iSixSigma

boettler

Forum Replies Created

Forum Replies Created

Viewing 100 posts - 1 through 100 (of 105 total)
  • Author
    Posts
  • #187404

    boettler
    Member

    What is your principle?  Is it I am to brilliant to waste my time with lesser beings trying to teach me what I already know?  Look if the money for the MBB program is your ultimate aim and you can’t achieve it any other way than to sit through those classes than do it and get on with your life.

    0
    #62517

    boettler
    Member

    Pitch yourself as an indepent consultant (even if you’re working now), contact hospital department leads, and offer to do Lean Six Sigma work on a pro-bono (free) basis.  That’s how I broke into healthcare/hospital work 8 years ago. 

    0
    #57749

    boettler
    Member

    Hi,
    Can I suggest you start with a visual factory (scoreboard). In my experience, over a time period of around a month, performance will improve just by measuring data and throughput. It will also highlight variations between crews, shifts, operators etc. 5S is also an important tool as this can been driven through safety initiatives. Good luck.

    0
    #62230

    boettler
    Member

    Hi,
    There are quite a few OR efficiency studies on the web. Type in OR efficiency. Most have been theoretical, not six sigma standard.  I have heard of pathways projects in OR’s but would be keen to hear about your approach. I have always wanted to see a pareto of the key causes of delays in OR’s. This could point to where a project should be focused. Haven’t seen one yet.
    Good luck Rob

    0
    #57683

    boettler
    Member

    I am curious as to how these measures really affect throughput. In Australia, hospital sites use a OR utilisation measure and also a labour expended measure. Eg they start measuring the first operation from the time the Anasthetics team commences the first line of fluids (outside the OR) and completes the time at the time the patient leaves the room.
    Labour appears to be the more critical cost component rather than throughput. I am interested to see if anyone has comments on this.
    Rob

    0
    #178959

    boettler
    Member

    Great advice Dr Maass!  You appear to be the exact type of Professional MBB that folks need leading them.  Based on your advice, Vee will get the experience and then can decide based on his work /efforts, what he wants to do.  I appreciate your comments.
    ——————————-next—————————-
    Eric, I am currently in the Air Force and worked as the Program Manager for AFSO21 (Air Force Smart Operations) in Guam.  AFSO21 is the equivalent of a BB in industry; this is where I gained my interest in Lean Process Improvement / Sig Sigma.  By trade I am a Contracts Manager / Officer.  Can I contact you via email for some advice regarding LSS, I just recently completed Villanova’s LSSBB course and will take the certification exam next year. My initial desire was to take the Motorola University program, but could not attend the session live.
    My email is [email protected] or cell 240-603-4472.  Thanks in advance for any guidance.
    Best regards,
    Robert
     

    0
    #177171

    boettler
    Member

    Thanks George. I will alert the staff here at the nursing home so they allow me to use the computer.

    0
    #177168

    boettler
    Member

    Thanks George,
    I have been waiting 19 months for your answer and it finally came. Appreciate the feedback. Now, I can get on with my project.

    0
    #172230

    boettler
    Member

    Brandon, actually what she meant was $4K…(Your original post said your GB project was not successful….now you would have us believe it saved $4 million??? Your story is not making much sense.) However Nisha, how come all of a suddent you made $4K impact and earlier you mentioned that the project was screwed up?

    0
    #172060

    boettler
    Member

    look under six sigma lean 5’s

    0
    #165108

    boettler
    Member

    If the r square is less than 0.80 or between 0 – 0.80 your correlation could have an error greater than 20 %. In few words, the chances for your calculated values to match the real ones may be 1 in 5. However on natural systems r squares are found to be between 50 – 90 %. This is why it was suggested that you a simple student t evaluation and see if the sample size is large enough to give the degree of confidence that you want or seeking after.

    0
    #165100

    boettler
    Member

    A correlation having an r square less than 1 is already suspicious, especially when it is 70 %. May I offer a suggestion, do a calculation to see the minimum number of samples needed to get a 95 % degree of confidence (alpha = 0.05) and this will tell wherther 10 samples is enough to obtain a robust correlation. From a personal perspective, I don’t believe you do.

    0
    #164985

    boettler
    Member

    Tamlyn – thanks for the great answer! I really do appreciate it.

