{"id":1779,"date":"2019-05-31T15:18:43","date_gmt":"2019-05-31T15:18:43","guid":{"rendered":"http:\/\/wiki.thomasandsofia.com\/?p=1779"},"modified":"2019-05-31T15:18:43","modified_gmt":"2019-05-31T15:18:43","slug":"six-sigma-transcripts-5","status":"publish","type":"post","link":"https:\/\/wiki.thomasandsofia.com\/?p=1779","title":{"rendered":"Six Sigma Transcripts 5"},"content":{"rendered":"
\n
\n
\n

Steps in the Measure phase<\/h3>\n
\n
\n

– The Measure phase is the second phase <\/span> of a Six Sigma project. <\/span> It is the M in DMAIC. <\/span> Let’s start with a basic question. <\/span> Why bother doing the Measure phase? <\/span> What is the purpose? <\/span> The Measure phase is to measure the size and scope <\/span> of the problem or performance gap. <\/span> How big, how bad, how widespread it is. <\/span> Say you are the owner of a pizza chain <\/span> of 10 restaurants in the local area, <\/span> and your sales have been declining over the past year. <\/span> Initial analysis of the year’s complaint data <\/span> shows that 85% of complaints were related to pizza crust. <\/span> So Where would you focus your project? <\/span> Pizza crust, of course. <\/span> Remember in Six Sigma we use the equation <\/span> y is the function of x, which is y equals f of x. <\/span> In this project, the y is the pizza crust. <\/span> Wouldn’t you want to know how big and bad <\/span> the pizza crust problem is? <\/span> And wouldn’t you want to know how widespread it is? <\/span> For example, is pizza crust problem <\/span> equally bad across all 10 restaurants? <\/span> Are some worse than others? <\/span> Or is it limited to just one restaurant? <\/span> That is what the Measure phase does, it measures the y. <\/span> The purpose of the Measure phase <\/span> is to measure the y in y equals f of x. <\/span> What are the stops involved in the Measure phase? <\/span> Before you spend time and resources <\/span> collecting data and measuring, <\/span> you need to develop a data collection plan. <\/span> That’s step one. <\/span> To help you know where to collect data, <\/span> you need to understand activity <\/span> or processes involved that impact pizza crust. <\/span> You need to map the relevant processes. <\/span> That’s step two. <\/span> Before you start collecting data, <\/span> or using data that has been collected, <\/span> you need to ask, are the measurements valid? <\/span> Were they measured and recorded correctly? <\/span> You need to ensure that a the data <\/span> and measurement system used is valid. <\/span> That leads us to step three. <\/span> Then and only then can you measure how bad the problem is. <\/span> How bad compared to what? <\/span> How bad compared to requirements, specifications or targets? <\/span> In other words, how well are requirements <\/span> and customer expectations met? <\/span> How often is it met or not met? <\/span> How widespread is it, and so on. <\/span> Use the collection plan developed earlier <\/span> to guide you in measuring the y, <\/span> so that all the questions listed on that plan <\/span> will be answered. <\/span> So step four is, measure the y in y is a function of x. <\/span> In summary, here are the steps in the Measure phase. <\/span> Develop a data collection plan, <\/span> map relevant processes, <\/span> validate the measurement system, <\/span> measure the y. <\/span> Also often, project teams waste time going in circles, <\/span> trying to measure everything in this phase. <\/span> You, on the other hand, will not. <\/span> These steps will help you plan <\/span> and execute the Measure phase. <\/span><\/p>\n

