RaghavendraRao

When the process is too much unpredictable, then variation would be a key measure than central tendency. In case of special causes having major influence on the system variation then in that case as well variation would be more relevant compared to central tendency. More skewed the data is then more relevant would variation become compared to central tendency.

Categorical data class of discrete data will be more useful to understand overall characteristic of the target under study like eg: underweight, normal, obese. This is usually just another kind of binning. In case of performing qualitative study like customer satisfaction discrete data will be more useful to analyze and come to conclusion rather than a discrete data. In scenarios where ranking has to be done based on relative performance ordinal class of discrete data will be handy compared to continuous data. Population census data analysis and clinical trial analysis of drugs are the other areas where discrete data are handier compared to continuous data.

Tribal knowledge in unwritten information about a company, which is commonly known by company. Tribal knowledge can also be related to innate skill that the work force hold. There should be conscious effort to enhance the company working model with these tribal knowledge aspects, by which this undocumented gap is kept to minimal. Strong training programs will help bridge the knowledge gap between older workforce that hold tribal knowledge and the fresh work force that is building future of the company. It’s important to identify the key personnel from experienced work force and also identify the key knowledge that need to be shared across with new work force. Center Of Excellence focusing on key Tribal knowledge area would be a good idea. Management need to accept the importance of the tribal knowledge and invest time of the company work force to nurture it. Since Tribal knowledge has influence on the quality of the deliverables of the company, it’s very important to focus on harnessing this. To make sure all other effort for improvement achieves its intended objective, it’s important to harness tribal knowledge to contribute in this direction.

Rational subgrouping first of all helps Excellence Practitioner to make analysis a cost efficient one, unlike targeting big set of data for analysis, this help to gather reasonable amount of data that represent a population. In case if rational subgrouping is not considered then in pursuit of process improvement, we will not be able to distinguish between what is the key influencing factor for the behavior of the process samples. Ideally it’s expected that the sub grouped sample have a consistent behavior and are produced under similar condition. This helps to make meaning out of the behavior of the group, else it will be difficult to attribute the behavior to a specific cause. Understanding variations in the process is an important aspect of process improvement, so if the subgroup is not consistent with its behavior then studying variations will become complex due to varied behavior of different data set in the sampled group. At a basic level, if rational subgrouping is not considered then it may increase the need of increasing the sample size that adds on to the cost.

Since it always works efficiently and effectively when we introduce things in top down approach, sponsors play a crucial role in Business Excellence journey. Most important qualities needed for the Sponsor is the appetite to understand the latest Business Excellence strategies adopted in the industry. Sponsor should make Business Excellence initiatives part of strategic goal starting right from the vision of the organization. Sponsor should have open mind to invest efficiently for Business Excellence with long term returns in mind. Sponsor should play an ongoing role of being the brand ambassador for the Business Excellence initiative which will motivate people to make these part of their initiatives. Regular communication from Sponsor on the importance of these initiatives to the organization plays a crucial role. Also Sponsor should make Business Excellence initiatives journey progress review a key part of regular governance activities. Sponsor should also make sure that progress status are communicated to organization to keep people in action. Appropriate rewarding mechanism to encourage the Business Excellence initiatives will keep the momentum going.

Primary influencing factor for baselines before and after improvement to become non-comparable is probability of process itself undergoing significant change. Which means that some of the key parameters might undergo major change, which calls for process to be re-baselined again before it can be compared. All possible influencing factors are to be kept under check as we make improvement is the key. This helps us to get at logical conclusion that whatever changes observed in process purely due to the improvements made. Just statistical analysis may show that there is significant change in process before and after improvement, but logical analysis to make sure that the improvement done on targeted parameter caused the same is very important. DOE – Design Of Experiment if it fits in to a scenario then it would help in a situation where, process before and after have undergone change. Here some of the process factors that may have undergone changes due to influence of something outside the intended change then those factors can be made constant and then analyze the impact of factors under consideration and then may be baselines of process before and after improvement will become comparable.

Though zero rework should be the mindset in the pursuit to business excellence its extremely important to trade off this decision with Return On Investment provided by such high quality outcome. Overall output is influenced by cost, quality and time. It’s an important conversation that is needed with customer on how we tradeoff between these three in the context of their importance to customer. When time becomes critical then zero rework may not be feasible, and cost will go high as well. Rework acceptance also boils down to criticality of the output and where does it fit in. Like in case of pace maker that is implanted in to body would expect to be manufactured with lower rework compared to an office printer which is not similarly critical. Space shuttle would be one another critical area that would need perfection as outcome. Otherwise there is no need to compromise on cost to just to get zero rework outcome. Also in case of mobiles it may not make sense to wait for perfection until you reach to market only to realize that your version is outdated, it may make sense to go in to market with at best quality and then strive to rework on improvising the version so that you may not lose on marker hold.

