representation of data Flashcards
median ( odd)
median (even)
why is mean not suitable
because there’s an extreme value () which can affect the final average
why is mode not suitable?
mode is not suitable as it will be the lowest/highest value () which can affect the interpretation of data
LQ
1/4 *n
UQ
3/4*n
IQR
Q3-Q1
2 comparisons
On Average (median/mean/mode) , compare using higher than, greater than, more than or less than
Range/IQR- more spread, less spread
always label stem and leaf
in diagrams and write key
standard deviation
always 3sf
mean for ungrouped
the standard deviation for ungrouped
mean for grouped
the standard deviation for grouped
variation is
sd^2
outliers
Q1-(1.5* IQR)
Q3+(1.5* IQR)
the numbers more than or less than these are the outliers
explain why the mean is only an estimate
- mean can only be an estimate because we do not know the individual measurement of _. all the data has been grouped so we can only roughly estimate the mean for the grouped data.
advantages of the cumulative frequency graph
- suitable for continuous data
- median, lower quartile, and upper quartile can be estimated from the graph
- sets of data can be compared by drawing graphs on the same diagram
disadvantages of the cumulative frequency graph
it doesn’t show each data drawn from a grouped frequency table. the visual impact can be altered by choosing different groups
advantages of histogram
suitable for continuous data
shows whether the distribution is symmetrical or skewed
disadvantages of histogram
it dosent show each data as it is constructed from a grouped frequency table.
the visual impact can be altered by choosing different groups
two distributions cannot be shown on the same diagrams
advantages of stem and leaf
- shows all the original data
- median, mode and quartiles can be found from the diagram
disadvantages of stem and leaf diagrams
not suitable for a large set of data
advantages of box and whisker plot
- easy to see whether the distribution is symmetrical or skewed
- median. lower quartile and upper quartile can be seen from the graph
- sets of data can be compared by drawing box and whisker plots on the same diagram
disadvantages of box and whisker plots
it doesn’t show each data
negatively skewed
positively skewed
positively skewed
negatively skewed
in histogram the y axis is
f.d
f.d=
f/c.w
what assumption needs to be made for the estimate to become accurate
data is evely distrbuted within each class
