A scatter diagram is a graphical tool that shows whether or not there is a correlation between two variables.
Use: When using a scatter diagram there are two types of variables – a dependent variable and an independent variable. The independent variable is usually a plotted along the horizontal axis. The dependent variable is usually plotted along the vertical axis. If no dependent variable exists, either type of variable can be plotted on either axis. If the clustering of intersecting dots in the paired comparisons shows a pattern that extends from lower-left to upper-right, the scatter diagram shows evidence of a positive correlation. If the pattern of dots tends to go from the upper-left to the bottom-right, there is evidence of a negative correlation. Two things to remember:
- Correlation does not mean causation. There might be a correlation suggesting that ice cream sales causes more shark attacks, but clearly there is a third variable – the weather outside means that when the weather is warmer, more people tend to eat ice cream and more people tend to go swimming.
- The second thing to remember is that a negative correlation does not mean a bad thing. It simply means that as the vertical axis decreases, the horizontal axis increases. That’s all it means. Sometimes people think that a negative correlation is bad. It has nothing to do with good or bad. It has everything to do with whether or not there is a positive or negative correlation. Also know that if there is no pattern of evidence of a trend in either direction, there is evidence of no correlation, which is good to know as well.