Descriptive Analytics is quiet well captured by Lean Six Sigma community. As industry has largely systems established to track the performance through performance metrics and these historical data is used to understand the trend of the business based on which future goal of the business can be decided. This also facilitates solving current problems of the business understanding trend of performance. Predictive Analytics are captured to a reasonable extent by Lean Six Sigma community, though there are system in place to capture performance and use the same to build predictive engines, but due to challenges in data management and tracking, these systems has not been used to best extent. Prescriptive Analytics are somewhere in between other two, in terms of how well they are captured by Lean Six Sigma community, as many business decisions are now based on the outcomes of the historical data trends and predicted outcome of the process. As business decisions are largely happening based on top management expectation based on their experience, prescriptive analytics is slowly pitching in for making better decision, and bringing confidence to management to make decisions based on these. But more confidence need to be built by Lean Six Sigma community to make sure this system is completely reliable.

Basic needs addressing should become part of the culture of the organization. Systems should be built in the organization to make sure that the basic needs of the product are built in efficiently and effectively. Establishing a good Delivery Excellence framework referring to best models in the industry may be ISO standards, CMMi models and other best practices. Performance needs are the aspects that provides opportunity to gain customer confidence for long term engagement. Part of performance need to be built in to the product as part of effort involved in building basic need, which will be part of establishing a good system. On top of it performance needs also help addressing customers evolved needs based on the market experience of the customer. Since this is an opportunity as well as responsibility this can be considered as top up layer for the organizational culture once basic need addressing system is built. For this, continual improvement mindset initiatives like KAIZEN, Lean Management would be helpful, where every individual is involved and contributing to build the culture. In case of excitement needs addressing, this is an opportunity to establish hold on market place and delight customer by something which is unexpected by customer. For this kind of impact organization need to look at disruptive innovation that helps build, disruptive solutions for delighting the customer.

Statistically significant difference is the statistical confirmation that the difference seen between two sets of data points are significant. If we go by simple difference and conclude that two sets are different it may not help us understand if the difference is significant. Only if its statistically significant difference then it makes sense to draw conclusion about set of data points. This is evaluated using hypothesis testing, where null hypothesis is taken as there is no statistically significant difference between two sets of data points, whereas alternate hypothesis is stated as there is statistically significant difference between the data points. Which hypothesis test to be chosen depends on the type of data sets and is a different topic of discussion. Based on hypothesis results obtained (p value) either of the hypothesis statement is proved. One basic application of this concept is to evaluate, if the actions taken for a problem is effective. Only if it proves that the data sets before improvement and after improvement are having statistically significant difference then we will arrive at the fact that the action plans are effective, if not analysis of cause and action plan would need further investigation. This analysis also helps in understanding how significant is the difference by looking at standard deviations of data sets as well. Based on the statistical significance of the difference between two data sets, further decision making will be influenced. Also this concept helps to make decision about the characteristics of the two population of data like, to select best vendor for the services based on their historical performance data. Also would help to make decision to select best performing product based on their historical performance.

Stable process is one where the variations are predictable and the causes of the variations are also predictable and are common causes inherent within the system. Basically all possible special cause of variations in the system are understood and addressed. Capable process are one where process is primarily stable and in addition it is good enough to meet the specified goals consistently. In case of stable process distribution of data will be consistent over period of time. Process stability has to be pre-requisite for all processes, though stable process does not mean process is capable and vice versa also is true. But capability of process is the state at any point of time, whereas stability is the state of process over period of time. And also assessment of capability is against a specified goal, its important to make sure that process is understood well before declaring it capable. In that context its important to confirm stability before assessing capability. Example would be a insurance claim handling process where time taken to close the claims would be stable means that the process is consistent in handling time with known variations. Unless its confirmed to be stable how do we make sure that process is robust and capable to meet customer demand. It may happen that some claims breach the SLA due to unusual behavior of the process. So for a proactive monitoring of process stability is primary reference followed by capability.

Though Correlation does not prove the cause-effect relationship of two variables, it still is the first good step to ensure that there is some kind of relation between the variables. Either positive or negative relationship between variables can be known. It also provides details on the strength of the relationship between the parameters. This plays a prominent role when root cause analysis is done, so that the confidence level will be high for applicability of the causes identified for the problem. Else going only by root cause analysis method would bring in subjectivity. Correlation helps in quantitatively establishing the relation before further root cause analysis is done.