    0
    #164427

    boettler
    Member

    Brandon – you are entirely correct about inspecting in quality. The drivers for the fail test is if the product leaks then it won’t be shipped. The customers expectation is that they won’t get a product which leaks and they don’t. All products which leak are captured internally. This is the problem; no one really understand why they leak.I guess what I’m asking here is what tools and techniques can be used to define the CTQ’s, as you say, “identfying the causal factors for those failure modes”.How do I identify these causal factors? Brainstorming, Cause and Effect, etc.

    0
    #163897

    boettler
    Member

    Dr. Scott, didn’t you recently apologize for such useless posts? This is a Six Sigma forum, not an alcoholic forum.

    0
    #163714

    boettler
    Member

    email address is:
     
    tti dot lean at hotmail dot com
    Thanks for all your help.

    0
    #162428

    boettler
    Member

    You could check out this post on my blog:http://learnsigma.com/six-sigma-alcohol/Here’s a snippet:At Six Sigma Vineyards and Winery we combine the old-world art of making wine with the science of data-driven Six Sigma principles. To accomplish this, we have gathered a team of experts working with us towards a common goal: Making wine of an extraordinary quality at an affordable price.The data-driven principles of Six Sigma are employed, not only in the wine-making process as such, but in all stages of the process, for example when we:* Conduct extensive analyzes of soil, water and climate to find the most favorable sites for our vineyards.
    * Choose rootstocks that thrive best in the soil composition of a given vineyard.
    * Meticulously prune vines to enhance the quality of grapes and to allow consistent ripening.
    * Apply chemical and sensory analyzes to pick the grapes at just the right time to produce optimal flavor in the wine.
    * Listen to the voice of the customer – whether you are a sophisticated wine drinker with well-defined preferences, a social wine drinker who knows what you like and wants the security of consistency, or you just want a good place to start.Rob

    0
    #160105

    boettler
    Member

    Thanks for the advice – time to start clicking I think!Rob

    0
    #160104

    boettler
    Member

    Some great guidance – thanks for this!Rob

    0
    #61491

    boettler
    Member

    Any luck with the case study scenario?
    10 years of mortgage banking under my belt
    What’s in your background?
     

    0
    #154416

    boettler
    Member

    Thnx.

    0
    #153981

    boettler
    Member

    This explains why you were named “Allthingsidiot”.
     
    But thank you for making an attempt to reply to a genuine question.

    0
    #153976

    boettler
    Member

    I CAN’T BELIEVE THAT ALL THE SMART PEOPLE THAT POST ON THIS WEBSITE HAS NO ANSWER FOR MY QUESTION(S).
    MAY BE MIKE, STAN, DAN, BRIT ARE ALL ON VACATION FROM THE MILLIONS THEY EARN AS CONSULTANTS.

    0
    #153748

    boettler
    Member

    1) You should be free of special cause variation
    2) for Box-Cox the values must be positive.  This is not true for JT.
    3) Transforming the data should make sense.  If I am not mistaken, the transformations only modify data skewness.  If there is something else wrong or weird with the process, a transformation is not going to do it for you.

    0
    #153747

    boettler
    Member

    Infinity QS is excellent as well.
    They have the ability to include drawings and work instructions as part of the data collection or collect directly from the equipment.

    0
    #153746

    boettler
    Member

    Infinity QS is a very nice system as well. They the to

    0
    #153745

    boettler
    Member

    Infinity QS is a very nice system as well. They the

    0
    #153744

    boettler
    Member

    Infinity QS is a very nice system as well. They

    0
    #152554

    boettler
    Member

    Again thanks!
    I will try the options you’ve mentioned (I-MR, p-charts, c-charts) and see how the distributions we have look on those charts.  One difficulty we have is the large number of defect categories we track (>100 given different products).  So the distributions and value ranges look very different at times (as I mentioned in my previous message posted, our total defectives can range from 0.1% to 5%) and this can be a challenge in trying to find a single type of control chart to fit all.  But I will try your suggestions and then post how that goes so you’ll know.
    Thanks a million!

    0
    #152552

    boettler
    Member

    Thanks again for the replies!
    As far as the total number of defects per 100000 we typically get between 100 to 5000 defects or 0.1% to 5%.

