Statistical Representations
Studying this course? Keep your progress in one place.
Key facts
- Pie chart angle ; pictograms need a key.
- Histogram bars touch. With unequal widths, height is frequency density and area is frequency.
- Cumulative frequency is plotted at the upper class boundary and joined with a smooth curve.
- A box plot shows minimum, Q1, median, Q3 and maximum; .
- Scatter graphs show correlation; use a line of best fit to predict, within the data range.
Bar charts, pie charts, pictograms
Each shows categories: bar height gives frequency, pie sector angle gives share, and each pictogram symbol stands for a fixed amount.
Bar charts: equal-width bars with gaps, labelled axes.
Pie charts: angle .
Pictograms: each symbol is a fixed number of items; partial symbols show smaller amounts. Always give a key.
| Bar chart | Pie chart | Pictogram | |
|---|---|---|---|
| Shows | Height = frequency | Angle = share of 360° | Symbols = fixed amount |
| Must have | Gaps between bars | Show the angle calculation | Needs a key |
Bar chart
- Shows:
- Height = frequency
- Must have:
- Gaps between bars
Pie chart
- Shows:
- Angle = share of 360°
- Must have:
- Show the angle calculation
Pictogram
- Shows:
- Symbols = fixed amount
- Must have:
- Needs a key
Worked example
A pie chart is drawn for 80 people. 20 chose football. Find the angle.
- 1
20 ÷ 80 = ¼.
- 2
¼ × 360.
One symbol stands for 10 items. How many items are 3.5 symbols?
Histograms
For equal class widths height shows frequency; for unequal widths height is frequency density.
Histogram bars touch because the data is continuous.
With unequal class widths (Higher Tier), use frequency density for the height, so that the area of each bar is the frequency.
Frequency frequency density class width.
| Bar chart | Histogram | |
|---|---|---|
| Data | Categorical or discrete | Continuous, grouped |
| Bars | Gaps between bars | Bars touch |
| Height shows | Frequency | Frequency density |
Bar chart
- Data:
- Categorical or discrete
- Bars:
- Gaps between bars
- Height shows:
- Frequency
Histogram
- Data:
- Continuous, grouped
- Bars:
- Bars touch
- Height shows:
- Frequency density
- Frequency density
Worked example
A bar has frequency density 2.5 and width 4. Find the frequency.
- 1
Frequency = 2.5 × 4.
A class 10–30 has frequency 50. What is its frequency density?
Cumulative frequency
Plot the running total against the upper class boundary and join the points with a smooth curve.
Cumulative frequency is a running total.
- Add each frequency to the total so far.
- Plot at the upper class boundary.
- Start the curve at the lower boundary with 0.
- Join with a smooth curve.
For values, read across from , and to get the quartiles and median.
Worked example
For the 100 values, find the median from the graph.
- 1
Median is at 50 on the vertical axis.
- 2
Read across to the curve, then down.
Where should each point be plotted?
Box plots
A box plot shows the minimum, quartiles, median and maximum, so two data sets can be compared.
(Higher Tier) A box plot is drawn from five values: minimum, lower quartile, median, upper quartile and maximum.
The box runs from the lower to the upper quartile, with a line at the median. Whiskers reach the minimum and maximum.
The box width is the interquartile range .
- 1
Minimum
Start of the left whisker
- 2
Lower quartile
Left edge of the box
- 3
Median
Line inside the box
- 4
Upper quartile
Right edge of the box
- 5
Maximum
End of the right whisker
Median
- A higher median means higher typical values
Spread
- Compare IQR or range
Skew
- Median off-centre in the box
Worked example
A data set has minimum 10, Q1 20, median 30, Q3 45, maximum 60. Find the IQR and the range.
- 1
IQR = 45 − 20 = 25.
- 2
Range = 60 − 10 = 50.
Which part of a box plot shows the interquartile range?
Scatter diagrams
Describe a scatter diagram by its direction and strength, and use the line of best fit for predictions.
Strong correlation: points close to a line. Weak: more scattered.
A line of best fit balances the points either side. It need not pass through the first and last points.
Predicting inside the data range is interpolation; beyond it is extrapolation and less reliable.
| Positive | Negative | None | |
|---|---|---|---|
| Pattern | Both rise together | One rises, the other falls | No pattern |
| Example | Height and shoe size | Age of a car and its value | Shoe size and exam mark |
Positive
- Pattern:
- Both rise together
- Example:
- Height and shoe size
Negative
- Pattern:
- One rises, the other falls
- Example:
- Age of a car and its value
None
- Pattern:
- No pattern
- Example:
- Shoe size and exam mark
Points slope downward from left to right and lie close to a line. What is this?
Time series
Describe the trend, any seasonal pattern, and unusual values; a moving average smooths the short-term ups and downs.
Time is on the horizontal axis. Look for:
- trend: the general direction
- seasonality: a pattern repeating at fixed intervals
- anomalies: unusual spikes or drops
A moving average smooths fluctuations to show the trend.
- 1
Trend
Which way overall?
- 2
Seasonality
Repeating peaks and troughs?
- 3
Anomalies
Unusual values?
- 4
Moving average
Smooth to see the trend
Worked example
Sales are 10, 14, 12, 16, 14. Work out the 3-point moving averages.
- 1
(10 + 14 + 12) ÷ 3 = 12.
- 2
(14 + 12 + 16) ÷ 3 = 14.
- 3
(12 + 16 + 14) ÷ 3 = 14.
What is the main purpose of a moving average?
Try an exam question
The table shows the times 100 people took to finish a puzzle: 0 < t ≤ 10: frequency 20; 10 < t ≤ 30: frequency 50; 30 < t ≤ 60: frequency 30. Work out the frequency density for each class, ready to draw a histogram.
[4 marks]
- [1]Frequency density = frequency ÷ class width.
- [1]0 < t ≤ 10: 20 ÷ 10 = 2.
- [1]10 < t ≤ 30: 50 ÷ 20 = 2.5.
- [1]30 < t ≤ 60: 30 ÷ 30 = 1.
That's the notes covered.
Carry on to the next subtopic.
Try a question
Which subject is the mode of this data set?
1 mark, marked against the mark scheme
Which subject is the mode of this data set?
1 mark, marked against the mark scheme