What happens as we increase the number of classes in a histogram?

If you increase the number of classes in a histogram the columns become narrower, class intervals become rounder and central tendency becomes more obvious meaning the data becomes more accurate and any underlying information becomes more detailed as you are able to collect more data and the histogram becomes more informative.

A histogram is a basic quality tool. It is used to graphically summarize and display the distribution and variation of a process data set. The main purpose of a histogram is to clarify the data presented to make sure it is both accurate and correct.

Typical applications of histograms in root cause analysis include:

• Presenting data to determine which causes dominate

• Understanding the distribution of occurrences of different problems, causes, consequences, etc.

A histogram is a specialized type of bar chart, high bars can indicate more points in a class whereas low bars can indicate less points.

However there are weaknesses in analyzing data this way. These are:

• If too few or too many bars are present then the data can be misleading

• histograms can show many different pictures thus can be manipulated.

So, depending on the type of presented data you need to clarify a histogram may not be the most suitable method as sometimes it can tell a different story but sometimes it can only tell part of a story.