Q. 160  Hypothesis Testing - Business Success for any company depends on Continuous Improvement(CI) . CI requires creating hypothesis and testing them frequently. Most organizations create and test hypothesis (do trials for new ideas or carry on small experiments). For some reason, most professionals do not carry out statistical testing of hypothesis on sample data and tend to rely on gut feeling. It is seen that most Green Belt professionals do not use it while they have been trained on it. What are the key reasons for lack of use of this powerful family of statistical tests?   

 

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.

 

* Lack of knowledge on using hypothesis testing tools.

* Over confident on their decision due to experience.

* Management doesn’t permit to conduct trials and to collect data.

* Time doesn’t permit to conduct test.

* Not knowing the impact of bad decisions.

* Cost of data collection doesn’t allows.

There are many reasons as why Green Belt Professionals do not use Hypothesis Testing despite they getting trained on it:

1. Time constraint due to Management needs: One of the foremost reason (in my opinion) is time. Companies (especially Corporates!!) do have their own agenda - in completing a number of Six Sigma Green Belt(GB) projects (or even Black Belt projects) within a stipulated time period(normally half-a year or a year)- For instance, in the case of an IT company, it can happen at every vertical (Say Banking, Finance, Health,Manufacturing...) - this depends on a company's needs!! This goal can probably be set by top leadership and/or a combination of market needs(from Company's strategic thinking or goal alignment perspective) and Key stakeholders/top mgmt.  So every Continuous Improvement(CI) activity/project might have a curtailed time period and therefore this hypothesis testing might be overlooked.

 

2. Time constraint (induced due to size and complexity of the Data Collected): Time is a precious commodity. Normally, any CI project like PDCA, Six Sigma could take atleast 3-4  months of time and only with the help of a dedicated Sponsor or a process leadership team or a motivated set of individuals , a CI project such as a six sigma project(be it GB or BB) can be achieved.Now Assume (For simplicity sake, taken a crude and yet powerful(?!) example)that we are collecting data for efficiency(in terms of timely availability at the destination and prompt start from the bus depot-both measurable things) of bus transportation within a state or province. I need to have at least 3-4 months of data to see a pattern of how bad (that's why you go for an improvement project. Is it not?) it is. Assuming now you have collected the data (do you ever thought data collection is an easy job always ? :-) ) Now as we move on to hypothesis testing, the complexity and size of the data collected becomes a big challenge. Multiple factors can come into play especially if the scope is for multiple bus transportation units(Different vendors operating different category of buses across multiple locations) in that said state or province. So the GB team may not have sufficient time to properly analyse and utilise the data collected given the time bound nature of Six Sigma phases. Therefore Hypothesis testing might not be preferred.  

 

3. 'Cost' Factor: Any continuous improvement activity requires few things: Motivated Individual, Idea(to improve), Time and Cost. Often you get the first two (in that order), but the next two(Time and Cost) are vital things which determine if the idea can be implemented over a stipulated period of time. 'Time' and 'Cost' should go hand-in-hand to have an improvement activity. Having time alone and not having 'cost' is a problem. Hypothesis testing can turn-out to be a costly affair especially when analysis is made on complex and huge data and if there is not a proper guidance from a Black Belt or Master Black Belt (say, in case of a GB/BB project respectively), or if there is no subject matter expert(functional domain) associated for helping the GB team on providing the finer points on the analysis of the data collected.Therefore the GB team may consider in relinquishing this(hypothesis testing) exercise.
 
I feel the aforementioned factors, are key reasons for Hypothesis testing not being used effectively.  A special case scenario is also there.

 

Fear Factor (Due to lack of Hands-On Experience): However well a person is trained on Hypothesis testing(for that matter any activity!!), unless the person gets a personal(hands-on) experience , he or she will not feel how and what it is to do a hypothesis testing. The fear factor(for some people it is difficult to overcome the inhibition) can cause a team to deny the use of hypothesis testing. Though this can be a rarity case(but i have seen people with such inhibitions because hypothesis is a demanding technique and which requires deeper understanding and usage and training knowledge is not suffice and practical knowledge also slightly steep and only by experience you get accustomed to that).

 

Conclusion: Hypothesis testing is a very key activity in a continuous improvement exercise. Reason is that , you can statistically prove your point(read notion) or argument(Statement). It can statistically tell how significant or insignificant the factors that you took for your hypothesis is justifying the outcome.In other words, With hypothesis testing, we can actually see how much the statistical significance is being converted .into practical significance and how much it benefits the business. Therefore it brings so much value to the table. Its therefore, wiser to use hypothesis testing more so especially if the professionals are more trained in it.

