Dotplot: See the Distribution of Every Data Point
What is a Dotplot?
A dotplot draws one dot for every observation, stacking dots with the same or similar values vertically, so the actual distribution of the data is visible. Compared with a histogram it keeps every raw data point and loses no binning information, making it ideal for small samples (n < 50) and for comparing several groups. Clusters, sparse regions and outliers stand out immediately, which makes it a fast data-exploration tool.
When to Use It
Use a dotplot when showing small samples, fewer than about 30 points per group, when comparing multiple groups such as shifts or batches side by side, or when supplementing a histogram with the raw data density. It is also effective for showing the full data picture to non-statistical audiences. Because no bin width needs to be set, the visual is free of parameter bias; as data volume grows, switch to a histogram or boxplot.
How to Use It (Step by Step)
Paste one or more columns of numeric data; the tool stacks the dots and supports group coloring and outlier labeling. Look at where the dots cluster (center), how far they spread (dispersion), the stack height (density) and isolated points (outliers). For grouped data, compare the centers and ranges across groups to judge whether they overlap, and investigate flagged outliers with an outlier test before acting.
Key Formulas / Example
A dotplot is graphical, not formula-driven: the height of the stack at any value is simply the count of observations at that value, and no binning parameter is involved. For example, with 20 measurements per group, the plot shows each point individually, and a point far from the main cluster is a candidate outlier to confirm with a formal outlier test. Quantitative conclusions still need statistics, so pair the plot with descriptive statistics for support.