Data processing, presentation and interpretation Flashcards
Outlier formulae
- Greater than Q3+1.5(Q3-Q1)
- Less than Q1-1.5(Q3-Q1)
Ways of representing data
Box plots, cumulative frequency graphs, histograms
Mean of values from frequency tables
mean= (total of (xf))/n
x= value of variable
xf= value of variable x frequency
n= number of data items (total frequency)
Advantages and disadvantages of grouped data
+ Easier to display data
- Information is lost in the form of individual values, and therefore any measures calculated are only estimates
Displaying continuous grouped data
Frequency charts, histograms
Frequency charts
Used to display data that are grouped into classes of equal width
Histograms
frequency density= frequency/class width
frequency density represented by y axis of histogram
frequency= area of bar
Working out mean from grouped continuous data
mean= total of (mid-value x frequency)/total frequency
What is the moral class in grouped continuous data
The highest bar of the histogram (highest frequency density)
Cumulative frequency curves
- Plot upper bound of each class interval against cumulative frequency, then join points with smooth curve
Bivariate data
Investigating the relationship between two variables
Displaying bivariate data
Scatter graphs can be plotted and then correlation (strong/weak positive/negative) can be identified
Measures of spread of data
-Range
-IQR
-Standard deviation
Standard deviation formula
Standard deviation= square root of (sum of (x- mean)^2)/n