4.3 Measures of central tendency and dispersion
Studying this course? Keep your progress in one place.
Key facts
- The mean is ; for a frequency table .
- The median is the middle value and is not affected by extreme values.
- For grouped data, estimate the mean with the mid-interval value of each class.
- IQR ignores outliers; standard deviation uses every value.
- Adding shifts the mean but not the spread; multiplying by scales the spread by (variance by ).
Mean, median and mode
The mean is the sum divided by the count, the median is the middle value and the mode is the most frequent.
The mean is . For a frequency table, , which your GDC does from lists.
The median is the middle of the ordered data, or the mean of the two middle values if is even. The mode is the most frequent value.
The median is not affected by extreme values, so it suits skewed data; the mean uses every value.
- Mean
- Medianmiddle of the ordered data
- Modemost frequent value
Worked example
Find the mean, median and mode of .
- 1
Order the data: .
- 2
Mean .
- 3
There are 10 values, so the median is the mean of the 5th and 6th: .
- 4
The value appears four times, so the mode is .
Which average is least affected by one very large value?
Grouped data
Use the mid-interval value of each class to estimate the mean, and divide by the total frequency.
For grouped data the individual values are unknown, so use the mid-interval value of each class (the mean of its end points) to estimate the mean:
The modal class is the class with the greatest frequency, for equal class widths only.
Worked example
Classes have frequencies . Estimate the mean and give the modal class.
- 1
Mid-interval values: .
- 2
.
- 3
, so .
- 4
The greatest frequency is , in the class .
What is the mid-interval value of the class ?
Measures of dispersion
Range and IQR are quick measures of spread; standard deviation measures typical distance from the mean.
Range . The interquartile range is the spread of the middle half.
The standard deviation measures typical distance from the mean; the variance is . Use your GDC (one-variable statistics). At SL treat the data as the population unless stated, so use ; the sample value is slightly larger.
By hand, .
| Range | IQR | Standard deviation | |
|---|---|---|---|
| Affected by outliers | Yes | No | Yes |
| Uses every value | Yes | No | Yes |
Range
- Affected by outliers:
- Yes
- Uses every value:
- Yes
IQR
- Affected by outliers:
- No
- Uses every value:
- No
Standard deviation
- Affected by outliers:
- Yes
- Uses every value:
- Yes
Worked example
Find the variance and standard deviation of (mean ).
- 1
.
- 2
Variance .
- 3
.
Which measure of spread ignores outliers?
Quartiles from technology
Quartiles split ordered data into four equal parts; use the GDC and accept small differences from hand methods.
Quartiles divide ordered data into four equal parts: , the median and . For discrete data, find them with your GDC.
Methods differ (for example whether the median is included in each half when is odd), so a GDC value may differ slightly from a hand calculation. Use the GDC value.
Worked example
Find , and the IQR of .
- 1
Lower half: , so .
- 2
Upper half: , so .
- 3
.
and . What is the IQR?
Effect of constant changes
Adding a constant shifts the centre only; multiplying scales both the centre and the spread.
If a constant is added to every item, the mean, median and quartiles change by , but the standard deviation, variance, IQR and range are unchanged.
If every item is multiplied by , the mean, median, quartiles, standard deviation, IQR and range are all multiplied by , and the variance by .
- Mean
- Standard deviation
| Add | Multiply by | |
|---|---|---|
| Mean and median | +k | ×k |
| Quartiles | +k | ×k |
| Standard deviation, IQR, range | Unchanged | ×k |
| Variance | Unchanged | ×k² |
Add
- Mean and median:
- +k
- Quartiles:
- +k
- Standard deviation, IQR, range:
- Unchanged
- Variance:
- Unchanged
Multiply by
- Mean and median:
- ×k
- Quartiles:
- ×k
- Standard deviation, IQR, range:
- ×k
- Variance:
- ×k²
Worked example
Temperatures have mean and . They are converted by . Find the new mean, standard deviation and variance.
- 1
Mean: .
- 2
Standard deviation: multiply only, (the does not change spread).
- 3
Variance: .
Every value is multiplied by 3. By what is the variance multiplied?
Try an exam question
Ten numbers have mean and standard deviation . Each number is multiplied by and then is subtracted. Find the new mean, standard deviation and variance.
[4 marks]
- [1]New mean .
- [1]New mean .
- [1]Standard deviation (subtracting does not change spread).
- [1]Variance .
That's the notes covered.
Carry on to the next subtopic.
Try a question
Write down the mode of the number of goals.
1 mark, marked against the mark scheme
Write down the mode of the number of goals.
1 mark, marked against the mark scheme