Statistics — Correlation

• Reading and interpreting scatter diagrams for bivariate data.
• Computing Karl Pearson's correlation coefficient r and its interpretation.
• Understanding the range −1 ≤ r ≤ 1 and what each value means.
• Spearman's rank correlation for ordinal data or when exact values aren't reliable.

Level 1 — Scatter diagram and qualitative correlation

Scatter diagram: Plot (xᵢ, yᵢ) on coordinate axes. Pattern indicates correlation type.

Positive correlation: Height and weight. Study hours and marks. Negative correlation: Temperature and hot beverage sales. Price and demand (law of demand).

Zero correlation: Shoe size and IQ. Birth month and salary.

Level 2 — Pearson's r and Spearman's rank correlation

Karl Pearson's r:

r = Σ(xᵢ − x̄)(yᵢ − ȳ) / √[Σ(xᵢ−x̄)² · Σ(yᵢ−ȳ)²]

Shortcut formula:

r = [nΣxᵢyᵢ − (Σxᵢ)(Σyᵢ)] / √{[nΣxᵢ² − (Σxᵢ)²][nΣyᵢ² − (Σyᵢ)²]}

Interpretation of r:

Spearman's rank correlation (rₛ): For ranked data or when distribution is non-normal.

rₛ = 1 − 6ΣD²ᵢ / [n(n²−1)]

where Dᵢ = difference in ranks of the i-th observation.

JEE tip: In JEE problems, the shortcut formula is faster. Set up a table with columns: x, y, x², y², xy. Compute column sums, then plug into formula.

NCERT spotlight — Correlation vs causation

Correlation measures linear association; it does NOT imply causation. Classic example: ice cream sales correlate with drowning deaths — both caused by hot weather (confounding variable). Valid correlation with likely causation: studying more → better marks. Always question: is there a third factor?

Properties of r: −1 ≤ r ≤ 1 always. r is dimensionless and unit-free. r unchanged by shifting (adding constant) or scaling (multiplying by positive constant). Same r for (x,y) and (y,x).

Limitation of Pearson's r: Only detects linear relationships. Two variables can be strongly related non-linearly yet have r ≈ 0.

Find Pearson's r for: x: 1, 2, 3, 4, 5; y: 2, 4, 5, 4, 5.

Step 1 — Set up table:
  x:   1,  2,  3,  4,  5   → Σx = 15
  y:   2,  4,  5,  4,  5   → Σy = 20
  x²:  1,  4,  9, 16, 25   → Σx² = 55
  y²:  4, 16, 25, 16, 25   → Σy² = 86
  xy:  2,  8, 15, 16, 25   → Σxy = 66
Step 2 — n = 5.
Step 3 — r = [5(66) − 15×20] / √{[5(55)−225][5(86)−400]}
         = [330 − 300] / √{[275−225][430−400]}
         = 30 / √{50 × 30}
         = 30 / √1500
         = 30 / 38.73
         ≈ 0.775.
Step 4 — Interpretation: positive moderate-to-strong linear correlation ✓.

Applications — data science and research

Pearson's r forms the basis of linear regression. Rank correlation used in sports rankings, academic performance comparisons. Heatmaps in data science show correlation matrices. Medical research uses correlation to identify risk factors (e.g., smoking and lung capacity).

• Describe what r = −0.9 tells you about two variables.
• In Spearman's formula, n = 5 and ΣD² = 10. Find rₛ.
• Why might ice cream sales and sunscreen sales be correlated without one causing the other?

Open the Practice tab for graded questions on Correlation.

• Use the platform-native live simulation or PhET-style tool for this topic (number line, Venn, physics playground, molecule builder, sensor dashboard, etc.).
• Mirror / body / home activity: physically do the concept (count objects, measure, role-play) and photograph or describe for portfolio.
• Voice or text reflection with AI Mentor: explain the concept to a younger student or family member.

• "Explain this concept to a Class 6 student using one real example from an Indian home, school, market, or festival."
• "What is one common mistake students make here, and how would you catch yourself making it?"
• Stretch: "How does this connect to coding, robotics, money, health, environment, or a future career?"

• Complete the core practice + one extension activity (photo, table, short reflection, or mini-project) for base XP + topic badge.
• 5-7 day streak or family discussion note = multiplier + visible artifact in parent/principal dashboard.
• Best real-world application stories (anonymised) featured on class or national leaderboard.

• One hands-on project or measurement using the Drishti kit or household items that makes the concept physical.
• Direct link to at least one Future Skill track (Money Management, Green Tech, Cyber Defenders, Micro-Entrepreneurship, AI Mastery, Sustainable Living, Personality Development).
• Coding extension where relevant (simple script, simulation, or data logging).

This material emphasises experiential "learning by doing", competency (apply/create/analyse), vocational exposure, critical thinking, and multidisciplinary connections. Designed to feed live worlds, AI Mentor (with memory), gamification, robotics, parent analytics, and future skills — not just exam prep.

Portfolio Evidence Idea: Your photo/table/reflection/project + one sentence on "How this helps me in real life or a possible future path."

Open the Practice tab for aligned questions (easy/medium/hard + case-based) with full AI scaffolding.

See curriculum for cross-links and the full future-skills/robotics chapters.