Marginal Plot: See Variable Relationships and Distributions Together
What is a Marginal Plot?
A marginal plot adds histograms (or boxplots or density curves) of X and Y along the top and right edges of a scatter plot, showing the relationship between two variables and each variable's distribution in a single view. It fills the gap of a plain scatter plot, which cannot show the univariate distributions, and is a high-information-density chart for the exploration stage. The relationship and the distributions complement each other.
When to Use It
Use it while exploring the relationship between two variables while also checking their distribution shapes, examining whether skewness or outliers affect a correlation analysis, and during initial exploration of multivariate data. It lets you check correlation and distribution in one pass, exposing data problems that would distort the correlation before you rely on it.
How to Use It (Step by Step)
Paste two columns of data, choose the margin type (histogram or boxplot), and the tool draws the scatter with marginal distributions and supports AI interpretation. Look at the marginal histograms for skew, multiple modes and outliers, then interpret the central scatter accordingly. Switch the margin type to highlight outliers or distribution shape as needed.
Key Formulas / Example
There is no formula; the chart is the deliverable. Example: with X = temperature and Y = strength, the marginal histograms may reveal a bimodal X distribution that explains two clusters in the scatter. Remember that the marginal plot is exploratory: correlation significance still requires the correlation coefficient, and outliers should be handled before analysis.