Histogram Maker
Paste numbers to draw a histogram with automatic or custom bins, mean and median lines and summary statistics, then download it as PNG.
- ✓Sturges, square-root or custom bins
- ✓Frequency or relative-frequency axis
- ✓Mean and median reference lines

Your histogram will appear here
Paste data on the left and click Generate
Create a Histogram Online: Examples and Interpretation
Use the free histogram generator above to graph numerical data. This guide explains how to choose bins, view a frequency histogram, interpret its shape, and export your chart.
What Is a Histogram?
A histogram shows how numerical observations are distributed. It divides a number line into intervals called bins and displays how many observations fall in each interval. The horizontal axis represents value ranges; the vertical axis shows either a count (frequency) or a share of the data (relative frequency).
For example, a histogram of exam scores can show whether most students scored in the middle, whether scores are spread widely, and whether unusually high or low ranges deserve a closer look. Unlike a categorical bar chart, the intervals have a numerical order and their bars are normally adjacent.
This free online histogram maker is designed for one straightforward task: paste a list of numeric values, create a histogram, inspect its shape and summary statistics, then save the resulting chart as a PNG image. Your pasted values are processed in browser JavaScript for this free tool.
Key Takeaways
Histograms group numerical values into ordered intervals called bins.
Bin choices can change the appearance of a distribution. Try several sensible settings.
Choose frequency to see counts or relative frequency to see percentages.
Interpret shape, spread, and center without assuming the chart proves normality.
How to Make a Histogram Online
To create a histogram graph, you only need a set of numerical values. This browser-based histogram creator groups the numbers into bins and draws the frequency bars automatically. The tool is located above this guide.
- Paste your numerical data into the Your data box. Separate observations with commas or line breaks. For example:
12, 15, 18, 18, 21, 24. - Choose a bin method. Leave Auto (Sturges) selected for a starting point, choose √n for the square-root rule, or choose Custom to enter a bin count.
- Choose the y-axis. Select Frequency (count) or Relative frequency (%).
- Customize the display if helpful: choose a bar color, enter an optional chart title, and show or hide the mean and median reference lines.
- Click Generate Histogram. The chart and summary statistics appear to the right of the controls, or below them on a narrow screen.
- Read the chart. Look at the center, spread, possible skew, peaks, gaps, and whether your chosen bins make the pattern easy to understand.
- Try another reasonable bin count when the shape looks overly smooth or fragmented. The numbers remain the same; only their grouping changes.
- Click Download PNG when the chart is ready for a report, presentation, or classroom assignment.
1200, not a thousands-formatted number such as 1,200, because a comma separates observations. Double-check the displayed Count: the current parser may omit nonnumeric text or interpret a partially numeric entry unexpectedly.How Histogram Bins Work
Each bin covers a range of values. For example, bins might cover 0 to under 10, 10 to under 20, and 20 to 30. The height of each bar then tells you how many values fall in that interval. On this tool, bins have equal widths. The lower endpoint belongs to its bin; the upper endpoint belongs to the next bin, except that the largest observed value is included in the final bin.
Bin selection matters. Too few bins can hide real features in the data, while too many can make ordinary random variation look important. There is no universally best number of histogram bins for every dataset. Automatic formulas are useful starting points, not proofs that a particular grouping is optimal.
Auto (Sturges' Rule)
Sturges' rule estimates the number of bins as k = ⌈1 + log₂(n)⌉, where n is the number of observations, k is the bin count, and the brackets mean round up. With 18 observations, for instance, the formula returns six bins. This is a common, simple heuristic; its suitability depends on the data and what you want to examine.
k = number of bins · n = number of observations
Square-Root Rule (√n)
The square-root rule uses k = ⌈√n⌉. It offers another quick starting point based on sample size. Neither the square-root rule nor Sturges' rule is automatically superior for all distributions.
A convenient alternative starting point for bin selection.
Custom Number of Bins
Select Custom when you want to try a specific whole-number bin count. The input provides a range from 2 to 200, and the chart does not use more bins than observations. Try a few sensible counts instead of selecting the one that makes a preferred narrative look strongest.
