MerQuR+Statistics Glossary

Statistics Glossary → Histogram and bin count

Histogram and bin countconcept

A chart that splits the range of a numerical variable into equal-width intervals (bins) and shows the number of observations in each as bars.

A histogram shows the shape of a distribution at a glance: symmetry or skewness, one peak or several, outliers and gaps. Bar height shows frequency (or density) and bar width shows the interval; unlike a bar chart, the horizontal axis is continuous and the bars touch.

The picture is very sensitive to the number of bins: too few hide detail, too many give a noisy, jagged look. Sturges' rule k = ⌈log2 n + 1⌉ is a common starting point but suggests too few bins for large or skewed samples; the Freedman-Diaconis and Scott rules choose the bin width from the spread of the data. To judge normality, a histogram should be read together with a Q-Q plot.

An everyday example

A café records customers' waiting times for a month. The times are grouped into intervals such as 0-2, 2-4 and 4-6 minutes, and the number of customers in each is drawn as a bar. The chart shows that most customers wait 2-4 minutes, but a thin tail to the right includes people who waited up to 15 minutes.

In MerQur

In Descriptive Statistics, 'Bin count' (1-100; 1 = Automatic, Sturges' rule) sets the number of bins in the Histogram and Frequency tab. The 'Chart' option of the paired t-test offers a difference histogram with a normal curve; histograms also appear in the normality tests and multiple linear regression.

Analyses where this concept appears

Descriptive StatisticsNormality TestsPaired t-TestMultiple Linear Regression

Related concepts

Box plotQ-Q and P-P plots