iSixSigma

Tony Burns

Forum Replies Created

Forum Replies Created

Viewing 36 posts - 1 through 36 (of 36 total)
  • Author
    Posts
  • #90481

    Tony Burns
    Member

    Dear Stan,
    [email protected] ” as displayed in my recent messages, is my e-mail address, not a web site address. It would be polite for you to display yours.
    You are entitled to your opinion about e-learning. Hundreds of thousands of people would disagree with you.
    Dr Tony Burns
    [email protected]

    0
    #90451

    Tony Burns
    Member

    The author is Dr Donald Wheeler. SPC Press.
    It’s very thorough and great reading.
    Dr Tony Burns
    [email protected]

    0
    #90449

    Tony Burns
    Member

    Your dilemma is a common one in large corporations. It is compounded by issues of ensuring training consistency; costs, including travel and accommodation; employee off-the-job time; and training management. Have you considered e-learning ? If you are interested, I can arrange for you to speak to people in a similar situation to yourself, who have taken this path.
    Dr Tony Burns
    [email protected]

    0
    #90448

    Tony Burns
    Member

    Normality cannot be assumed for any distribution. There are a variety of ways to estimate dispersion, described in detail in Chapter 3 “Advanced Topics in SPC”. Looking at the extreme tail of a distribution is not one of the methods listed. The tail is a very poor indicator of the shape of the dog.
    Dr Tony Burns
    [email protected]

    0
    #90411

    Tony Burns
    Member

    MMB,
    I would assume your comments apply to a particular e-learning product with which you have had experience. Making general statements is like saying “green belts can’t learn from books”. Certainly, green belts might find “Advanced Topics in SPC” rather intimidating but there is much material designed to suit every level.
    I have seen e-learning to be extremely effective with folk below leadership level. In fact this is where e-learning can do what it does do best, in providing training to thousands of people in a consistent manner. When well designed with games, exercises and a high level interactivity, it can also be much more motivating than a blackboard.
    It is a far more cost effective way to train than the classroom. It allows people’s spare time to be used, rather than taking them off the job. Students can work at their own pace.
    Most importantly, it relieves teachers to focus on what they should be doing. Teachers should help apply the knowledge, rather than simply repeating the same material over and over to different groups.
    Nothing is a panacea, but e-learning is an important complement to other forms of training and experience.
    If you would like to email me, I can send you volumes of evidence of the success of e-learning at all levels in many organisations.
    Dr Tony Burns
    [email protected]

    0
    #90406

    Tony Burns
    Member

    Dear Susan,
    I’ve been involved in this area for the past 14 years. If you’d like to email me I can help you with some articles and other information.
    Dr Tony Burns
    [email protected]
     

    0
    #90334

    Tony Burns
    Member

    Reigle,
    It’s great to see that you follow the Wheeler “bible”. It is a wonderful book that everyone on the forum should read and study. The chapters I referred to discuss control charts in great detail and the difference between “short term” variation within groups and “long term” variation. For Wheeler’s view on six sigma, you have to go to page 202:
    ” Failure to operate a process on target with minimum variance will inevitably result in dramatic increases in the Average Loss Per Unit of Production. Such losses may be severe and are always unnecessary.
    …Six-Sigma Quality and all other specification-based nostrums miss this point. … The sooner one wakes up to this fact of life, the sooner one can begin to compete.”
    And in a personal correspondence from him:
    “The only antidote to ignorance is education.  My most effective antidote is known as Understanding Variation, the Key to Managing Chaos.”
    Dr Tony Burns
    [email protected]

    0
    #90327

    Tony Burns
    Member

    Ricardo,
    Exactly what are you measuring or counting? What is the process?
    Dr Tony Burns
    http://www.q-skills.com/sixsigmatraining.htm
    [email protected]
     

    0
    #90325

    Tony Burns
    Member

    Reigle,Your note focusses on the differences between “short term” and “long term” variances:”…After an extended period of sampling we can use one-way anova to compute the “within set” variation and the total variation. This gives us the sums of squares within sets (short-term) and the total sums of squares (long-term). …”This is precisely what the range chart of a control chart does ! Range control charts compare the variation within groups (short term) to the variation between all the groups (long term). The +/- 1.5 theory confuses the differences in variances with means. I suggest reading Wheeler “Advanced Topics in SPC” Chapters 4 and 6 for a detailed understanding.It would be extraordinary if we could do some theoretical calculations that would force our process means to drift, despite our best efforts to keep processes on target with minimum variation !Dr Tony [email protected]

    0
    #90264

    Tony Burns
    Member

    Rare events may be plotted on an XmR chart using the event rate (inverse time between events). The events on the chart, should relate to a similar cause. If possible, it is always preferable to take measurements and plot the variable on a control chart, rather than counting rejects.Dr Tony Burns