\n

How to map the current process<\/h3>\n
\n
\n

– If you have problems getting to work <\/span> on time in the mornings, <\/span> would it not be useful to understand the activities <\/span> and sequence of steps that take place each morning? <\/span> In other words, what does your wake up <\/span> and get to work process look like? <\/span> What you need is a process map. <\/span> A process map is a diagram that provides <\/span> a visual representation of the process flow, <\/span> or sequence of activities, <\/span> or steps that take place in a process from start to finish. <\/span> Here’s an example of a process map <\/span> for the Wake-Up-and-Get-to-Work Process. <\/span> Activities or tasks are represented by rectangles, <\/span> decisions are represented by diamonds, <\/span> and the sequence of flow is represented by arrows. <\/span> And start and end points are represented by ovals. <\/span> If you run out of space, connectors shaped as circles <\/span> can be used to continue to the next page. <\/span> The flow can go from left to right, or from top to bottom. <\/span> Here are some common symbols for process mapping. <\/span> Process maps are very useful in a Six Sigma project. <\/span> During the measure phase we map the current process <\/span> using a process map. <\/span> This provides the project team, <\/span> and everyone else involved, <\/span> with a visualization and common understanding <\/span> of what actually happens in the process. <\/span> Think of it as a photographic snapshot <\/span> of the actual SS process. <\/span> A process map enables you to see and understand the process. <\/span> A picture is worth a thousand words. <\/span> Also, once a current process has been mapped, <\/span> the team will also know what’s not happening <\/span> or what’s different from what should be happening. <\/span> Therein lies the power and benefit <\/span> of mapping the current SS process. <\/span> In our example, you get a better understanding <\/span> of what goes on each morning. <\/span> It will help you decide where in the process <\/span> to collect data and analyze further, <\/span> or it may show immediately where the delays, bottlenecks, <\/span> and work-around’s are that is causing you <\/span> to be late for work. <\/span> The process map provides a basis for understanding, <\/span> and further analysis. <\/span> When you map a current process, <\/span> I would recommend the following: <\/span> Involve those who work the process, <\/span> and those who know the process. <\/span> They are most familiar as to what actually happens. <\/span> Decide on the start and end points of the process map. <\/span> Use a logical orientation. <\/span> Either from left to right, or top to bottom flow, <\/span> to capture the sequence. <\/span> Walk the process as if you are the transaction or work item <\/span> that is being processed from start to finish. <\/span> For example, if you are mapping the invoice process, <\/span> be the invoice. <\/span> Walk step-by-step as if you are the invoice. <\/span> Document what happens to you at each step of the way. <\/span> Do not try to analyze or improve the process at this time. <\/span> Just capture the as is of what actually happens. <\/span> You are mapping the current process, <\/span> not proposing any solutions. <\/span> When the process map is completed, <\/span> have it reviewed and validated <\/span> by those familiar with the process, <\/span> including those who work the process. <\/span> You can map any process, including your morning routine. <\/span> Follow these tips and you’ll make it to work on time. <\/span><\/p>\n

