Data summaries, histograms and interpretation
Introduit| English | Sens |
|---|---|
| frequency density/ˈfriːkwənsi ˈdensɪti/ | densité de fréquence |
A chart that changed hospitals, 1858
- In 1858, Florence Nightingale sent the British government a "rose diagram" of soldiers' deaths in the Crimean War. It showed that far more soldiers died of preventable disease in field hospitals than of wounds. Her charts helped bring in army sanitary reform. A good diagram can make a summary of data impossible to ignore.
- This lesson covers the summaries and diagrams AQA expects: means, standard deviation, quartiles, box plots and histograms.
Centre
- Mean $\bar{x} = \dfrac{\sum x}{n}$; for grouped data, $\dfrac{\sum fx}{\sum f}$ using midpoints.
- The median is the middle value; it is not pulled by extreme values.
Find the mean of 3, 7, 8, 10, 12.
Difficulté 2/5 · 140 pièces + un petit bonus lors de la première réussite aujourd'hui
$40 \div 5$.
Classes 0–10 (frequency 4), 10–20 (6). Estimate the mean.
Difficulté 2/5 · 140 pièces + un petit bonus lors de la première réussite aujourd'hui
$\tfrac{5 \times 4 + 15 \times 6}{10}$.
Spread
- Standard deviation $\sigma = \sqrt{\dfrac{\sum x^2}{n} - \bar{x}^2}$; the interquartile range is $Q_3 - Q_1$.
- An outlier is often defined as more than $1.5 \times \text{IQR}$ beyond a quartile, or more than 2 standard deviations from the mean.
Data summaries, histograms and interpretation
Compare an appropriate average and spread in context
Choose a centre and a spread measure for the worked observations.
Worked example: mean and standard deviation
For 10 days, rainfall (mm) has $\sum x = 52$ and $\sum x^2 = 410$. Find the mean and standard deviation, and decide whether a day with 14 mm is an outlier (2 s.d. rule).
- Mean: $\bar{x} = 5.2$ mm.
- Standard deviation: $\sqrt{41 - 5.2^2} = \sqrt{13.96} = 3.74$ mm.
- Outlier: $5.2 + 2(3.74) = 12.7 < 14$, so yes, 14 mm is an outlier.
For 8 values, $\sum x = 40$ et $\sum x^2 = 232$. Find the standard deviation.
Difficulté 2/5 · 140 pièces + un petit bonus lors de la première réussite aujourd'hui
$\bar{x} = 5$; $\sqrt{\tfrac{232}{8} - 5^2} = \sqrt{4}$.
Histograms
- With unequal class widths, the bar height is the frequency density 频率密度 $= \dfrac{\text{frequency}}{\text{class width}}$; the area shows frequency.
- A class 20–30 with frequency 15 has density 1.5.
A class 40–60 has frequency 30. Find its frequency density.
Difficulté 2/5 · 140 pièces + un petit bonus lors de la première réussite aujourd'hui
$30 \div 20$.
Box plots and comparison
- A box plot shows the minimum, $Q_1$, median, $Q_3$ and maximum, with outliers marked as crosses.
- Compare two data sets with one measure of centre and one of spread, in context.
$Q_1 = 12$ et $Q_3 = 20$. Above which value is a data point an outlier ($1.5 \times$ IQR rule)?
Difficulté 2/5 · 140 pièces + un petit bonus lors de la première réussite aujourd'hui
$20 + 1.5 \times 8$.
The height of a histogram bar is not the frequency. With unequal widths, a tall narrow bar can hold fewer values than a short wide one: area, not height, gives the count.
In a histogram with unequal classes, the tallest bar always holds the most values.
Difficulté 1/5 · 100 pièces + un petit bonus lors de la première réussite aujourd'hui
Area gives frequency.
Summarise centre with the mean or median and spread with the standard deviation or IQR, using $\sigma^2 = \tfrac{\sum x^2}{n} - \bar{x}^2$. Histograms plot frequency density so area is frequency. Identify outliers by a stated rule, and compare data sets in context.
Daily maximum temperatures in two towns in July: Town A median 24 °C, IQR 3 °C; Town B median 21 °C, IQR 7 °C. Compare the two towns.
One centre, one spread.