    0
    #152309

    boettler
    Member

    Thank you again!
    Your assessment of why p-charts don’t work well is correct.  There are very low defect rates but extremely large N in my case.
    Regarding the I-MR option, wouldn’t the control limits in an I-MR chart assume normality?  If so, wouldn’t the limits be inaccurate given that the distributions are binomial?  That’s why I thought that using either box-cox transformations or non-parametric statistics would produce more accurate limits… please advise.

    0
    #149488

    boettler
    Member

    Thank you for the repsonse.
    I do understand this but the confusing thing is the performance. In real world situation it is possible to obtain data, say for a week,  on quality and availability, but not on the performance (time taken to validate a note).
    Could the OEE be used reliably with a constant value for performance (example: average accept time based on sampled data)
    I appologise if the questions seem silly, but I would like to clearly understand the application of the priciples for ticky equipment variables.
    Thanks
    Rob
     

    0
    #144999

    boettler
    Member

    Your project on transactional improvement is beneficial for blackbelt esp. if its an issue plaguing the site level. Implement the lean six sigma transactional tools to make this happen and provide more value.  

    0
    #144998

    boettler
    Member

    if it’s a non-normal data for process capability and you have chosen weibull, it will only show Ppk and its ok to use that information.

    0
    #144378

    boettler
    Member

    Need to have a Cpk for each because each is considered a defect opportunity.

    0
    #144375

    boettler
    Member

    Assuming process sequenceProcess A = 95% yieldProcess B = 90% yieldProcess C = 85% yieldRolled Throughput Yield is 0.95×0.90×0.85 = 0.73

    0
    #143336

    boettler
    Member

    I’m fairly new to the concept of Six Sigma, so my questions
    probably don’t hide that fact. VOC certainly helps to meet the needs of the consumer but
    innovation is also about creating need. Or finding new ways to
    meet the needs of customers/clients. From my limited experience with Six Sigma, I don’t know that our
    Black Belts were concerned with allowing for that kind of
    innovation. And while it may be a limited example, keeping things
    in a box where ultimate cost-cutting and pure efficency are the
    goal, does not seem to allow for the risk/failure process that true
    innovation demands.

    0
    #141746

    boettler
    Member

    you can use any of the attribute control chart (p, np, c, and u) BUT you need to segregate the charts for each location to effectively address the stability per site. if you want to compare the performance, just hypothesize. 

    0
    #58865

    boettler
    Member

    You can use a combination or any of the ffg. audit standard1. COPC2. BS7799

    0
    #141745

    boettler
    Member

    You can use a combination or any of the ffg. audit standard1. COPC2. BS7799This thread has been moved to the Financial Services discussion forum. Please click here to continue the discussion.

    0
    #141744

    boettler
    Member

    if it’s one unit at a time, why not focus first on DPU to make it more reasonable and less hybrid.

    0
    #141743

    boettler
    Member

    Try to have the ffg.:1. Boxplot – variability chart so that each appraiser will see their variation with others2. ANOVA – to see if the different readings are significant3. Post Hoc test – Tukey Kramer – to see who among the appraisers have the closest significant readings4. GRnR – to determine the gare repeatability and reproducibility and determine also the ndc (number of distinct categories)

    0
    #139799

    boettler
    Member

    Thanks for the info.  I will try the demo version.   

    0
    #138749

    boettler
    Member

    Thanks you.  I guess it time to take out the management science materials again! 
    Rob

    0
    #135253

    boettler
    Member

    Patti,
    The Navy has a program (LeanSigma) in place and is moving at a rapid pace.  If you like to dicuss please let me know – [email protected]
    Rob

    0
    #134250

    boettler
    Member

    We have a threshold for potential project savings in order to qualify an idea as a full 6 Sigma project.  If the idea has all the features of a 6 Sigma project but not a large enough value, we will then evaluate if we want to assign it to a Green Belt.   We refer to this as mini-projects.  A mini-project should be able to be wrapped up within 3 months or less.  If it will take longer than that, I would look to narrow the scope of the project.
    One method to arrive at a threashold of savings is to look at the return you are expecting from your 6 Sigma program as a whole.  Typical range is between 1-5% of gross sales(you need to decide how “bad” you are currently doing).  Divide this total by (number of Black Belts X number of projects you expect each BB to complete, somewhere between 3-5 projects for a fully trained BB).  While this method is less than exact, it is a place to start!
     