This tool adjusts the number of equal-width bins. It does not currently offer independent controls for exact bin edges, bin width, or a custom x-axis range. For a single repeated value, there is effectively no spread to interpret, so a histogram will be less informative than reporting that value directly.
Frequency Histogram vs Relative Frequency Histogram
Frequency is the number of observations in a bin. If five data points are between two boundaries, that bar has a frequency of five. This is usually the most immediate way to read a histogram.
Relative frequency tells you the proportion of all observations in a bin. The formula is fi / n, where fi is the bin count and n is the total count. Multiply by 100 to express the result as a percentage. A bin with five out of twenty observations represents 25% of the dataset.
Switching between these two options changes the vertical scale, not the underlying observations or the bin boundaries. Relative frequency can make proportions easier to understand, particularly when comparing datasets with different sample sizes. The free tool shows relative frequency as a percentage, not as probability density.
Histogram Example: Make a Chart From Numbers
Suppose you have 18 observations from a small measurement exercise. Copy these values into the histogram input above:
55, 61, 62, 64, 67, 68, 69, 71, 72, 73, 74, 76, 77, 79, 82, 85, 88, 92Choose Auto (Sturges) and Frequency (count), then generate the chart. Sturges' rule yields six equal-width bins for 18 values. The underlying values and the calculated summary statistics are:
- Count: 18 observations; minimum: 55; maximum: 92.
- Mean: approximately 73.06; median: 72.5.
- Population standard deviation: approximately 9.50. This page's current Std Dev calculation divides the sum of squared deviations by n, not n − 1.
With equal-width bins across the range from 55 to 92, the frequencies are:
| Value interval (approx.) | Frequency | Relative frequency |
|---|---|---|
| 55 to under 61.17 | 2 | 11.1% |
| 61.17 to under 67.33 | 3 | 16.7% |
| 67.33 to under 73.50 | 5 | 27.8% |
| 73.50 to under 79.67 | 4 | 22.2% |
| 79.67 to under 85.83 | 2 | 11.1% |
| 85.83 through 92 | 2 | 11.1% |
| Total | 18 | 100% (before rounding) |
The intervals in this example are displayed with rounded boundaries; bin assignment uses unrounded boundaries. The middle bins contain more observations than the edge bins, and the most populated bin contains five values. This is a useful visual description of this small sample, not evidence that the source population follows a particular distribution.
These figures describe the example above; they are not a preloaded result in the tool. The actual histogram and statistics are calculated when you paste the numbers and click Generate Histogram.
How to Read a Histogram Graph
A histogram is an exploratory view of a numerical distribution. Read the x-axis ranges first, then examine the heights of the bars. The main questions are where values cluster, how widely they spread, and whether the shape is balanced or asymmetric.
- Center and spread: Identify the range where observations concentrate and the distance from the smallest to the largest values. The mean and median lines can help locate typical values, but they do not capture the whole shape.
- Rough symmetry: Similar patterns on both sides of the center may indicate a fairly balanced distribution. Mean and median may be close, but that alone does not establish symmetry.
- Right skew: A longer tail extends toward higher values, even if most observations cluster toward the lower end.
- Left skew: A longer tail extends toward lower values, even if most observations cluster toward the higher end.
- Peaks: One clear peak is called unimodal; two apparent peaks may suggest bimodality. Several peaks can reflect distinct groups, binning effects, or chance rather than proving separate populations.
- Gaps and extreme regions: Empty or sparse bins can be worth investigating, but an isolated bar alone does not prove that a data point is an outlier.
- Uniformity: Bars of fairly similar height may suggest a roughly uniform pattern over the observed range.
Histogram Shapes: Symmetric, Skewed, Bell-Shaped and Uniform
The shape of a histogram describes how values are distributed across bins. A right-skewed histogram has a longer tail toward higher values, while a left-skewed histogram has a longer tail toward lower values. The side of the tail—not the tallest bar—determines the direction of skew.
