# Representation of Data

• Created by: eleanor
• Created on: 11-04-15 12:06
• Representation of Data
• Stem and Leaf
• They still have all details of the data
• They allow direct comparisons of two sets of data
• They give a sense of location and spread
• Key Points
• Always put values in order from the centre
• Make sure values in leaf are always one digit
• Spilt data up to ensure you show a shape
• Always include titles and a key
• How To Read From Stem And Leaf
• Mode = Most Comman
• Range= biggest - smallest
• Median = number of values / 2
• Interquartile Range = Q3-Q1
• Lower Quartile = Number of values /4
• Box Plots
• Shows location and spread at a glance
• Always use clear labels for each box plot and scale
• Outliers
• Are generally found using 1.5 x IQR
• Then subtract from LQ if anything is below this then it is an outlier
• Add to UQ if anything is above this it is an outlier
• Histograms
• Key Points
• Histograms are used for continious data
• If a table does not show continuous data you must alter the class boundaries
• Frequencey Density = (frequency /class width)
• The area of the bar is proportional to the frequency
• The modal group is the group with the largest area
• to calculate the height of each bar use the formula  k x frequency
• Skewness
• box plots positive: Q2-Q1 < Q3 -Q2
• Negative: Q2-Q1 > Q3 -Q2
• Symmetrical: Q2-Q1 = Q3 -Q2
• histograms 3(mean-median)/ standard deviation
• Positive: mode< median< mean
• Negative:  mode> median> mean