Averages & Spreads
PART 2: OTHER MEASURES OF DATA LOCATION
Alternatively, we can split data up into sections called percentiles or quartiles
Quartiles
Quartiles involve splitting data into equal segments of 25%
Calculating the interquartile range lets us see the spread of the middle half of the
data.
NOTE: if calculating quartiles using discrete data ensure the value is a whole
number. If not, round up
PART1: MEASURES OF DATA LOCATION (MEAN, MODE,
MEDIAN.)
Interpolation is used to
Mean= average calculate median,
Mode= value that occurs most often quartiles and percentiles
Median= middle value in grouped data.
When to use each value
Mean
- Uses for quantitive data (numerical values).
- Uses all pieces of data so is representative PART 3: MEASURES OF SPREAD
- Answer can be skewed by extreme data (Sometimes called measures of dispersion or measures of variation)
Measures of spread are used to calculate how widespread data
Mode
- Uses quantitive or qualitative data is. This includes interquartile range or the largest value take away
- Not very informative the smallest.
Interquartile range is a more accurate representation as it is not
a ected by extreme values, unlike normal range.
Median
- Used for quantity data Inter-percentile range is one percentile take away another (eg.
- Not a ected by extreme values 90th-10th still takes into account 80% of data)
PART 5: CODING
PART 4: OTHER MEASURES OF SPREAD
Coding is used to make statistical clues easier to work
Variance with. You are usually given a formula in the exam that
Another way to work out spread of data is a method called you have to re-arrange or sub in given values.
variance. Its is usually necessary to calculate the mean and
This involves realising that each data value is a number away standard deviation of the data rst.
The second equation (below) is for when using raw data.
Standard Deviation
Standard deviation is the
square root of the variance,
and variance is the square of
the standard deviation
This equation means the
variance is equal to the mean
of the squares minus the
square of the mean.
ff
ff fi
PART 2: OTHER MEASURES OF DATA LOCATION
Alternatively, we can split data up into sections called percentiles or quartiles
Quartiles
Quartiles involve splitting data into equal segments of 25%
Calculating the interquartile range lets us see the spread of the middle half of the
data.
NOTE: if calculating quartiles using discrete data ensure the value is a whole
number. If not, round up
PART1: MEASURES OF DATA LOCATION (MEAN, MODE,
MEDIAN.)
Interpolation is used to
Mean= average calculate median,
Mode= value that occurs most often quartiles and percentiles
Median= middle value in grouped data.
When to use each value
Mean
- Uses for quantitive data (numerical values).
- Uses all pieces of data so is representative PART 3: MEASURES OF SPREAD
- Answer can be skewed by extreme data (Sometimes called measures of dispersion or measures of variation)
Measures of spread are used to calculate how widespread data
Mode
- Uses quantitive or qualitative data is. This includes interquartile range or the largest value take away
- Not very informative the smallest.
Interquartile range is a more accurate representation as it is not
a ected by extreme values, unlike normal range.
Median
- Used for quantity data Inter-percentile range is one percentile take away another (eg.
- Not a ected by extreme values 90th-10th still takes into account 80% of data)
PART 5: CODING
PART 4: OTHER MEASURES OF SPREAD
Coding is used to make statistical clues easier to work
Variance with. You are usually given a formula in the exam that
Another way to work out spread of data is a method called you have to re-arrange or sub in given values.
variance. Its is usually necessary to calculate the mean and
This involves realising that each data value is a number away standard deviation of the data rst.
The second equation (below) is for when using raw data.
Standard Deviation
Standard deviation is the
square root of the variance,
and variance is the square of
the standard deviation
This equation means the
variance is equal to the mean
of the squares minus the
square of the mean.
ff
ff fi