    0
    #90252

    Tony Burns
    Member

    Joyce,What is your process? What are you measuring?Dr Tony Burns

    0
    #90222

    Tony Burns
    Member

    Dr Scott,
    You said: “There is not such animal as long or short term or a 1.5 sigma shift.”
    There is indeed such an animal. He was a horse called “Clever Hans” and he was part of what is known as the Pygmalion Effect or the self-fulfilling prophesy. If you expect the mean to shift, it eventually will if nothing is done to manage the process … and of course it won’t find any reason to stop at 1.5 sigma. That is one of the reason for quality programs, to keep processes on target. Dr Scott, it’s good to see someone being able to see through the nonsense.
    Six sigma programs can bring great benefits to companies, because at last there is commitment to quality from senior management. At the same time, it is important to view all information critically.
    Dr Tony Burns
    [email protected]

    0
    #90220

    Tony Burns
    Member

    Dear Weipeng,
    I can’t agree more that if you win the hearts, the minds will follow … and using games is the perfect way to do that.
    This forum doesn’t allow advertisements but if you email me at [email protected]  I will direct you to something that should suit your needs.
    Dr Tony Burns

    0
    #90210

    Tony Burns
    Member

    Michael,
    You stated:
    For example consider these 2 processes; which one is more stable?

    process1   m = 10,  s = 5
    process2   m =  5,   s = 3
    Standard deviation, “s” is a measure of dispersion. It is not a measure of stability. To determine the relative stability of the processes you need a control chart for each.
    Dr Tony Burns
    [email protected]
    http://www.q-skills.com/sixsigmatraining.htm

    0
    #90170

    Tony Burns
    Member

    John,
    Would you mind posting your document as an RTF please. My virus checker detected a malicious script. DOC’s can have attached viruses. RTF’s can’t.
    Thanks,
    Dr Tony Burns
    http://www.q-skills.com/sixsigmatraining.htm

    0
    #90162

    Tony Burns
    Member

    “3” is used when there is a single spec limit.
    Dr Tony Burns
    http://www.q-skills.com/sixsigmatraining.htm
    [email protected]

    0
    #90128

    Tony Burns
    Member

    Trends are one of the 4 detection rules in the Western Electric Handbook. They are indicators that a process may be about to produce out of spec product (even if spec limits have been set at 6 sigma ! ).
    Shewhart only used Rule 1 : Lack of control is indicated when a point falls outside outside a control limit.
    Wheeler recommends Rule 1. He suggests Rule 4 may be added when personnel become more sophisticated. (Rule 4: A lack of control is indicated when 8 successive points fall on the same side of the center line.)
    I had a look for your critique of the claimed +/-1.5 sigma but could not locate it. Was it on the forum?
    Regards,
    Dr Tony Burns
    [email protected]
    http://www.q-skills.com/sixsigmatraining.htm

    0
    #90122

    Tony Burns
    Member

    Why not go to the core? Read Wheeler, then collect the papers by Taylor, Evans, Bender etc and write a critique.
    Dr Tony Burns
    [email protected]kills.com

    0
    #90120

    Tony Burns
    Member

    Katherine,
    There was an earlier thread on call centres. I pointed out that the distribution of call times is a good example of a strongly non-normal distribution. (Six sigma focuses on normal distributions).
    Dr Tony Burns
    [email protected]

    0
    #90119

    Tony Burns
    Member

    We are not in a world of zero defects. Low defect rates are only possible when a process is behaving predictably. A process that is in statistical control is operating as consistently as it can. A process that is not in control, is in a state of chaos and there is nothing that can be done to prevent defects.
    Our focus should be on bringing process to a state of statistical control.
    Dr Tony Burns
    http://www.q-skills.com
    [email protected]
     

    0
    #90118

    Tony Burns
    Member

    Yes, I agree “PS Zero defects is very easy to measure”. You may recall it’s a process called “Quality Assurance”. I understand that Quality Assurance was initially introduced in World War II when munitions were inspected and tested for defects after they were made. This was superceded by methodologies focussing on reducing variation in processes. Back to the future !
    Dr Tony Burns
    [email protected]

    0
    #90110

    Tony Burns
    Member

    John,
    Your name rings a bell … do I know you?
    In relation to trends, it’s worth reading Wheeler “Advanced Topics in SPC” page 136 to 137. Despite the usually taught stuff on trends, Wheeler suggests they add to false alarms and that it’s better to rely on the limits. Forget about constant corrections … fiddling with the controls is what operators commonly do … it doesn’t help. If your mean is shifting by 1.5 sigma or anything else, your process is out of control. Look for causes.
    Best regards,
    Dr Tony Burns
    [email protected]
    http://www.q-skills.com
     