A symmetric histogram is roughly balanced around the center. A bell-shaped histogram has a prominent central peak with frequencies tapering toward both ends; this appearance alone does not prove a normal distribution. A uniform histogram has bars of broadly similar heights, and a bimodal histogram has two apparent peaks.
To inspect these patterns, create a histogram using your own data and compare a few reasonable bin counts. Changes in bin boundaries can make peaks or skewness look more or less pronounced.
Histogram vs Bar Chart: What's the Difference?
Both displays use bars, but they answer different questions. Use a histogram for the distribution of numerical measurements; use a categorical bar chart for comparisons across named groups such as product types or regions.
| Feature | Histogram | Bar chart |
|---|---|---|
| Data | Numerical observations | Usually categories |
| Horizontal axis | Ordered numeric intervals | Category labels |
| Bar meaning | Observations within an interval | Count or value for a category |
| Bar order | Fixed by numeric scale | Can often be rearranged |
| Spacing | Bins normally touch | Bars are often separated |
For example, a histogram can describe customer order values, whereas a bar chart can compare orders by product category. Treating categories as if they were continuous numeric intervals can lead to a misleading chart.
Histogram vs Box Plot
Both charts help you explore numerical data, but they highlight different characteristics. A histogram makes the distribution's shape visible: peaks, gaps, skew, and how frequently values occur in different ranges. A box plot summarizes the median, quartiles, interquartile range (IQR), and potential outliers using a more compact display.
Choose the histogram when the pattern across value ranges is your main question. Choose a box plot when you want a compact summary or need to compare numerical distributions across groups. If quartiles and outliers matter, try the Box Plot Maker alongside this histogram generator.
When Is a Histogram Useful?
A histogram can be helpful in a statistics classroom to examine test scores, in research to explore measurements, in business to look at delivery times or order values, and in data analysis to check spread before choosing a model. It is a quick starting point for understanding what the data look like, not a substitute for causal analysis or formal statistical testing.
Education
See how exam scores are distributed across intervals.
Research
Explore numerical measurements before choosing an analysis.
Operations
Examine delivery times and measurement variability.
Business
Understand how order values or wait times spread out.
When sharing the downloaded PNG, give readers the measurement units, sample size, population or dataset context, and any important binning decisions. If the chart suggests a surprising pattern, compare reasonable bin choices and inspect the original measurements before drawing conclusions.
Common Histogram Mistakes to Avoid
- Using categories as numbers: A histogram is for quantitative observations, not categories such as departments or brands.
- Choosing too few or too many bins: Either extreme can obscure a useful picture of the distribution.
- Treating automatic bins as the only correct answer: Sturges and square-root rules are practical defaults, not guaranteed best choices.
- Confusing count and percentage: Frequency is a count; relative frequency is a share of all observations.
- Comparing unequal sample sizes without checking the scale: Percentage views may communicate differences more fairly than raw counts.
- Declaring normality or outliers from appearance alone: A histogram suggests patterns but does not establish a formal statistical conclusion.
- Ignoring bin boundaries: Values near a boundary can move between neighboring bars when the bins change.
- Omitting chart context: A PNG without a meaningful title, units, or sample description can mislead readers.
For other one-task utilities, explore all free data tools. For a more extensive analysis involving multiple charts and columns, see AmriData's data visualization and data analysis features. These are separate from the free paste-and-generate tool.
Statistical reading: See the NIST/SEMATECH histogram reference for fundamentals of histogram construction and interpretation, and Penn State STAT 200 for distribution shapes and skewness.
Use it for a focused statistical question.
The free tool is intentionally narrow. It is fastest when you already have numeric values and want one clear distribution view without building a full dataset workspace.
Histogram Maker questions
How the free browser tool behaves.
Does the Histogram Maker upload my numbers?+
No. The values you paste are processed in your browser. The signed-in dataset workspace is a separate workflow for uploaded files.
Which bin method should I use?+
Sturges is a reasonable starting point for smaller datasets and the square-root rule is another quick option. Choose Custom when specific breakpoints matter in your field.
Can I download the histogram?+
Yes. After you generate the chart you can download it as a PNG image.