Voice Of Customer may fail to be useful if we do not understand need and importance of the same. Its just not enough to collect too much of customer feedback and try to fit them in to the design of product without focusing on incorporating the changes in to the processes involved. Also other challenge is translation of actual expectation of customer in to customer delivery without losing out on original expectation is another road block. One of the example of VOC becoming detrimental, is likelihood of customer feedback coming from the areas of their familiarity, and not being holistic in nature, this may lead to building in wastes in the system. Good example on working at high leve and designing product without focusing on systemic change is Kodak company which though innovated in to digital cameras good not gain out of it as they did not have needed business model for the same. Another good example is when customer demands for the solution we may have look deep in to the need and design the solution that will help build customer delight. Good example is in this article referred below, which gives example about the company demand on windows cleaning services, where their expectation was on quality of cleaning and time of cleaning beyond office hours, with the need of making sure that the good amount of light enters the work space providing good work environment. While many cleaning service companies have been using such customer feedback to improve their offerings, another company has virtually succeeded in eliminating or minimizing the need to clean glass windows. Providing a clear view of the outside and allowing sunlight into the room without the need for cleaning the window regularly. By taking inspiration from nature, Pilkington Glass created a “self-cleaning glass” with potential to disrupt the window cleaning industry. After studying lotus leaves, which have a microstructure that repels water droplets and allows those droplets to pick up dirt particles, Pilkington developed a photo catalytic and hydrophilic coating for the external glass pane of windows, enabling the self-cleaning process. Reference: https://www.leanmethods.com/resources/articles/fallacy-voice-customer

Organization has to start with SIPOC which is bird eye view of the overall process. SIPOC helps to understand overall end to end process starting from understanding who all are the suppliers for the process, what all inputs comes in to the process, what all process gets executed, to convert the inputs to valuable output, what all are the outputs of the processes and who all are the customers of the processes. Second step would be to arrive at swim lane, which focusses on various interactions that happen between various departments or processes of functions within the organization. This help to understand the need of key collaboration across various functions involved. Next steps would be to study the value flow across the processes. Value Stream Mapping helps to chart down complete process breaking down every conceivable process steps, assessing if every element of the processes adds value to the customer or not. Also analyzing the cycle time of every process element. These analysis outcomes about value proposition and the time spent in the process steps together helps to make decision about the need of optimizing current process by possibly eliminating the process step, or reduce time spent on it.

First reference for confusion between continuous and attribute data is when there is mix of continuous and attribute measures that forms a metric. Example Defects density is a metric derived by dividing total number of defects by total effort spent in the project. Here total defects is a attribute data where as total effort is a continuous data, but since atleast one of them is continuous data, overall outcome which is defects density is considered as continuous data. Other confusing scenario is pseudo continuous data, When you treat discrete data as continuous, it may be referred to as pseudo continuous. And when you take averages of ratings for let's say 10 bank tellers. An example - This could be a 0 to 10 rating scale. You may get an average rating of 7.5. One should usually manipulate discrete data into continuous or consider it as pseudo continuous with the intent of using tests applicable for continuous data. (Please note this was clarification provided by VK or Rupinder from Benchmark on one of my question). Other confusing scenario is when we need to consider, data points above 10 as continuous else discrete.

Correction is a quick fix to immediately take control of the situation. Corrective action focusses on the root cause of the problem and addresses it, to take care of possible recurrence of the problem. Preventive action focusses on elimination of any possible similar issues that may come up based on the experience gained due to problem that has already occurred. Preventive action basically focusses on potential root causes that would create problem. Lets take problem as buttons in the shirt has fallen off. Correction would be to stich the button back so that shirt can be put to use immediately. Corrective action would be to identify what caused this problem, if the root cause turns out to be the way shirts are washed, then corrective action should be to change the way that shirt is washed, so that this problem of shirt buttons getting cut off can be avoided. So based on the root cause corrective action should be decided to remove those root causes from the system. So that in future even if problem persists it should not be from same root cause. For preventive action we need to look at this problem and gather learning and try to use this learning and plugin in all potential causes that may create problems related to shirt button. In Research and Development situations, largely correction may be applicable in most of the situations, where as preventive and corrective action may not be applicable. Since the scope of the operation itself is to explore on all possible permutation and combinations in reasearch, largely focus would be to make course correction and keep exploring.