    0
    #90068

    Tony Burns
    Member

    You asked: “What does “minimum variation” really mean? ” in relation to my statement that:
    World Class Quality = On Target with Minimum Variation.
    In relation to variable data, good quality means much more than zero defects or fewer defects. A defect occurs when a product is outside specification limits. The number of defects depends on where the specification limits have been set. I have read statements by consultants boasting how they reduced defects in companies. This is easy, just change the spec !
    Reducing variation is more difficult. It involves working on special then common causes. Only by focussing on variation and keeping the product on target, can the process be improved.
    Dr Tony Burns
    [email protected]
    http://www.q-skills.com/sixsigmatraining.htm

    0
    #90067

    Tony Burns
    Member

    Lazarus,
    I recall a very similar project, looking at the effects of lighting on productivity. Lighting was improved, productivity went up. Lighting levels were increased again, productivity went up further. Again lighting was improved and again productivity went up. Out of curiosity, the lighting levels were decreased – productivity went up again !
    The employees felt that they were being attended to and cared for.
    … and sorry, I can’t recall the source …
    Dr Tony Burns
    [email protected]
    http://www.q-skills.com
     

    0
    #90065

    Tony Burns
    Member

    Dicky,
    Could you describe your problem in detail please.
    Thanks,
    Tony
    [email protected]
    http://www.q-skills.com

    0
    #90064

    Tony Burns
    Member

    Avatar,
    You are on the right track, looking at controlling variation.
    A problem with your suggestion is “then define how much I will allow the process to deviate”. You can specify a specification limit but the process will do it’s own thing. If the specification limit lies within control limits, you will produce defects. If your process is not in control, you may produce defects.
    If your interested in control chart alternatives, read Ch 4 and Ch 10 in Wheeler’s “Advanced Topics in SPC”. He provides a very detailed analysis.
    Dr Tony Burns
    [email protected]
    http://www.q-skills.com

    0
    #90062

    Tony Burns
    Member

    Dear Kniles,
    1. We do NOT “set” control limits as you suggest ! Control limits are calculated from process data. Control charts are “The Voice of the Process”. They tell us what is happening in our processes.
    The only setting of limits that can be done is with specification limits. Specification limits are “The Voice of the Customer”. They are what the customer has specified. Hopefully, they reflect the customer’s needs and not something that we want to impose on long suffering customers, in order to reduce our costs.
    2. It does not surprise me that you have processes with drifting means, that are “questing entropy”. This is a common situation. This is (hopefully) the reason that companies introduce quality programs in the first place !  Processes should be managed rather than being victims of chaos.
    3. You suggest “…the effort it would take to understand and manage all the control variables “. Control charts are not an academic exercise. The very purpose of control charting is to gain insight into the process ! It is for this reason that it does not matter that a process does not have to be brought into control before calculating limits, nor does it matter if data is autocorrelated. The aim is insight so that we can work on reducing variation. If we wish to sit back and let “noise based natural occurrence” take control, we might as well go back to the bad old days of Process Control and simply count defects at the end of the line and rework them or throw them away.
    It is worth emphasising the often forgotten basic:
    World Class Quality = On Target with Minimum Variation.
    I strongly suggest reading Wheeler “Understanding SPC”
    Dr Tony Burns
    [email protected]
    http://www.q-skills.com

    0
    #89998

    Tony Burns
    Member

    If we put aside the controversial origins of the +/- 1.5 sigma shift in the mean, any drift in the mean will cause points to fall outside control limits. A shift of 1.5 sigma will cause about 7% of points (depending on the shape of the distribution) to fall outside a control limit. Not something that would please customers! If every process has a +/- 1.5 sigma shift in the mean over time, can no process ever be “in-control” and therefore predictable ?
    Shifts in means do occur in processes such with tool wear, as described in the original six sigma papers by Bender, Taylor etc on tolerancing. The amount the mean changes depends on the amount the tool wears before adjustment. Shifts in means hopefully (or by good quality management) do not occur in the myriad of continuous process that are more common.
    Dr Tony Burns
    a_bur[email protected]
     

    0
    #89982

    Tony Burns
    Member

    Mike,
    If the mean of a continuous process starts to drift, points will start to fall outside control limits. The process will no longer be “in-control”. It will become unpredictable and incapable of producing product that is within specification. If a process mean drifts to +/- 1.5 sigma, the process is well “out of control”. That is why control chart software does not allow for, or ignore, drifting means.
    Dr Tony Burns
    [email protected]

    0
    #89980

    Tony Burns
    Member

    Mike,
    A great post ! Good to see a pragmatist !!
    Dr Tony Burns
    [email protected]

