What is a Histogram?
Information & Training. | SPC and Statistical Methods of Improvement.A histogram is a form of bar graph based on the distribution or frequency of occurrence of a range of data. The histogram creates a visual picture which allows the reviewer to relatively easily understand and interpret a set of data. The bars within the histogram reflect the frequency of occurrence of particular sets of data. Histograms are different to other forms of bar graph in that there are no gaps between the bars within the graph so that information is shown in a continuous format, versus discrete sets of data which may be shown with other forms of bar graph. The bars within the histogram are shown in accordance with how data arises, i.e. the data is not rearranged along the lines of increasing or decreasing frequency, in this manner the histogram gives a true picture of the data as it exists from the selected process being measured.
An example of a histogram is as shownA review of the histogram will provide very useful information such as the mean, mode, average, range, skewness, the existence of multiple distributions, the frequency and extent of any outliers. With this information, decision can made on actions required to improve a process, equally, where changes are made to a process, histograms taken before and after the change can quickly and very visually demonstrate the impact of the change.
When can you use a histogram?A histogram will provide a significant amount on information in a very visual format on process performance. A histogram can be utilized to show process history, or to predict future process performance. However, the process must be stable, if not stable then the information provided may not be reliable.
Stable processes, Common Cause variation and Histograms.
A stable process is a process where the causes of all variation arise from common causes* (versus special causes of variation), the result is that the output of the process is predictable within understood limits. These limits of process output may be acceptable or unacceptable in terms of variation, but at least they are known. If the variation is unacceptable, then decisions can be taken to try to reduce the process variation, in effect increase the process capability.
*Note: Common cause variation, is variation caused by unknown factors which result is a random but steady distribution around the average of the process outputs.
Histograms for Discrete and Continuous data.
Histograms are applied when interrogating sets of both discrete and continuous data. Discrete data are values, numbers, etc., that are counted as separate and distinct and can only take particular values, for example the number of components in a product, number of products shipped, etc.. Continuous data, is data which is measured and which can take on a range of values within finite or infinite intervals, for example weight, length, temperature can all be measured to infinite levels of detail, however, in practice will only be measured between 1 and 2 decimal places of accuracy in most situations.
Benefits of Histograms for process and operational analysis and improvement.Histograms are a very clear, powerful, visual means of communicating process performance. They are an excellent means of communicating the effect of changes implemented on a process. They can be used to demonstrate current process capability, hence expected future process outputs and therefore allow process owners to determine if change is required to meet customer expectations or alternatively can be used to justify decisions against implementing change within a process.
Information & Training.
SPC & Statistical Methods for Process Improvement.
- Process Capability. Variability Reduction. Statistical Process Control.
- Pre-Control. R&R Studies.
- Process capability indices Cp, Cpk, Cpm, Capability ratio.
- Performance indices Pp and Ppk.
- Variable Control Charts.
- Attribute Charts.
- Pareto Charts.
- Individual – X Charts.
- Histograms / Process Capability Analysis.
- Scatter Diagrams.
- Etc. … Etc. …
- Information & Training presentation >>>