Paste a column of data and get an instant histogram with mean, median, standard deviation, an optional normal curve, and quick Cp/Cpk against your spec limits — all client-side.
Paste your data and press Calculate to build the histogram and descriptive statistics.
Watch: Why Your Average Is Hiding the Problem: Histograms Explained
You have 50 fill-weight readings and want to see the shape of the process — is it centred, spread out, skewed? Enter the lab to turn the numbers into a picture.
Enter a single column of measurements — fill weights, cycle times, dimensions, anything numeric. The calculator parses one value per line (commas and tabs also work) and ignores blanks.
Your values are grouped into equal-sized buckets. The calculator picks a sensible number of buckets automatically based on how much data you have, but you can adjust it to see how the picture changes.
You get the count of values, plus the average, middle value, spread, low and high. You can overlay a normal (bell) curve to see if the data is symmetric, and enter spec limits to see LSL/USL lines plus quick Cpk scores.
A histogram is the fastest way to understand a set of measurements. It groups your data into bins and shows the shape, centre and spread at a glance — revealing skew, outliers and whether the process can meet its specification.
A histogram is a bar chart of a single continuous variable. The range of the data is split into equal-width intervals (bins), and the height of each bar shows how many values fall into that interval. Because the bars touch and the axis is numeric, a histogram reveals the distribution's shape — symmetric, skewed, bimodal — together with its centre and spread.
The calculator sorts your values into equal-width bins and counts how many fall in each — those counts are the bar heights that reveal the distribution's shape. It also reports the usual summary numbers: the average, the standard deviation (a measure of spread), and the median, minimum and maximum. If you enter spec limits, it adds the capability indices Cp and Cpk, which compare your process spread against the spec width. Higher is better, and a value of 1.33 or more is a common target.
A service team records 50 call durations. Most run 4–7 minutes, but a handful stretch to 12–15 minutes. The histogram shows a right-skewed shape — a long tail of complex calls pulling the average up.
The average is 6.2 minutes but the median is 5.1 minutes. Reporting the average makes performance look worse than it is for the majority of customers.
What to do with this: Treat long-tail calls as a separate process — they likely need a specialist queue. Improving the main process won't fix the 10% that are genuinely complex.
A histogram is usually the first picture you draw of any dataset. It tells you instantly whether a process is centred on target, how much it varies, and whether the shape is normal — all of which drive decisions about capability, control charts and the right statistical test to use next.
Use a histogram in the Measure and Analyse phases of DMAIC to characterise a baseline, spot outliers, and check the normality assumption before running capability studies or hypothesis tests. With spec limits added it becomes a quick capability snapshot before a formal Cp/Cpk study.
Histograms are one of the seven basic quality tools. They underpin process capability analysis, support root-cause investigations (a bimodal shape often points to two machines or shifts), and provide the visual evidence that turns raw data into a clear improvement story for your tollgate review.
If the shape is symmetric and roughly normal, confirm it with a normality test, then run a full capability study against your specification. If it is skewed or bimodal, investigate the cause — different shifts, machines or materials — before computing capability, and consider a nonnormal capability method. Either way, monitor the process over time with a run chart or control chart so you know the distribution is stable, not just a snapshot.
Pair the histogram with normality testing, regression and a DMAIC project structure to turn a picture of your data into action.
A paired t-test is used when the same items (machines, patients, stations) are measured twice — before and after, or under two conditions. Because each pair shares variability, the test eliminates that source of noise and is more powerful than a 2-sample test. A 2-sample (independent) t-test is used when the two groups are completely separate, with no natural pairing between observations.
Data is paired when there is a natural one-to-one correspondence between each before and after value — the same machine, the same patient, the same workstation. Examples: cycle time on 10 machines before and after a process change; blood pressure in 20 patients before and after treatment; inspection times for the same parts under two methods. If the items in the two groups are different, use a 2-sample t-test.
The paired t-test assumes: (1) observations are independent of each other (one pair does not influence another); (2) the differences (after minus before) are approximately normally distributed — for small samples use a normality test; (3) there are no extreme outliers in the differences. Violations of normality with small samples suggest using a nonparametric alternative such as the Wilcoxon signed-rank test.
The minimum recommended is about 10–15 pairs, though the test works with fewer if the differences are normally distributed. The required sample size depends on the expected mean difference, the standard deviation of differences, and the desired power (typically 80%). For a kaizen study where you expect a 10% improvement with moderate variability, 20–30 pairs typically gives adequate power. Use a sample size calculator to plan your study.
A histogram shows you the shape of your data. Structured training shows you how to act on it — capability, control and root-cause analysis.
More calculators for statistics, quality, and improvement.
Want to know how to use histograms to understand process variation? The Yellow Belt covers histograms, basic statistics, and the core data analysis toolkit.
View Black Belt →