Statistics Definitions > What is a bin (or Class Interval) in statistics?

## What is a Bin in statistics? Overview

In statistics, data is usually sorted in one way or another. You might sort the data into classes, categories, by range or placement on the number line. A **bin** — sometimes called a class interval — is a way of sorting data in a histogram. It’s very similar to the idea of putting data into categories.

## What is a bin in statistics: Why not use “Categories” instead of Class Intervals?

When you put data into categories, you’re putting them into those categories without any thoughts about how that data might tell you something. Basic sorting into categories like male/female or yes/no does exist in statistics, but when it comes to making a histogram you’re aiming to make a chart that tells you some very good information about how your data is spread out. Therefore you want to **carefully choose categories/classes.** You can think of a **bin** as being a physical bin where you might sort objects into.

Imagine you’re working in a clothing store and want to know which shoe items is most popular in your inventory. If you only fill one bin, your bin might end up overflowing pretty fast and you’d have no information. You could try using different bins for flats, heels, sneakers and sandals. That might give you a better idea about your inventory. Or you could further add bins for black heels, white heels and so on. It’s the same principle when choosing bins for a histogram; you want to choose the right amount of bins to give you the information you need.

## What is a bin in statistics: Choosing bins

**Choosing bins** can be done by hand for simple histograms in most cases. For example, if you are making a histogram for exam scores, choosing bins that matches grades (70-79, 80-89, 90-100) is a fairly obvious choice. You have two numbers associated with each bin: the low value (sometimes called *bin low*), which in this example would be 70, 80, 90 and the high value (sometimes called *bin high*) which for this example is 79 89 100.

In most cases though, choosing bins isn’t going to be that simple especially for large data sets. When dealing with large sets of numbers, you’re usually better off using technology like Microsoft Excel to create a histogram (how to create a histogram in excel 2007), because if your bin choice doesn’t make for a nice-looking diagram you can dynamically change the bin values without having to draw a graph.

That said, if you want to choose bin sizes by hand, watch this video or click the link below for the full article:

Next: How to choose bin sizes in statistics

------------------------------------------------------------------------------If you prefer an online interactive environment to learn R and statistics, this *free R Tutorial by Datacamp* is a great way to get started. If you're are somewhat comfortable with R and are interested in going deeper into Statistics, try *this Statistics with R track*.

*Facebook page*and I'll do my best to help!

Do you find bins only for Qualitative data?

Not, you could find bins for quantitative too. For example, heights or weights could be separated into bins.

But in Excel using the Analytic Pack add-in it when doing a Histogram is the Bin that it generates the upper bound, middle, or lower bound of the space?

William,

It’s the upper bound,

Stephanie

you can interpret bin as the size or width of the category. Then you can put your stuff or data in this bin, if the bin size is large, it can accommodate more data in this bin, it the bin size is too large, we may lose the peak values. e.g. we have one bin for all the data.

if it is small, we get more details about the data, but more computation effort.

Nice interpretation, Lisa :)

Please give me the definitons of the “bin high“ and the “bin low“

You have two numbers associated with each bin: the low value (sometimes called

bin low), and the high value (sometimes calledbin high). I added an example to the article, hope it helps clarify this.