Over the while I've acquired a set of heuristics on how to effectively plot the association between two numeric variables. I imagine most people who work with data would have a similar set of rules.
Examples of such rules might be:
- If one of the variables is positively skewed, consider plotting that axis on a log scale.
- If there are a lot of data points (e.g., n > 1000), adopt a different strategy such as using some form of partial transparency, or sampling the data;
- If one of the variables takes on a limited number of discrete categories, consider using a jitter or a sunflower plot;
- If there are three or more variables, consider using a scatterplot matrix;
- Fitting some form of trend line is often useful;
- Adjust the size of the plotting character to the sample size (for bigger n, use a smaller plotting character);
- and so on.
I'd like to be able to refer students to a web page or site that explains these and other tricks for effectively plotting associations between two numeric variables, perhaps with examples.
- Are there any pages or sites on the internet that do a good job of this?