DJM Topic 5 - Visualizing Correlation Flashcards
Correlation
A statistical measure that describes the relationship between two quantitative variables
Positive correlation
When one variable increases, the other variable tends to increase as well
Negative correlation
When one variable increases, the other variable tends to decrease
Linear correlation
A straight-line relationship between two variables
Curvilinear correlation
A curved relationship between two variables
Linear correlation coefficient (r)
A value ranging from -1 to 1 that describes the strength and direction of a linear correlation
Coefficient of determination (r^2)
A value ranging from 0 to 1 that describes the strength of a correlation, but not the direction
Scatterplot
A graphical display used to visualize the relationship between two quantitative variables
Scatterplot matrix
A display showing multiple scatterplots to compare multiple pairs of variables
Table lens
A display that allows for detecting possible correlations among many variables at once
Aspect ratio
The recommended shape for a scatterplot is roughly square
Reference regions
Visual aids that help compare data to a reference set of values
Trend line
A line that traces the basic shape of the data and can be used for prediction
Line of best fit
The trend line with the least amount of residuals, often chosen based on the highest r^2 value
Multiple trend lines
Used to visualize categorical differences in the data
