Descriptive statistics Flashcards
Mean
Arithmetic average
Median
Central score in a list of rank ordered scores
Mode
Most common or frequently occurring score
Mean strength
Unlike the median, which only represents the middle value, a strength of the mean is the most sensitive measure of central tendency
As it is the only measure which is representative of all the scores in the data set
Mean limitation 1
The mean can give peculiar outcomes that don’t represent reality (e.g. 2.6 children)
Mean limitation 2
Unlike the median, which only represents the middle value, a limitation of the mean is that it is easily distorted by extreme scores
Making it unrepresentative of the majority of the scores in the data set
In such case, the median may be more representative of the data set
Median strength
Unlike the mean, which is representative of all the scores in the data set
A strength is that it is not distorted by extreme scores, making it less likely to be biased
Median limitation
Unlike the mean, which is representative of all the scores in the data set
Limitation is that it is less sensitive as it only represents the middle of the data set
Mode strength
Unlike the mean, which is representative of all the scores in the data set,
a strength is that it is not distorted by extreme scores making it less likely to be biased
Mode limitation 1
Unlike the mean, which is representative of all the scores in the data set,
a limit is that it is less sensitive than the mean as it only represents the most frequently occurring score
Mode limitation 2
The mode may not appropriate for small data sets in which each score only appears once, as no score appears more than any other
Range
Simplest measure of dispersion, which shows the spread of the scores in any data set by subtracting the smallest score from the largest
Larger range suggests more dispersion amongst the scores, as they are widely spread
Smaller range suggests less dispersion amongst the scores, as they are closely spread
Standard deviation
More precise measures of dispersion, which shows the spread of the scores in any data set by calculating their average distance from the mean
Larger SD suggests more dispersion amongst the scores, as they are widely spread
Smaller SD suggests less dispersion amongst scores, as they are closely spread
Range strength
Very easy to calculate (by simply subtracting the smallest from the largest score in any data set)
Range limit 1
Less sensitive than the SD as it doesn’t use al the scores in its calculation of the dispersion
Range limit 2
Easily distorted by extreme scores making it unrepresentative of the majority of scores in the data set
SD strength
Most precise measure of dispersion as it is the only one to use all of the scores in the data set by measuring their average distance from the mean
SD limit
More difficult to calculate than the range,
Bar chart to contain
Title: including IV & DV & type of graph drawn
Clearly labelled Y axis
Scale showing the maximum possible value
Accurately presented data
Clearly labelled x axis
Calculating a percentage
Divide given score by the total possible score
Multiply by 100
Fraction to percentage
Divide top number by bottom number
Multiply by 100
Ratios
Find the lowest possible number that both numbers are divisible by
Write these numbers with a colon between them
Measures of central tendency
Mean, mode, median
Measures of dispersion
Range, standard deviation
Discuss a possible implication
What could happen
Give ideas of what the findings could mean for wider society
e.g. are people more likely to want to do something, will the results affect one group of people over others, will there be any positive or negative financial implications for people or the gov
Use number of marks available as an indicator of how many implications you should give and how much detail to add
Discuss a possible application
What you should do
Give ideas of what the findings should mean for how society could be changed
E.g. should people be encouraged to do something by the gov, business or in the work place, could the results be used to affect one group of people over others
Use the number of marks available as an indicator of how many applications you should give and how much detail to add
Bar chart
Present non-continuous data, which falls into categories
Frequency of event is plotted on the y axis
Use to show test of difference
Columns don’t touch as each show a separate condition
Scattergram
Use to show test of correlation
Data points not connected
Trend illustrated by line of best fit
Histogram
Present continuous data, which is measured on a continuous scale (e.g. time; age; distance; height; etc..) along x axis
Frequency of event shown on y axis
Columns touch each other as each shows an interval along a continuous scale
Frequency polygon
Present continuous data, measured on a continuous scale
Used to show a test of difference when more than 1 set of data needs to be presented