    0
    #133296

    boettler
    Member

    I am looking to improve communications in my organization as well. Please send me a copy. [email protected]
    Thanks,
    Rob

    0
    #64144

    boettler
    Member

    I was looking a trying to optimize our requirement gathering process in terms of speed and reducing rework.  Things I been looking at are extra functionality, extra reviews, defects caused by unclear requirements, and delays in requirements sign off.

    0
    #64073

    boettler
    Member

    Thanks for the info. 
    I was looking at using a standard peer review criteria for each review and having each criteria be used as a oppertunity.  Not sure this approach will work?????
    Any thoughts…..
    Rob
     

    0
    #64047

    boettler
    Member

    Thanks for the insight. 

    0
    #119078

    boettler
    Member

    Ron-
    I am not sure if you are still active in either SS or this site, if you are I would be interested in receiveing a copy of your PP on Turnover.  We are a small company (127) just starting our depolyment and have identified Turnover as our most urgent area of improvement.  I am sure your presentation would be helpful in getting our first project off on the “right” foot. 
    Thank you,
     
    Rob

    0
    #115248

    boettler
    Member

    Could you please forward a copy of template also.
    thx,
    Rob
    [email protected]

    0
    #109510

    boettler
    Member

    It has a boundary limit of 0.  I am also not sure of what the Goodness to Fit AD* value is representing.  I know that lower is better fit but what is it. 

    0
    #109501

    boettler
    Member

    Looking for a database with more report functionality built-in.  Access I do not believe fits this.

    0
    #109423

    boettler
    Member

    Cheryl:
    BMG doesn’t require corporate sponsorship.  I obtained my BB certification through them earlier this year.  Very comprehensive program and MBB instructors.  If you want to know about their program from a hands-on perspective, Email me directly ([email protected]). 

    0
    #109417

    boettler
    Member

    Breakthrough Management Group (http://www.bmgi.com) has strong Six Sigma e-Learning programs (BG, BB, MBB).  They are well-recongized in the industry.   Their ad is displayed in the top right hand corner of this page. 
    /rw

    0
    #60331

    boettler
    Member

    Ronald:
    Another few points in addition to my other posting in this forum:
    1) While clinical problems in healthcare perhaps are more exciting, don’t forget the claims processing, billing, etc. end of things.  Plenty of opportunities out there, and they don’t require RN licensure.
    2) I’m a firm believer in obtaining letters of recommendation from previous employers/clients.  Draft one for your recent work and provide it to your customer to edit and print on his/her company (hospital) letterhead.  Then include the letter as a scanned image on the last page of your MS Word resume that you float around.  It’ll distinguish you from all the “lemmings” out there.   This is a general technique that I would suggest to anyone out there job hunting.  The resume that I circulate actually has 2 letters of recommendation as scanned images on pages 3-4 of my resume.  I have continued my work a local, 150-bed hospital, but they can’t keep me busy full-time. 
    Hope these ideas are helpful.
    /rw

    0
    #60327

    boettler
    Member

    Ronald:
    Just to let you know you’re not alone.  I’ve been leading IT quality/performance improvement projects for years, but have wanted to get into healthcare.  In the last few year, I’ve been able to land two projects for the Laboratory Services department of a local, 140-bed hospital.   I too think building a network is the way to go, but I would encourage you to accelerate the process by marketing yourself directly to quality departments as a consultant.  I think it’s also helpful to formalize your experience on a web page that you can include links to showcase your work (e.g., http://rwillif.home.comcast.net/ss_examples.html) which is part of my larger web site: http://www.rwilliford.com.

    0
    #109049

    boettler
    Member

     “see how Tweedle D and Bush do tonight”  that’ll cool the rhetoric… 
     
    Here is a good perspective on the debate:
     http://www.chicagotribune.com/news/columnists/chi-0410130238oct13,1,4979512.column?coll=chi-news-hed

    0
    #107462

    boettler
    Member

    If you provide a little more information it might help you get meaningful responses.    