1. Sometimes the Input Output differentiation is not ok.

2. Skipping is Human tendency and relying on experiences.

3. Sometimes it is skipped intentionally as you want to go for Alternative Hypothesis. 

Hypothesis testing: It is a statistical tool that evaluates two mutually exclusive statements about a population. The Hypothesis testing uses the sampled data to determine which statement is the best supported by the sampled data. the two mutually exclusive statements being the Null Hypothesis (H_o) and the Alternate Hypothesis (H_a)

Situations where Hypothesis testing can be deployed are 

• Is the mean height of boys greater than the mean height of the girls in the same age group
• Are male and female graduates with the similar competency and experience earning equally in diverse fields

and so on . However, there is a likely chance that the hypothesis testing is not practiced by the eligible six sigma professionals. it could be due to the reasons as listed below

1. The Organization culture: There could be organizations which run on unstructured methodologies, this is likley in proprietory type of organizations where in the authorities in the organization are less confident on the employees, or do not want to risk the six sigma professionals job wherein the jobs are less secure and providing replacements are tedious tasks.

2. Lack of support from Higher reporting authorities: When the higher authorities lack the wisdom to rely on the statistical techniques owing to incompetency.

3. Time constraints: It is very likely that the project timelines are not met and that further time to analyse the data is felt as time eating exercise.

4. Lack of trust on the competency of the six sigma professional: When the higher authorities sense a fear in the misinterpretation of data by the six sigma professionals then they take a call on their past experience and make unfactual decisions.

5. No testimony of previous records of continual improvements due to continual attrition of employees and frequent replacements.

 

The test is not used by GB's due to Negligence, or they are confident on their Gut feel, which can be wrong, however, there should be some grooming to the fresh GB's on the results and accuracy of hypothesis test.

Benchmark Six Sigma Expert View by Venugopal R

Hypothesis testing is no doubt a very powerful method for objectively deciding whether we have enough reason to believe that two populations are different. Once we understand the concept of hypothesis testing, one can discover that it has potential to be applied in almost all the phases on DMAIC. However, if we need to look at some of the key reasons why the tool is not patronized to the extent it could be, I would put down the below points, though these may not be exhaustive.

 

1.     A green belt professional can gain adequate proficiency and confidence in the use of TOH only by repeated practice and deep thinking. The few examples used in a GB training are meant to illustrate the tool and its application, but many more examples need to be tried out.

 

2.     From the various examples that are done, the participant needs to relate situations in his / her work area where the type of data used can be comparable. For instance, an example from a manufacturing situation can be compared to one in a services industry as far as the data is concerned. It could be “number of units produced vs number transactions served”.

 

3.     The non-availability of statistical software like Minitab, Sigma Magic or equivalent has been seen as a deterrent. Most participants get trained using a trial version and later they are not equipped with the software.

 

4.     Many a time, the leader (& sponsor) is anxious to implement improvement actions and do not spend adequate time and effort to have baseline data. Once improvement is done, even if they want to compare with the ‘before’ situation, they are constrained due to lack of baseline data.

 

5.     Participants are sometimes unsure of the choice of the tests as applicable to their projects. Hence, they tend to avoid using this tool, in fear of using a wrong test.

 

6.     The sponsors and other senior management leaders may not have the knowledge to appreciate the usage of Test of Hypothesis, which could discourage the GB to try it out, unless strongly supported by a good Blackbelt / Master Black belt.

 

7.     The ability to interpret the results in a “Business language” rather than a “Statistical language” is another important skill for a Project leader to impress the benefits derived by using TOH, and other tools.

 

8.     There may be some instances where the volume of data available could be very large, or the delta is large, to show very obvious differences between populations, which could render the usage of hypothesis testing as redundant.

 

9.     There could be some who would not have gained an acceptance nor belief to the usage of the method and continue to be comfortable with ‘gut feeling’ decisions.

 

There would be many other reasons as well, which I expect other ambassadors to narrate. On the whole, usage of TOH will be improved with more mentor-ship, exercises, making the software available, and getting the senior leadership exposed to appreciate the use and power of such tools.

The chosen best answer is that of R Rajesh, because of the structure and detail. 

 

Each one of the answers, however, outlines some unique challenges that keeps practicing GBs away from Hypothesis Testing. Read through to get a well rounded understanding before you devise a plan on how to overcome these obstacles.

 

If availability of software is one of them, use our calculators at https://www.benchmarksixsigma.com/calculators/

 

Our expert view is provided by Venugopal R