| Survey Method | Collects self-reported data through questionnaires or interviews. |
| Naturalistic Observation | Observing subjects in their natural environment without interference. |
| Case Study (Quantitative Aspect) | Collects detailed, often numerical data from one or a few individuals. |
| Causation vs Correlation | Correlation identifies a relationship, but only experimentation can establish causation. |
📌 Notes
Correlational and descriptive research methods are essential when manipulation of variables is impractical or unethical, offering insight into natural associations between phenomena.
1. Correlational Research
- Seeks to identify the strength and direction of a relationship between two measured variables.
- Uses Pearson’s r as a measure (values close to +1 or -1 indicate strong relationships).
- Example: Kendler et al. (2006) – twin study showing a positive correlation in genetic predisposition to depression between monozygotic twins.
Strengths:
- Useful for studying variables that cannot be manipulated (e.g., intelligence, personality, genetic traits).
- Enables prediction of one variable based on another.
- High external validity if data collected naturally.
Limitations:
- Correlation ≠ causation. No directionality (does A cause B or vice versa?) or third-variable control.
- Susceptible to spurious correlations (e.g., ice cream sales and drowning both increase in summer).
- Interpretation requires caution and statistical literacy.
2. Descriptive Research
- Aims to observe, record, and describe behaviour.
- Often forms the foundation for hypothesis generation.
- Methods include surveys, structured observations, and archival data analysis.
- Example: Levine et al. (2001) — cross-cultural study measuring helping behaviour in urban environments.
Strengths:
- Provides real-world insights and large data sets.
- Cost-effective and relatively easy to administer.
Limitations:
Subject to self-report bias in surveys or observer bias in naturalistic settings.
🔍Tok link
Correlational research raises questions about interpretation of evidence and the nature of causality:
- “How do we know if one variable causes another or merely coexists with it?”
- TOK prompt: “Does identifying a pattern in data always count as knowledge?”
🌐 Real-World Connection
Correlational research forms the basis of studies in epidemiology, education, and health psychology.
- For example, correlations between smoking and lung cancer paved the way for public health interventions.
- Psychologists use correlations to explore links between screen time and mental health, income and well-being, or parenting styles and achievement.
❤️ CAS Link
- Students could design a survey project exploring correlations between stress and sleep patterns or social media use and academic motivation within their school community — combining service (awareness-raising) and creativity (data visualization).
🧠 IA Guidance
- Correlational designs can inspire extended essay or IA pilot projects, even though IB IAs must remain experimental.
- Students can include correlational pilot data for background exploration or use it to justify an experimental hypothesis.
- Always interpret data cautiously and note that correlation ≠ causation.
🧠 Examiner Tips
- Define “correlation” clearly — don’t confuse it with “cause.”
- Use terms like positive, negative, and strength precisely.
- When referencing correlational studies, mention the coefficient (r) where possible.
- Always discuss the third-variable problem in evaluations.