    0
    #106367

    boettler
    Member

    Matt,
    I have created a number of simple databases which the call centre populates using their monitoring forms.
    These forms contain numerous categories regarding the content / script path.
    Each of these are scored 1-3 or N/A (1 poor, 2 good, 3 excellent), the database calculates their performance by simply calculating the score they have acheived against the score they could have potentially acheived. eg. if the question was N/A then it’s potential rating of 3 would not be included in the calculation.
    Let me know if you want to go down a similar route and I’l be happy to assist / share examples of what I have done.
    If so desired, you could always comvert the percentage score to a sigma rating.
    Good luck
    Rob

    0
    #105536

    boettler
    Member

    Matt,
    With my scant practical knowledge, i would first ask what are you trying to acheive… are you trying to say that your operators are xsigma?
    What is the VOC.. being a call centre, surely you will have SLA’s by which you may be better off calculating a sigma rating for.
    In my experience, the measurement of individual operator performance is used for their appraisals, unless you are going to be telling them that their pay award depends on them scoring xsigma or better, I’m struggling to see what you would use this for.
    This is not criticizm, as I said above, I’m just learning too.

    0
    #104039

    boettler
    Member

    Have you looked at  “The Big Book of Business Games – John Newstron & Edward Scanell”.
     
    It has got Icebreakers, Creativity Exercises & Meeting Energizers – an easy to follow book that I have used several times.

    0
    #63537

    boettler
    Member

    Hi All,
     
    Much the same line of questioning as other individuals in the telco space – can someone please suggst the best approach for implementing Six Sigma into a telco involved in data, voice, cable tv, mobile, network development with multiple lines of business e.g. consumer and business

    0
    #101525

    boettler
    Member

    Jennifer,
    If it was that easy there would be no Six Sigma Black Belt training and mentoring from Master Black Belts needed.    Your manager either has a great deal of confidence in your ability to absorb knowledge and practicum through osmosis or he/she is a real dufuss, Black Belt or not.    I’m betting it’s dufuss.   I would suggest that you let your manager know that you would be glad to get Six Sigma training and work on the project during the course of the training.  Rob

    0
    #99943

    boettler
    Member

    Please find attached the failure rate for 5 vehicle lines vs cause for rejection.
    I have been ask to complete a Chi Square test on this data, and i am very unsure about how to complete this.

    Cause for Rejection

    Vehicle Type
    Split Tyre
    Seat Bolt
    Flat Tyre
    Bolt in Tread
    Damage / Worn
    Damaged Rim
    Damaged Wheel
    Puncture
    Damaged Side Wall
    Scratched Wheel
    Cut On Side Wall
     
    Total

    A
    1
    4
    1
    13
    0
    1
    5
    4
    0
    4
    1
     
    34

    B
    0
    0
    0
    0
    2
    0
    3
    3
    0
    3
    0
     
    11

    C
    0
    0
    0
    0
    0
    1
    0
    0
    0
    0
    0
     
    1

    D
    0
    0
    0
    12
    0
    0
    1
    10
    3
    0
    0
     
    26

    E
    0
    0
    0
    0
    0
    0
    1
    6
    0
    0
    0
     
    7

    Total
    1
    4
    1
    25
    2
    2
    10
    23
    3
    7
    1

    79
     
    Could somebody send me some details of how to complete the test. i am looking for the following answers for
    a) Do the vehicle types differ with regard to the proportions of failures within each category,
    b) Does the distribution of rejects differ from vehicle o vehicle.
    Regards
    Rob
     
     
     

    0
    #99867

    boettler
    Member

    I have also had this challenge on occassion.  If you can’t get the raw numbers to get a pure average, I have weighted the number.  It isn’t perfect but it will get you in the ball park as long as you don’t need 100% accurate numbers.  I have found that often times the ROI doesn’t support getting the raw numbers.
     

    0
    #99040

    boettler
    Member
    #97030

    boettler
    Member

    Thank you Gabriel.
    I undertstand what you mean, it will become more clear once i read over from page 135, it is the Manager who seems to be on the path as I described previously.
    Thanks for the help 

    0
    #97004

    boettler
    Member

    Thank you for the information, the attachement you have added to your e-mail, for some reason I can not open it, the command has been cancelled. according to the MSA manual 3rd edition for attribute studies,one can calculate the bias for attribute study pages a 125- 140. Once I am able to open your attachement hopefully, it will clarify the quaqtions i have and how to do it. Like I said the example in the MSa Manuel 3rd edition I find confusing.

