Bivariate data and scatter graphs
Plot pairs of data, name the kind of data, describe the correlation, drag a line of best fit, predict from it and tell correlation from cause and effect.
- UK: Year 9
- France: grade 11
- Iran: grade 10
- Afghanistan: grade 11
- Syria: grade 7
- Palestine: grade 10
- Russia: grade 8
Guide
Bivariate data comes in pairs: for each student, the hours of practice and the test score. A scatter graph plots each pair as one point, (hours, score). Both variables must be numbers to go on the axes. Do not join the points up: they are separate people, not a journey.
Look at the cloud of points. If it rises from left to right, the graph shows positive correlation; if it falls, negative correlation; if there is no pattern, no correlation. The closer the points are to a straight line, the stronger the correlation.
A line of best fit goes through the middle of the cloud, with about as many points above it as below. It does not have to go through (0, 0), or through the first and last points. Use it to predict inside the range of the data. Far outside the range, a prediction can be nonsense.
Correlation does not prove causation (cause and effect). Two things can rise together because a third thing (such as hot weather) pushes both.