Measures of Location and Spread Cheat Sheet Stats/Mech Year 1

Measures of central tendency When data is presented in a grouped frequency table, you can use interpolation to Example 1: Shamsa records the time spent out of school during lunch hour
A measure of central tendency describes the centre of the data. You need to estimate the medians, quartiles, and percentiles. This method assumes that the data to the nearest minute, 𝑥, of the students in her year in the
decide of the best measure to use in particular situations. values are evenly distributed within each class. table below. Calculate the standard deviation.
Time spent out of school (min) 35 36 37 38
+
The mode or modal class is the value of class which occurs most often. This is Q1 = th data value Frequency 3 17 29 34
,
used when data is qualitative or quantitative with one mode or two modes +
(bimodal). It is not informative if each value only occurs once. Q2 = th data value
- 1. Find Σ𝑓𝑥 # , Σ𝑓𝑥 and Σ𝑓
(+ Σ𝑓𝑥 # = 3 × 35# + 17 × 36# + 29 × 37# + 34 × 38#
Q3 = th data value
The median is the middle value when the data values are put in order. This is , = 114504
used for quantitative data and usually used when there are extreme values as Σ𝑓𝑥 = 3 × 35 + 17 × 36 + 29 × 37 + 34 × 38
they are unaffected. Measures of spread = 3082
Measures of spread shows how spread out the data is. They are also known as measures Σ𝑓 = 3 + 17 + 29 + 34 = 83
The mean can be calculated using: of dispersion or measures of variation. 2. Use formula for grouped data in frequency table to find variance:
Σ𝑥 • Range 114504 3082 #
𝑥̅ = 𝜎# = −6 7 = 0.74147 …
𝑛 The difference between largest and smallest values in the dataset. 83 83
• Interquartile range (IQR) 3. Square root variance to find standard deviation:
Where 𝑥̅ (x bar) is the mean,
The difference between upper and lower quartile. 𝜎 = √0.74147 … = 0.861 (3s.f.)
Σ𝑥 is the sum of the data values,
• Interpercentile range
𝑛 is the number of data values
Difference between the values of two given percentiles. Coding
For data given in a cumulative frequency table, the mean can be calculated Each value in the data can be coded to give a new set of values, which is easier
using: Variance (𝝈𝟐 ) and standard deviation (𝝈) to work with. Coding also changes different statistics in different ways.
Σ𝑥𝑓 The variance also shows how spread out the data is. There are 3 versions of the formulae
𝑥̅ = !"#
Σ𝑓 used to find variance: If data is coded using the formula 𝑦 = , where 𝑎 and 𝑏 are constants that
/(!"!̅ )" $
Where Σ𝑓𝑥 is the sum of the products of the 1. 𝜎 - = +
Easier to use when you have to choose or given in the question:
data values and their frequencies, given raw data !̅ "#
/! " /! - • Mean of coded data: 𝑦# =
Σ𝑓 is the sum of frequencies 2. 𝜎 - = +
−/+0 $
Rearrange the formula to find original mean: 𝑥̅ = 𝑏𝑦> + 𝑎
You can remember this as “mean of squares minus square of means” '
• Standard deviation of coded data: 𝜎& = !
2!! $
3. 𝜎 - = + Rearrange the formula to find original standard deviation: 𝜎$ = 𝑏𝜎%
The mean is used for quantitative data. It uses all values in the data therefore it
(/!)"
gives a true measure of data. However, it is affected by extreme values. Where 𝑆!! = Σ(𝑥 − 𝑥̅ )- = Σ𝑥 - − 𝑆$$ is a summary statistic
+ Example 2: A scientist measures the temperature, 𝑥℃, at five different points
used to simplify formula
You can calculate the mean, class containing median and modal class for You can use calculator to calculate 𝑆$$ of a nuclear reactor. Her results are given below:
continuous data presented in a grouped frequency table by finding the 332℃, 355℃, 306℃, 317℃, 340℃
Standard deviation is the square root of variance. !"())
midpoint of each class interval. a. Use the coding 𝑦 = to code this data.
*)

Other measures of location 2

Σ(𝑥 − 𝑥̅ )# Σ𝑥 # Σ𝑥 𝑆$$ Substitute each value into 𝑥 to get coded data, 𝑦.
The median(Q2) splits the data into two equal halves (50%). 𝜎=A =A −D E =A Original data, 𝑥 332 355 306 317 340
𝑛 𝑛 𝑛 𝑛
The lower quartile (Q1) is one quarter of the way through the dataset. Coded data, 𝑦 3.2 5.5 0.6 1.7 4.0
The upper quartile (Q3) is three quarters of the way through the dataset.
For grouped data presented in frequency table:
b. Calculate the mean and standard deviation of the coded data.
Percentiles split the data set into 100 parts. The 10th percentile is one-tenth of Σ𝑦 = 15, Σ𝑦 # = 59.74
the way through the data, for example. 10% of data values are less than the -
-
#)2
Σ𝑓(𝑥 − 𝑥 Σ𝑓𝑥2 Σ𝑓𝑥 15
10th percentile and 90% are greater. 𝜎 = = −6 7 𝑦> = =3
Σ𝑓 Σ𝑓 Σ𝑓 5
59.74 15 #
To find lower and upper quartiles for discrete data: 2 𝜎%# = − 6 7 = 2.948
Σ𝑓(𝑥 − 𝑥̅ )# Σ𝑓𝑥 # Σ𝑓𝑥 5 5
1. Divide 𝑛 by 4. (lower quartile) OR 𝜎=A =A −D E 𝜎% = √2.948 = 1.72 (3s.f.)
! Σ𝑓 Σ𝑓 Σ𝑓
Find " of 𝑛. (upper quartile)
2. If this is a whole number, the lower or upper quartile is the midpoint Where 𝑓 is the frequency of each group and Σ𝑓 is the total frequency c. Calculate the mean and variance of the original data using your
between this data point and the number above. If it is not, round up answers from part b.
and pick this number. !̅ "())
3= *)
so 𝑥̅ = 330℃
'!
1.72 = so 𝜎! = 17.2℃ (3s.f.)
*)

https://bit.ly/pmt-cc
https://bit.ly/pmt-edu https://bit.ly/pmt-cc