Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
BIVARIATE STATS
MCO552
Data in Business Journalism
Prof. Steve Doig
Two kinds of relationships
• Deterministic: You can
predict one variable exactly
given another
• Statistical: You can describe
a relationship between
variables, but it isn’t precise
because of natural variability
Scatterplot
Strength of Relationship?
Correlation (also called the
correlation coefficient or
Pearson’s r) is the measure of
strength of the linear
relationship between two
variables.
r = +.1 r = +.4
r = +.8 r = +1
Negative Correlations
r = -.4
r = -.1
r = -.8 r = -1
Zero correlation
r=0 r=0
Zero correlation
Number of Points Don’t Matter
r = .8 r = .8
Important!
Correlation
does not imply
causation.
Spurious correlations
Some reasons for correlation
• One variable is causing
change in the other
• Explanatory variable is a
contributing – but not sole --
cause of change
• Confounding (lurking)
variables may exist
• Both variables affected by a
common cause
• Both are changing over time
• Pure coincidence
END OF UNIT 11 VIDEO