    0
    #97002

    boettler
    Member

    I have got the 3 appraisers, the 8 samples length has been built where by the min is right at the bottom end of the tolerance spec ie 10000 mm and max is 1006.00 all others are nicely divided between 1000 and the 1006 mm length, therfore the tolerance band is 6 mm.
    According to the MSA 3rd edition each sample is to be checked 20 times, for a total of 160 measurments per appraiser since each  one that was checked to the tolerance band I made one osammple the min. sopec length alowed which is the one sample that the appraosers will question and another sample at the top end of the spec here again it is questionable all the other samples range in length which lay nicely within the 6 mm tolerance in the length of the samplethat meet the 6 mm tolerance. I have a total of 480 attribute results. How do I go about calculating the bias for the study. the example in the book i find very confusing. Is the bias reported to be between the appraisers or the bias of the entire study end results?
    The repeatablility, reproducibilty has been done using all 480 results. When I set up the study all 8 samples lengths are within the 6 mm tolerance length band. 
    The three appraisers I had one appraiser indicate 2 samples out and all others in . One sample at the min. end of the tolerance band and one at the max end, the appraiser indicated not ok when indeed the samples was in spec.
    appraiser two results they indicated one sample as being not ok this one was recorded as a not ok, when infact it was ok. this one was found on the min end of the spec of the tolerance band.
    Appraiser three had 2 questionable results indicated as “No ok”, here both the results they reported was for sample 1 of 8 that was on the min end of the tolerance band.
    help!!!!!!!!!!!

    0
    #96902

    boettler
    Member

    My shot at the solution
     
    Don’t overlook the obvious.  The correct answer was 6.  The spy shouldn’t have been wearing the armor of the enemy kingdom.  After all, the guard isn’t blind.

    0
    #96562

    boettler
    Member

    Thanks Dave for replying.
    The concept presented in the study as present by Matt and Joy I understand but how does one caluculate the BIAS from the data presented. I understand the study presented to be 20 samples appraisers 2 number of times each appraiser puts the samples through the attribute gage is once, find out the number of times the appraisers aggree between the tewo of them and then find the % where the appraisers aggree with the expert.  Cab I calculate bais? How?
    I have read over MSA 3rd edition a few times starting page 125 but I seem to be baffled.
     

    0
    #96097

    boettler
    Member

    Jason,
    You are correct.  Money is money and every company large and small have processes that can be improved.  Congratulations on your $1M project!

    0
    #96096

    boettler
    Member

    Julio,
    Have you looked at client comments or even Voice of the Business.  You will find valuable information which will lead you to a projects.  While the leadership should be involved in directing you to a project, if you are hitting a wall, hit the floor and ask for project suggestions.  I just finished a 10 month project that saved my company a little over $1M and the suggestion came from an entry level employee.  Some times, it takes a very simple view to find a great project.

    0
    #96095

    boettler
    Member

    I have been a Black Belt for 6 years now and completed a number of projects.  I have provided solutions for several companies and currently work for a small company.  I received my training/certification through Oriel and I also do training for staff members at my company however, I will not certify people as Green Belts.  While I am qualified to do so, I fear that there are too many people certifying and abusing training.  My certification took 18 months.  My question to you is do you feel comfortable in actually certifying Green Belts? 

    0
    #95863

    boettler
    Member

    I have implemented this at a number of clients with great success.  Its value is not in the tools – they are pretty vanilla – I typically rip these out and put in whatever my client is already using.  The real value is in the process guidance, ready access to the tool library, team collaboration, and exec dashboards.  This application differs from others out on the market in that there is value to the BB/GB and the project team, not just to the execs.
    You are right about the downloads – these are for the software which must be installed on an enterprise platform to work.  There are a couple options for you to “kick the tires”:
    – download the flash demo from the Microsoft site:  about 30 minutes of content complete with voice overlay and screen shots
    – get a Virtual PC demo image on a DVD:  this is basically the entire enterprise platform running in a self contained application that emulates the servers,etc.  It’s very slow, but fully functional.  Also, you need special software on your PC to run it (Microsoft Virtual PC).
    – get a one-on-one web demo from Microsoft
    You will definitely need to get IT and/or an implementation partner involved to deploy this.
    The Six Sigma Accelerator is “free”, but does require a number of other Microsoft products.  Typically companies already own most of the software from what I have seen …again, you’ll need to check with IT to see what you already own.
    Rob

    0
    #89026

    boettler
    Member

    Michael,
    I totally agree.  Several years ago, I worked on a project with a “marketing” group, which to Dr. Scott’s point was really a sales department.  In the end, we discovered that this sales group interpreted their efforts as marketing and in fact that was incorrect.  In adjusting and developing marketing functions within the over all process, we were able to increase sales which was our measure and replicate best practices of some of the sales people who actually did do some marketing.  Again, to Dr. Scott’s point, I think that many people confuse sales and marketing and you have defined the difference nicely.

