Q 76. Why is it that long term performance is calculated and treated differently from short term performance of a process? 

 

The answer with the simplest and accurate description will be preferred. 

 

Note for website visitors - Two questions are asked every week on this platform. One on Tuesday and the other on Friday.

• All questions so far can be seen here - https://www.benchmarksixsigma.com/forum/lean-six-sigma-business-excellence-questions/
• Please visit the forum home page at https://www.benchmarksixsigma.com/forum/ to respond to the latest question open till the next Tuesday/ Friday evening as per Indian Standard Time.  
• The best answer is always shown at the top among responses and the author finds honorable mention in our Business Excellence dictionary at https://www.benchmarksixsigma.com/forum/business-excellence-dictionary-glossary/ along with the related term.

The process capability and hence the sigma level of an improved process will be at a greater level, as soon the improvement is done. Because every process will have a natural degradation, the process capability and hence the sigma level of that process will lower down, over period of a time.

 

Motorola figured this out quite early and made a shift allowance of 1.5 sigma . Long Term variation = Short Term variation -1.5 Sigma.

 

Very simple example for a process degradation : If a road is being laid out on National Highways, for one/two month(s), there may not be a soft spot or potholes or damaged spots. But by 4-6 months, the road may be severely damaged or even inaccessible. This is due to multiple causes such as Env.conditions , heavy traffic, more heavy vehicles operating

 

Another example is Software Code deployed in production. First one or two months or during the warranty period (Short-term) there would not be much issues or minimal issues.But post that (long term), the issues could creep more as we may not have SMEs available, new team might work on the supporting the application,...

There is a shift of 1.5 sigma between long term and short term performance of a process. In other words a 6 sigma short term process would be a 4.5 sigma long term process. This is because the data considered for a short term performance calculation just has common causes of variation, is collected from from narrow inference spaces and restricted sampling is done like collection from one lot, batch, etc.

 

However, when data is considered for calculation of a long term process performance calculation, it is collected from different time frames, broader inference spaces and sampling is done from multiple batches, lots, etc. As such this data along with common causes of variation also has special or assignable causes of variation.

 

Hence a high sigma level for a process in short term lowers by roughly 1.5 if the long term performance of the same process is considered.

 

The long term performance or also known as “Long Term Capability” for a process, itself implies that it has to be taken for a reasonable period of time.

 

At any given point of time, if we measure the process capability for a process, it will always be the “Short Term capability”. The short term denotes to process potential, when operated under a set of variations that are always expected to be inherent in the process at any point of time. Statistically these are variations that may be typically depicted by the spread of an associated normal distribution on both sides of the mean value. It is particularly useful to quickly understand the effectiveness of a change that is expected to reduce the variation, i.e. improve the process capability.

 

If the short term capability itself does not meet the expected requirements, there wouldn’t be a need to run a long term capability. Knowing that during the long term a process will get subjected to additional variations the could impact in the shifting of the mean value, it is important that the short term capability has to be adequately good enough to enable the process to accommodate additional variations in the long term, so that the long term capability will still meet the expected requirements.

 

Considering the practical challenges in terms of the time and effort in obtaining the long term process capability, it has been agreed that during long term, one may expect a shift of the mean value by 1.5σ on either side of the mean will be an acceptable indication of the long term capability.

 

Thus in order to attain a long term process capability of 4.5σ, we need to ensure a short term capability of 6σ.

Before proceeding lets define what’s long term and short term.  For easy understanding say 1 year and above is considered as long term and anything below 1 year is short term.

 

• The variations or challenges might not vary drastically in a Short term process.  Where as a long term process would have higher spikes.
• Short terms cannot have a compounded effect, but long term has.
• Considering the investment, long terms always fetches good returns compared to short duration.
• Employees who work in the same company for longer period are considered as seniors irrespective of their performance where as a new employee will be treated differently (again irrespective of the performance).
• Short terms may seem attractive, but long term is taken for granted (in terms of process).

 

Long term performance is to be treated differently compared to short term performance as there is a scope of random variations that could be introduced in the process because of several changes which could be but not limited to new employees in the process, change in measuring standards and/or any abnormalities that could have run into the process. As the scope for this to happen in measuring short term performance is less, and as there would be more number of subsets in long term(of short term), the performance could most probably come down in long run.

 

This is even supported with the calculations of Short and long term sigma where usually the long term sigma is a difference of short term sigma and 1.5(one point five sigma) to attain long term sigma value. 

Long Term & Short Term Process Capability:

 

The Capability indices [ Cp, CpK ] & the Performance indices[Pp & PpK] can be considered as the Long Term & Short term  on the Basis of Method used to calculate Sigma, an estimate of Process Standard Deviation.

 

- Cp & CpK represent the Long term Process Capability, while Pp & Ppk represents the Short term Process Capability.

- The AIAG suggests us that we can use PpK for a Production run of less than 30 days & CpK for everything there after can be used

 

- Long Term Variability = Short Term Variability + 1.5 Sigma Shift. This Interpretation is based on the underlying assumption of Six Sigma, which indicated that the Process will drift or Shift  +/- 1,5 Sigma in the Long term. When this shift is taken into account, 6 Sigma process performance equates to 3.4 ppm, otherwise 4.5 Sigma Process performance equates to 3.4 ppm.

 

The Main reason why the Long term Performance is calculated & treated differently is that the Long term Process capability gives out the exact output of the current running Process. It also include the Common Causes that occur during the Process & gives us the result. During the Short term process, we cannot completely analyse the entire Process & Process Capability calculated during that period, may give us a hint only about the process. So Long term Process capability is preferred for complete understanding of the Process performance & calculate the Process capability

Long term performance of a process means Sigma Long Term and Short term performance of a process means Sigma short term. The question is why Sigma short term is calculated and treated differently than Sigma long term.

 

Sigma short term of a process is usually given higher value than Sigma long term of the same process because, it is without any noise and reflects the current state of the process. Smaller deviation is seen in the process when measured in the short term, similar to students performing excellently in Unit tests and weekly class tests. The person studies a smaller portion and answers a smaller set of questions, similar to having a smaller set of population to test the performance of the process.

 

In case of Long term performance of a process, the data points are more and hence more noise and more deviation.  Greater deviation can be attributed to lot of factors and indicates measuring performance of a population rather than a sample. Hence Long term performance is measured differently. An anology would be the student performing well in the Annual exams.

 

So simple answer is population and sample size determines it