Step 14 of 18 · Worked example · TEACH

← Statistics & Probability

0 of 3 done

Work through the example to CHECK to open the problems.

Reach CHECK to open the problems.Higher Level · Statistics · Step 14

Describe, predict, judge the prediction, then judge the claim.

For ten students, hours of study h (from 1 to 8) and test score s (out of 100) are recorded: r = 0.86 and the line of best fit is s = 42 + 5.1h. For the same students, daily hours of phone use and test score give r = −0.6. Describe both relationships, predict s for 6 hours of study, and comment on 30 hours. A report says phone use lowers scores: judge the claim.

Hours studied against test score

Hours studiedTest score

Strong positive linear association; more study hours go with higher scores. Correlation coefficient: r = 0.86. A pattern here describes association only, never cause.

Each point is one student; the pattern rises but is not perfectly straight.

For ten students, hours of study h (from 1 to 8) and test score s (out of 100) are recorded.

r = 0.86, and the line of best fit is s = 42 + 5.1h.

For the same students, daily hours of phone use and test score give r = −0.6.

Describe both relationships. Predict s for 6 hours of study. Comment on 30 hours.

A report says phone use lowers scores. Judge the claim.

Read it once, slowly. Then copy it onto your page.
  • What is going on? Two numbers per student: hours of study, from 1 to 8, and a score out of 100. Pairs like this are bivariate data.
  • What is given? Two correlation coefficients, 0.86 and −0.6, and a line: start at 42, add 5.1 marks per hour.
  • Asks: describe both; predict for 6 hours; comment on 30 hours.
  • And a report claims phone use lowers scores. Judge it.
Céim

Higher Level Maths · Statistics & Probability · Step 14 of 18

Bivariate Data, Scatterplots & Correlation

A scatterplot shows whether two numerical variables move together; the correlation coefficient measures how closely, and nothing more.

Why it matters

Prediction from a line of best fit and the refusal to claim causation are both examined every year.

The worked example

For ten students, hours of study h (from 1 to 8) and test score s (out of 100) are recorded. r = 0.86, and the line of best fit is s = 42 + 5.1h. For the same students, daily hours of phone use and test score give r = −0.6. Describe both relationships. Predict s for 6 hours of study. Comment on 30 hours. A report says phone use lowers scores. Judge the claim.

How the worked example goes

  1. Read

    • What is going on? Two numbers per student: hours of study, from 1 to 8, and a score out of 100. Pairs like this are bivariate data.
    • What is given? Two correlation coefficients, 0.86 and −0.6, and a line: start at 42, add 5.1 marks per hour.
    • Asks: describe both; predict for 6 hours; comment on 30 hours.
  2. Understand

    • What does r tell me?
    • The sign gives the direction: + means both rise together, − means one falls as the other rises.
    • The size gives the strength: near 1 (or −1) the points hug a straight line; around 0.5 a clear trend with scatter; near 0 little linear link.
  3. Reduce

    • Where do I start?
    • 1. Describe each r: sign, then size.
    • 2. Put h = 6, then h = 30, into the line. Is each inside 1 to 8?
  4. Solve

    • Describe both relationships.
    • r = 0.86: positive, and close to 1. More study goes with higher scores, points close to a rising line: a strong positive linear association.
    • r = −0.6: negative, size 0.6. More phone use goes with lower scores, with a lot of scatter: a moderate negative linear association.
  5. Check

    • Is it right?
    • Work back from 72.6: (72.6 − 42) ÷ 5.1 = 6 ✓
    • 72.6 lies between the line's values at the ends of the data, 47.1 at 1 hour and 82.8 at 8 hours ✓

Common mistakes to avoid

Key terms

bivariate · scatterplot · correlation coefficient · line of best fit · prediction · causation