\n
\n
<\/div>\n
\n

Plan for data collection<\/h3>\n
\n
\n

– Let’s assume you decide to get on a health <\/span> and fitness program. <\/span> What is the first thing you do? <\/span> Well, you’ll probably want to know what is <\/span> your current weight, how much you need to reduce <\/span> to get your desired target weight, <\/span> and what is your current level of activity, <\/span> are you in good health, and so on. <\/span> These are very good questions to ask as you plan <\/span> to collect data in order to measure where things <\/span> stand today and to measure progress. <\/span> Similarly, that’s what you need to do <\/span> in a Six Sigma project. <\/span> In this movie, I will discuss how to plan <\/span> for data collection during the measure phase <\/span> of a Six Sigma project. <\/span> Why plan for data collection? <\/span> Collecting data is not free or cheap. <\/span> Collecting data requires time, effort, and resources <\/span> being tied up. <\/span> All too often, project teams who do not plan <\/span> for data collection spend too much time during <\/span> the measure phase going in circles, <\/span> hunting for data, collecting data, and measuring <\/span> everything in sight. <\/span> Perhaps it would be useful to ask a basic <\/span> question regarding its purpose. <\/span> Why do we collect data? <\/span> To obtain information and answers to questions <\/span> we want answered and that’s where you need to start, <\/span> with the questions. <\/span> To plan for data collection, I recommend <\/span> the following steps. <\/span> Step one, make a list of specific questions <\/span> you want answered regarding the Y. <\/span> Step two, for each question listed, decide <\/span> how you want the answers presented and displayed. <\/span> Step three, based on that, decide what tools <\/span> are needed to make that possible. <\/span> Step four, for each question, what type of data <\/span> and how much data are required by that tool. <\/span> Step five, determine where and from whom <\/span> the data should be collected. <\/span> Going through these five steps will result <\/span> in a data collection plan. <\/span> For example, with a pizza crust problem <\/span> for our chain of 10 restaurants, specific questions <\/span> to be answered include how big and bad <\/span> is the pizza crust problem, how widespread is it, <\/span> is the pizza crust problem equally bad across <\/span> all 10 restaurants, are some worse than others <\/span> or is it limited to just one restaurant? <\/span> Those are the types of questions you want answered <\/span> regarding the Y, which is the pizza crust. <\/span> That is how you plan for data collection <\/span> in the measure phase. <\/span> And the benefits to you are knowing exactly <\/span> what data to collect, how much data to collect, <\/span> from where and from whom. <\/span> By planning correctly, you’ll avoid common <\/span> pitfalls of spending too much time in the measure phase <\/span> going in circles, data hunting, and measuring <\/span> everything in sight. <\/span> A data collection plan will help you carry out <\/span> the measure phase effectively and efficiently. <\/span><\/p>\n

\n

Types of data and graphs<\/h3>\n
\n
\n

– Throughout this chapter, <\/span> we have been using the example of a pizza chain <\/span> with customer complaints about their crust. <\/span> Let’s return to our example <\/span> to help us understand the types of data and graphs used <\/span> in Six Sigma projects. <\/span> With a pizza crust problem, you would want to know <\/span> if the thickness of pizza crust is consistent <\/span> and how many complaints on pizza crust were received <\/span> by each of the 10 restaurants. <\/span> There are two types of data, continuous and discrete. <\/span> Knowing the type of data can help you determine <\/span> which graphs to use. <\/span> Continuous data is data that can take on any value <\/span> on a continuum or continuous scale, <\/span> such as inches or centimeters on a measuring tape, <\/span> or pounds or kilograms on a weighing scale. <\/span> Continuous data can be expressed as decimals or fractions, <\/span> such as 2.2 meters tall, <\/span> or weighing 175.6 pounds. <\/span> Discrete data is data that take on values <\/span> which are integers or whole numbers. <\/span> In other words, discrete values. <\/span> These are usually numbers that you can count. <\/span> Examples include number of complaints, <\/span> number of people in each checkout line, <\/span> the number of on time departures, <\/span> and the number of late departures for airlines. <\/span> Proportions can be calculated from these counts. <\/span> For example, the proportion of M&M’s that are green, <\/span> the proportion of flights that are on time. <\/span> Because of categories used such as color of M&M’s, <\/span> on time departure or not, <\/span> and store location A, B, or C, <\/span> discrete data is also called categorical data. <\/span> Categorical data is a more contemporary name <\/span> for discrete data. <\/span> Why is it important to know the type of data? <\/span> This is because it impacts the type of graphs <\/span> that can be used. <\/span> For continuous data, <\/span> graphs can be used to show variation. <\/span> For example, a curve showing the variation <\/span> in the thickness of pizza crust. <\/span> Graphs and charts commonly used in Six Sigma projects <\/span> for continuous data are histograms, dotplots, and boxplots. <\/span> These graphs display the pattern of variation, <\/span> showing how spread out the measurements are, <\/span> and where they are centered. <\/span> For example, here’s a histogram and a dotplot <\/span> showing delivery times. <\/span> The Six Sigma project team can see that <\/span> even though it averages 24 hours, <\/span> there is a lot of variation in delivery performance. <\/span> It can take as short as 15 hours <\/span> or as long as 31 hours. <\/span> For discrete or categorical data, <\/span> bar charts and Pareto charts are typically used <\/span> to contrast the frequency count in each category. <\/span> The Pareto chart is the most popular chart, <\/span> as it shows and prioritizes <\/span> based on how frequently each category occurs. <\/span> For example, here’s a Pareto chart <\/span> showing which complaint type occurs most frequently. <\/span> In this case, complaints on pizza crust stands out most, <\/span> accounting for 70% of all complaints. <\/span> Armed with this information, <\/span> the team can focus their project on pizza crust problems. <\/span> For both continuous and discrete data, <\/span> to show trends over time, <\/span> graphs such as line graphs, time-series charts, <\/span> and control charts are used. <\/span> This chart shows delivery performance over time. <\/span> Knowing which types of data and graphs to use <\/span> and how to (inaudible) them <\/span> will help you answer key questions during the Measure phase, <\/span> such as how big, how bad, <\/span> and how wide spread the problem is. <\/span><\/p>\n