    0
    #88739

    boettler
    Member

    Dave,
    Thanks for your input. We have included the cross functional people in our initial efforts, and many ideas have been generated as to what are the specific failures and what is causing them. The problem we have is getting agreement on the size/volume of our failure causes and the failures themselves, and how we should report them(should a failure mode or failure mode cause be reported as a “function”, etc). Fun
     

    0
    #88737

    boettler
    Member

    It will be difficult to track both, as the entry is not centralized so the training is difficult, and we need to submit the requirements before hand regarding what will be needed in the entry tools, etc. A good idea though, so will look into it.
    We will be using the data to determine bias, so an individual failure would not necessarily drive an action(unless it was very special). My plan was to do control charts on the number of corrective adjustments and the dollar of corrective adjustments, and have the appropriate data to do at least a two level pareto as needed. From there, we will use the data for improvement focus and benchmarking of our gains(I hope). The data will be lagging, so it’s not preventative, but we hope to use it to determine key upstream variables that we can report on and control to reduce impacts to the customer.

    0
    #63007

    boettler
    Member

    Linda…   Is your PMO embraced and championed by Sr. Exectutive?  If so,  you may have a good core group in the PMO that can successfully deploy Six Sigma.  If on the other hand, the PMO is ‘bottom up’, I suggest that the Six Sigma deployment be done as a separate entity.  If Six Sigma is not ‘top down’, I suggest you cancel it.

    0
    #87320

    boettler
    Member

    Brian,
    I may know of someone in the Atlanta area.  Have you found another forum to post this.  I’m not sure if Fred is correct or not as you are not looking for employment, but if he is, we don’t want to misuse this forum.  Please let me know.
    Rob

    0
    #86635

    boettler
    Member

    Nadia,
    As the others have said, your professor is off base and good for you doing a little in depth research.  You have hit on a topic that can have a profound impact on your study and on your professor’s view.  In the late 1990’s, GE started using six sigma in a non-maufacturing enviroment and they have been very successful at it.  As a matter of fact, we have seen a large number of banks using Six Sigma.  Today, we see Six Sigma being employed in contact centers, insurance companies and countless businesses.  We all use processes. 

    0
    #85807

    boettler
    Member

    I was dis-heartened when I saw the title of today’s article until I read it and realized that the author was being factitious. Thank goodness someone has a sense of humor!
    I really liked Daniel’s opinion. As a trained Black Belt with a couple handful of project under my belt, I feel discouraged when I run into traditional TQM professionals bad-mouthing Six Sigma. I haven’t been in the industry long enough to speak to them otherwise, but I’m glad someone has!
    RobA Bank Belt

    0
    #82781

    boettler
    Member

    You asked a pretty open ended question.  If the projects your Black and Green belts are working are focused on labor reduction, then those displaced will have to be dealt with.  My previous company had about a 20% attrition rate, so nobody was ever laid off.  That however is a decision your management will make.  Many people were displaced from jobs they had held for a long time or moved into different departments alltogether.  It was a significant emotional event for most.  The best way we came up with for dealing with this was to keep them informed of the project from the beginning, let them know their position would be eliminated so they could bid on other jobs, and keep them informed of the financial benefit associated with the project.  Rob

    0
    #81776

    boettler
    Member

    Jim,
    I am not questioning the 1.5 sigma shift.  What I am questioning is the idea of convoluting the standard normal distribution table to account for it. 
    I created my own z table in Excel and extended the z’s out to 6.  A z-score of 6 corresponds to about 1 defect per billion opportunities ( not 3.4 defects per million opportunities).  A z-score of 4.5 corresponds to about 3.4 defects per million opportunities.  In most six sigma calculators, a defect level of 3.4 DPMO will return a sigma level of 6 because it accounts for the 1.5 sigma shift between long term and short term data.
    Why wouldn’t you leave the standard normal distribution table as it is in every stat book we have ever seen and acknowledge the difference between short term and long term sigma with a qualifier based on the data you used.  For example,  if you used short term data to calculate your first pass yield then you would state that your process has a short term sigma level of x.  If you wanted to estimate your long term sigma level and first pass yield, you could then subtract 1.5 sigma and look up the corresponding yield in the standard normal table.
    I think the practitioners at Motorola took a fairly simple concept and complicated it for reasons that are still unclear to me.  Any thoughts?
     