    0
    #89936

    Tony Burns
    Member

    Dear Elena,
    Yes, we have plenty of data, as well as more importantly, examples of the outcomes in business from application of the learning. We can also arrange for you to speak to some of our clients if you are planning in going down the e-learning path.
    I think it is also important to appreciate that no one approach is a panacea. Individuals respond differently to different approaches. The best approach is a combination.  I feel that it is a waste of trainers’ abilities to have them repeatedly present exactly the same information to different groups of people. Computers are much more efficient than people at doing the same thing over and over. What e-learning can do best, is to cover the basic ground in the most efficient and motivating manner (if it is well designed of course). I recall a waiter serving drinks at an exhibition being curious about one of our e-learning games … he ended up sitting down and getting involved. If a waiter can be motivated to learn so readily, imagine what it can do for employees. E-learning releases trainers to focus on the stuff they should be doing, such as explaining the more difficult concepts in detail to individuals, or helping people apply the knowledge in actual projects. This approach helps address the problem you describe, with people finishing classroom courses and entering a vacuum. 
    [email protected]
    Dr Tony Burns
     

    0
    #89887

    Tony Burns
    Member

    Prior to six sigma, PDCA (Plan, Do, Check, Act) was the core quality implementation methodology, however almost every major company had their own variants of this. A good thing about six sigma is that most companies have now standardised on the DMAIC variant. I suspect that all these date way back to the “scientific method”, what I might call the IDTC:Induction of hypotheses based on observation (That is, the formulation of generalisations based on a limited number fo specific events)Deduction of the implications of the hypotheses (The reverse of induction. Arriving at specific conclusions based on generalisations)Testing the implicationsConfirmation or Disconfirmation of the hypotheses

    0
    #89884

    Tony Burns
    Member

    As Michael says, the benefits of e-learning have been well documented: reduced training time and costs; more consistency; people learn at their own pace; easy management; no travel costs: train anywhere, any time.
    However, Michael’s comment that “some people may get bored” cannot be underestimated. This is e-learning’s single greatest problem. I have looked at hundreds of e-learning programs in different fields and it is almost universally page turning stuff … text, pictures and maybe a video or two thrown in. People can read 30% faster on paper than on a screen. There must be a major benefit to justify putting material on a screen, rather than keeping it simple and using paper and/or the classroom.
    There has been a major upsurge in e-learning in recent years. However, people have been driven by technology rather than content. E-learning is no different to CBT (computer based training), except for the delivery mechanism. The lessons of CBT have been forgotten.
    I have specialised in this area for the past 14 years. My company developed an e-learning product for six sigma with the lessons of the past in mind. I believe that the key is that learning should be FUN … through games and interactive exercises. If people don’t enjoy it, they won’t use it !! I won’t bore you with a product promo.
    Elena’s question “Who can share with me your experiences” can be answered with the dozens of client testimonals on our web site.
    Dr Tony Burns
    http://www.q-skills.com
    [email protected]
     

    0
    #89845

    Tony Burns
    Member

    Alok,
    Neither is correct.
    Individuals chart (median moving range):
    UCL = Mean + 3.145 * R tilda
    Individuals chart (average moving range – more common):
    UCL = Mean + 2.66 * R bar
    The “3” in your formula probably comes from 3 * R bar/d2, or perhaps “3 sigma” control limits, upon which control charts are based.
    It’s interesting to note that Wheeler calls them Natural Process Limits for individuals and Control Limits for subgroups with variables, although he uses Control Limits when individuals charts are used for counts. Other authors keep it simple with Control Limits.
    Don’t forget the LCL and the range chart … and don’t use sigma values calculated by reading off a corrected normal distribution for a six sigma program ! 
    Dr Tony Burns
    [email protected]
     

    0
    #89844

    Tony Burns
    Member

    Ken,
    The requirement you have described in your latest post “…The SLA they want to set is 80% of calls answered in 90 seconds” is different to your original post: “80% of my calls in an average of 90 seconds”. This post implies no calls longer than 90 seconds, whereas that is not the case with an average, as described in your first post.
    The first step in any problem solving task is to make sure you understand the problem.
    Dr Tony Burns
    [email protected]
    http://www.q-skills.com

    0
    #89833

    Tony Burns
    Member

    Ken,
    Firstly forget about normal distributions. Time to answer calls is almost certainly going to be a quite assymetric distribution, with a long tail on one side and steep on the other. Fortunately this does not matter for control charts.
    Where does your requirement for 80% of calls in an average of 90 seconds come from? Is this your personal choice? Which call data is to be eliminated in calculating the “80% with an average” ? … the high values ? Why ? Do you have any existing data on response times? If you have any existing response time vs time of days data, I would suggest plotting it on an XmR chart to gain insight into the process. A histogram may give further insight. This may indicate directions for further data collection and possible subgrouping, in order to target areas for improvement.
    Best regards,
    Dr Tony Burns
    [email protected]
     

    0
Viewing 36 posts - 1 through 36 (of 36 total)