\n

Measurement system analysis<\/h3>\n
\n
\n

– In the morning when I step on a bathroom scale, <\/span> I am x pounds. <\/span> When I visit a doctor’s office that same day, <\/span> the nurse weighs me and I end up <\/span> at more than x pounds, which weight is correct? <\/span> So which weighing scale should <\/span> I use as I train for the Olympics? <\/span> In this movie I will discuss the <\/span> importance of ensuring that data <\/span> is valid before using it. <\/span> In Six Sigma projects, this is done <\/span> using a technique called Measurement System Analysis, <\/span> or MSA for short. <\/span> MSA is done early during the measure phase <\/span> so that any data to be collected and used is valid. <\/span> The Measurement System includes the entire system <\/span> including the measuring instrument, <\/span> the operator, and the procedures used <\/span> to collect, measure, and record data. <\/span> To be valid, measurements should <\/span> be accurate with no bias, repeatable, and reproducible. <\/span> Let’s go back to my weight example. <\/span> To be accurate with no bias, <\/span> the bathroom scale should be centered <\/span> on zero when there is no one standing on it, <\/span> although the temptation is to offset it by negative two <\/span> so that I feel better that I’m two pound lighter. <\/span> In other words, the equipment should be calibrated. <\/span> To be repeatable means that if I <\/span> weigh myself twice, or even three times <\/span> on the same scale, I should get the same readings. <\/span> The measurement is said to be repeatable. <\/span> To be reproducible means that <\/span> my weight at home should be the <\/span> same as my weight in the doctor’s office. <\/span> If that is the case, the measurement is reproducible. <\/span> However, in my case, my weight measured by the nurse <\/span> is not the same as my weight at home <\/span> so the measurement was not reproducible. <\/span> When the measurement system analysis, <\/span> or MSA, is carried out, 20 to 25 <\/span> known items are selected and in a blind study, <\/span> each item is measured twice by <\/span> at least two operators. <\/span> Any inaccuracy, repeatability or reproducibility <\/span> problems with the measurement system <\/span> can be determined. <\/span> And if problems are corrected, <\/span> and the follow up MSA is carried out, <\/span> to verify that the measurement <\/span> system is good, and data collected is valid. <\/span> MSA has to be done before any data <\/span> is collected or used. <\/span> MSA is applicable to both types of data, <\/span> it is applicable for continuous data <\/span> such as weight or transaction time, <\/span> and it is also applicable to discreet <\/span> or categorical data such as the <\/span> classification of defects or complaints <\/span> into reason codes. <\/span> You need to perform a measurement <\/span> system analysis to ensure that data <\/span> is valid before it can be used, otherwise, <\/span> your project will be side tracked <\/span> chasing the wrong problem, analyzing incorrectly, <\/span> or drawing the wrong conclusions. <\/span> You definitely do not want to be a <\/span> victim of invalid data. <\/span> As the old saying goes, garbage in garbage out. <\/span><\/p>\n