Checksheet as a base concept may not be removed from the quality education as such. It is a basic mechanism of tracking system performance at the source. So it will retain its existence. Since for any analysis basic need is preliminary data, which is provided by the checksheet concept, it will hold ground as basic need. To make sure that the initial discussion done about a problem is not qualitative but factual checksheet provides a base. Checksheet as a concept will continue to work handy in many areas where on the floor observations matter, like taking note of car condition before it is taken in for service. Keeping check of machine condition on floor and so on.

Supplier not aligned with the manufacturer is a practical challenge, as planning and scheduling is not happening at close to shop floor, leading to making pull system difficult. Change in the incharge personnel is another challenge as that will create lack in consistently maintaining the practices enabling a pull based system. Pull based system cannot be implemented in all circumstances as it will increase the lead time of the processes. There would be certain part of process that can be managed with pull system, but certain processes need to be managed through push, to balance between push and pull. In case of healthcare complete pull system would not be practical due to varying health condition and demand.

Common cause variation would be historical references to compare with and its natural part of the system on most of the causes. Whereas special cause of variation will be unusual instances which do not have historical reference. Common cause variations impact on system would be considerably less compared to special cause of variations. Common cause of variations are predictable in nature whereas special cause variations are not. Differentiation is important as underestimating a special cause for a common cause may be harmful for the system as it may go out of control. Also taking special cause as a common cause may deny us the chance of using the system to its potential best. Misjudging of these in real world in case of health care would be a disaster. Say in case the symptoms of unhealthy condition in a body be judged as a common cause where as if its a case of special cause then there is potential of causing more harm to the body and health condition and lost oppurtunity to have proactively acted upon on the symptom. Other way round a common cause also cannot be misjudged as a special and treated which will induce unwanted treatment to the body when it was not needed.

One of the examples of autonomation from my own company is the BOTS that we are building to build on intelligence in to some of the routine, repetitive tasks that our Operations team does. We are in to tittle insurance business, our operations team handle many processes related to handling the tittle insurance of properties, right from understanding the content and making necessary updates in to data base and provide necessary feedback. We are working on creating BOTS that can understand the context of the document under processing and make all required checks, data gathering and processing of the documents. Here these BOTS cut down on possibility of error due to human intervention in these repetitive tasks and also cut down on the cycle time. Unlike if its just case of automation its more to replace repetitive work where still human intervention is required to validate the outcome of process. Autonomation process also helps to learn from the process handled by BOTS and refine it further and get better every time the operation is repeated.

Pacemaker process is a key point in the value stream, pace of entire value stream depends on way in which the pace of this key process is managed. Importance of selecting an activity as pacemaker is, it decides which all elements in the value stream becomes part of lead time computation from customer order to finished goods. Pace maker process also acts as the input process to receive the production schedule planned according to TAKT time, which further sets tone for upstream processes for further processing.

Primarily hypothesis is used in Analysis of the problem area to screen potential causes. Hypothesis test helps assess if proposed improvement project results in statistically significant improvement. In case of analysis of various process factors, hypothesis test helps to assess which all factors have significant influence on outcome. It also helps to figure out if the improvement observed in process is due to the actions initiated by us or due to chance variation. Hypothesis testing helps to address the possible sampling error involved in the study of sample data of the population. Overall in pursuit of excellence hypothesis test helps to validate any possible assumptions involved in the analysis and cut down on possible errors due to assumptions.

Primarily Poka Yoke is about setting of system where human error will not happen at all. Example is in case of Car, driver will be able to shift gears only by pressing the clutch pedal, this ensures that there is no uneven movements as the gear is shifted. Also in many cases car can be started only if brake pedal is pressed which ensures that there is no sudden movement of car. In case of human error may continue to happen but defects will not happen, where the fixture of machine would be equipped with the sensor, it will make sure that fixture does not operate unless the part is appropriately inserted in fixture. In case of error may happen, defect also may happen but will be detected and corrected, example would be auto correction feature on computers and mobiles.

In the scenarios of Cyber security operations, too many false alarm may lead to desensitized security personnel where there is chances of critical alerts getting missed. Where as few missed alert may not be significant in comparison to too many false alarms. Also in Health care centers where there are alerting system like blood pressure machines, ventilators and heart monitors, there is risk of too many false alerts sounds making the brain of the personnel in charge getting tuned to the sounds of alert where as few missed alerts in comparison would not be significant.

Since TAKT time is maximum available time to meet demand of the customer, it drives strategic decision making. TAKT time assits in configuring optimal speed of the production. TAKT time drives the lean mindset in the process because to meet customer demand, required speed of operation has to be maintained which calls for keeping process lean.