Tool description courtesy of Processfix Limited 2008

---

 

 

 

D

 

M 

 

A I

C

 

Tool description courtesy of  © Processfix Limited 2008  

 

 

 

Histogram 

 

Description 

 

Analysing data provides a great insight into the behaviour of a process, but when there is 

lots of it, a picture or graph is almost always easier to analyse than a set of numbers. 

The histogram is a graph that, once constructed, helps to identify whether the process is 

capable of meeting the customer’s expectation and provides an insight in to its behaviour. It 

provides a means to visualise the frequency (occurrence) of data, and thereby allows 

interpretation of process performance by analysing the centre of the data, the amount of 

variation and any significant changes or anomalies. 

  

 

The shape of the histogram gives further insight in to the behaviour of the process. Shapes 

that differ from the normal distribution (a symmetrical bell curve) indicate that other factors 

may be affecting the process, such as imposed targets, constraints or perhaps secondary 

processes. 

 

Where to use 

 

•

 

To assess the level of variation in a process 

•

 

To assess anomalies in the distribution 

•

 

To uncover the root cause of process performance 

•

 

To compare multiple sets of data, for example before and after improvement 

•

 

To investigate process performance in relative to the customer expectation 

 

How to use 

 

1.   Implement a data collection plan to collect the measures required to be analysed 

2.   Collect at least 50 data points to be confident that the sample will generate a 

representative histogram and distribution 

3.   Draw the horizontal (x) axis so that it encompasses the full range of data 

4.   Group the data into 10-20 intervals across the full range of data (depending on the 

sample size and resolution of the histogram required) 

5.   Count the number of data points that fall within each interval and plot the count 

(frequency or occurrence) on the vertical (y) axis 

6.   Calculate and mark the average of the data on the histogram 

7.   Identify the customer expectation and mark this on the graph with a vertical line 

8.   Compare the histogram to the normal distribution (bell curved and symmetrical) to 

understand how the process behaves and to identify anomalies 

9.   Assess the centre, spread and shape of the distribution to uncover the likely causes of 

variation 

10.  View the areas of the graph that fall outside the expectation limit(s) as the opportunity 

for improvement. 

---

 

 

 

D

 

M 

 

A I

C

 

Tool description courtesy of  © Processfix Limited 2008  

 

 

 

Handy tips 

 

Just because the average meets or exceeds the customer expectation does not mean that 

the process is working well. 

 

View the spread outside the expectation limit as the opportunity for improvement.  

 

 

Compare the histogram to the normal distribution (bell curved and symmetrical) to identify 

anomalies in process behaviour. 

 

Where there is more than one obvious hump, this signifies one or more processes in 

operation, for example a right-first-time process and a re-work process 

 

Always compare the histogram to local knowledge of the process. Knowledge of the data 

itself does not provide insight into potential improvements. 

 

Be wary of histograms that have very few columns as this may indicate a small sample size 

or low resolution of the measurement system 

 

Plot the same data in run chart form in order to detect trends and special cause in process 

performance. 

 

Example application 

 

Central government requires local planning authorities to make their planning decisions 

within a target time period. The planning authority’s ability to meet this target has a direct 

impact on their central funding. 

 

Constructing a histogram with number of days to process the application on the horizontal 

axis and the frequency of applications on the vertical axis, the performance of the process 

was plotted for applications received in the previous 12 months. 

 

With a range of 0 to 90 days, the horizontal axis was broken in to intervals of 5 days and the 

number of applications plotted in each interval. The results showed a prominent spike before 

the target time with most applications being completed just before the target date. 

 

The spike suggested that there was a frantic push at the end of the process to attempt to 

meet the target date. This suspicion was confirmed by those in the process who considered 

that application with a quick turnaround time were not a priority and thus delayed, often to 

the last moment in preference for those close to the deadline for a decision. 

 

The reason for this was the need to meet the target deadline rather than a drive to issue 

decisions in a timely manner. This target centric thinking became self defeating in that it 

caused a constant panic to return planning decisions before the looming deadline. 

---

 

 

 

D

 

M 

 

A I

C

 

Tool description courtesy of  © Processfix Limited 2008  

 

 

Consider using with 

 

•

 

Value stream map 

•

 

Run chart and histogram 

•

 Probability 

plot 

•

 Affinity 

diagram 

•

 Fishbone 

diagram 

 

 

Facilitation time 

 

30 mins 

---

 

 

 

D

 

M 

 

 

 

 

 

Number of BARs Customer specification limit  

 

A I

C

 

Tool description courtesy of  © Processfix Limited 2008