\n

Process capability and sigma level<\/h3>\n
\n
\n

– Imagine, you own an online retail company <\/span> that promises delivery within three to four hours. <\/span> And average delivery time reported <\/span> for this month is 23 hours. <\/span> This is a second month that it is 23 hours. <\/span> And everyone in the company is celebrating, <\/span> because 23 is less than a 24-hour maximum. <\/span> But wait. <\/span> Why are there still so many complaints <\/span> regarding late deliveries? <\/span> Hmmm. <\/span> In this movie, I will discuss how to measure performance <\/span> in terms of process capability and Sigma level. <\/span> What is process capability? <\/span> Process capability refers to how capable <\/span> or how well the process performs <\/span> against it\u2019s target requirements or specifications. <\/span> Most of us have driven into garages <\/span> with height restrictions, <\/span> where there is a horizontal bar that hangs at the entrance. <\/span> Cars drive right in without slowing down, <\/span> because cars are not tall and are very capable <\/span> of meeting the maximum height allowed. <\/span> But big trucks or SUVs always slow down at that entrance, <\/span> just to make sure they don\u2019t hit that bar, <\/span> because many are not capable <\/span> of meeting the maximum height restriction. <\/span> Similarly with any process, <\/span> how capable is the process in meeting specifications? <\/span> In our delivery example, <\/span> if we plot performance for the past 100 days, <\/span> it looks like this. <\/span> Yes, the average or mean is 23 hours, <\/span> but there is a lot of variation around that 23-hour average. <\/span> So much so, that there are many deliveries <\/span> that exceeded the 24-hour limit. <\/span> That 24-hour limit is also called <\/span> the upper specification limit. <\/span> Why upper? <\/span> Because any delivery more than 24 hours <\/span> is considered defective performance. <\/span> From the graph, we can see why <\/span> there are so many complaints about late deliveries. <\/span> Now that there is an upper specification limit, <\/span> is there a lower specification limit? <\/span> No. Not in this case. <\/span> Since there is no requirement to not deliver it too early. <\/span> Notice, that 16% of deliveries are late. <\/span> We say that the defect rate is 16%. <\/span> So, 16% of the time, the company is not capable <\/span> of delivering on its 24-hour guarantee. <\/span> Looking at it from the other side, 84% of the time it can. <\/span> We say that the yield is 84%. <\/span> To express this in terms of Sigma level, <\/span> a Sigma conversion table can be used. <\/span> A 16% defect rate is approximately a <\/span> 2.5 Sigma level of performance. <\/span> There you have it. <\/span> Process capability. <\/span> In summary, process capability can be expressed <\/span> as a defect rate, a yield rate, or Sigma level. <\/span> In the measure phase, <\/span> a key benefit of measuring baseline performance <\/span> in terms of process capability, <\/span> is that it enables you to know just how often, how well, <\/span> or how badly performance meets specifications. <\/span> Specifications which you agreed and promised to customers. <\/span> Another benefit is that improvement results <\/span> at the end of the project can be measured <\/span> against this baseline to show just how much was improved. <\/span> We cannot improve what we don’t measure. <\/span><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

Steps in the Measure phase – The Measure phase is the second phase of a Six Sigma project. It is the M in DMAIC. Let’s start with a basic question. Why bother doing the Measure phase? What is the purpose? The Measure phase is to measure the size and scope of the problem or performance ..<\/p>\n

<\/div>\n

Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[42],"tags":[],"class_list":["post-1779","post","type-post","status-publish","format-standard","hentry","category-six-sigma-foundations"],"_links":{"self":[{"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=\/wp\/v2\/posts\/1779","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1779"}],"version-history":[{"count":1,"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=\/wp\/v2\/posts\/1779\/revisions"}],"predecessor-version":[{"id":1780,"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=\/wp\/v2\/posts\/1779\/revisions\/1780"}],"wp:attachment":[{"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1779"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1779"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wiki.thomasandsofia.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1779"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}