How to Make a Histogram on Mac & Windows

A histogram is the quickest way to see the shape of a single variable — where the values pile up, how spread out they are, and whether they're skewed. Here's how to make one on Mac & Windows.

A histogram (sometimes called a frequency distribution) buckets a numeric variable into ranges and draws a bar for how many values fall in each. It answers the first question you should ask of any measurement: what shape is it?

Make it in three clicks

Drag your CSV or Excel file onto Stratum.
Choose the Histogram chart and pick a numeric column.
Read the bars — tall where values cluster, short in the tails.

A histogram of a numeric variable in Stratum — Pick a numeric column; Stratum bins it automatically.

Choosing the bins

Bin width is the one real decision. Too few bins hides detail; too many turns the shape into noise. Stratum picks a sensible default and lets you switch between standard rules (Sturges, Freedman–Diaconis) or set the count yourself. When in doubt, try a couple and keep the one whose shape is stable.

Adjusting the bin-width rule on a histogram in Stratum — Switch bin rules or set the count by hand.

Reading the shape

Four shapes cover most data: bell-shaped (symmetric, normal-ish), right- or left-skewed (a long tail on one side — the signature of prices and incomes), bimodal (two peaks, often two hidden groups), and uniform (flat). Add a normal curve or a smooth KDE overlay to judge how close to normal it really is.

Histogram vs bar chart. A bar chart compares categories (with gaps between bars); a histogram shows the distribution of one numeric variable (bars touch, because the axis is continuous). If your x-axis is labels, you want a bar chart; if it's a number line, you want a histogram.

Export it

One click sends a clean PNG or PDF to your report. For the full walk-through — KDE bandwidth, group faceting, and overlays — see Lesson 5.

Download Stratum

Frequently asked questions

What's the difference between a histogram and a bar chart?

A histogram shows the distribution of one numeric variable — the bars touch because the axis is a continuous number line. A bar chart compares separate categories, with gaps between the bars.

How do I choose the number of bins for a histogram?

Start with an automatic rule (Sturges or Freedman–Diaconis) and adjust. Too few bins hides structure; too many adds noise. Pick the bin width whose overall shape stays stable as you nudge it.

When should you not use a histogram?

With very few data points (the shape is unreliable), or for categorical data — use a bar chart or Pareto for categories. Histograms also hide individual values, so pair with a box plot when outliers matter.

Is a histogram the same as a frequency distribution?

Effectively yes — a histogram is the graph of a frequency distribution (counts per value-range). Stratum builds it straight from your raw data.