     
     

    0
    #80948

    boettler
    Member

    Arthur,
    Thanks for response. Interesting perspective, but I think you’ve hit it right on the head—–it depends on the role that this person will play in the overall scheme.
    Rob

    0
    #80943

    boettler
    Member

    I’ve watched this discussion with interest. I’m a headhunter that specializes in Six Sigma positions. It’s wonderful to be able to get different perspectives on what’s important in a Black Belt’s qualities. Exept for 1 response, I didn’t see anybody else mention “Degree” in their lists.
    Do you think that a good Black Belt can work in any industry? If that person does not have a technical degree (i.e. Mech. Eng., Ind. Eng., etc.) can they adapt to manufacturing processes easily?
    Rob
     

    0
    #71568

    boettler
    Member

    I can see from some of the responses, it doesn’t take much to stir-up some of you guys. Before lambasting your companies, it might be worthwhile to step back and take a look at the projects your presenting (i.e. economics of company investment) and take a look at your “sales” approach to the company. If no insight comes to you, it might be time to bail out. Don’t give up on Six Sigma. As a Recruiter, I know that Good companies are always looking for good Black Belts——but these good companies don’t always buy-in to every project. There are some disappointments along the way.
    Rob

    0
    #70172

    boettler
    Member

    This is easier than most people realize…Get the financial function to include 6S savings (forecast vs actual) in monthly operating reviews.  The savings need to show up somewhere in the financials for them to be real and credible in the first place.  Considering the questions that most financial teams have about 6 Sigma savings, this adds an additional benefit of building additional credibility into the savings and requires more finance/accounting team members to enter into the discussion.

    0
    #68280

    boettler
    Member

    Zst is based on variability within subgroups while Zlt is based on the overall variability of the data, ignoring subgroups.  If you had rational subgroups and a stable process, then the within (short term) and overall (long term) variability would be the same, and mere chance would determine which was larger, Zst or Zlt.  So it’s possible that a negative Z shift is a symptom of a very stable process. 
    Or it may be a sign that you don’t have rational subgroups.  You may have an extra source of variability in your subgroups that is inflating your short term estimate of the standard deviation.  For an excellent treatment of rational subgroups, take a look at Don Wheeler’s books.
    Rob

    0
    #68128

    boettler
    Member

    KAM,
    If the data come from an exponentional distribution or something similar, the inverse is probably not the right transformation.  Values very close to zero will transform to very large numbers, making the result even more skewed.
    Rob

    0
    #68074

    boettler
    Member

    I think the main point that Wheeler and Chambers were trying to make is that one should not shy away from using control charts just becasue the data are not from a normal distribution.  And I agree with this.  But I would also argue that control charts work best for normal data, and if you can transform your data to make it normal, you should do so. 
    With normal data, you know what your false alarm rates are, and they tend to be pretty reasonable.  With other distributions, the control charts may be overly sensitive to the natural random variation in the data or not sensitive enough to shifts in the process.  For example, I tried out some random data in MINITAB using a chi-squared distribution with 2 degrees of freedom.  Both the X-bar and R charts flagged too many out of control points, especially the R chart.  Also, all the out of control points were on the high side, indicating that the lower control limit was too low to detect shifts in that direction.  This is typical of a skewed distribution.  Applying the Box-Cox transformation eliminated the problem.  As another example, look at the uniform distribution in the Wheeler and Chambers book.  Clearly you would be better off with narrower control limits.
    Rob

    0
    #62719

    boettler
    Member

    I would be very interested and appreciative if you could fax me a copy as well.
     
    Thank you,
    Rob
    (419) 325-0997

    0
    #68051

    boettler
    Member

    I would be very interested and appreciative if you could fax me a copy as well.
     
    Thank you,
    Rob
    (419) 325-0997

    0
    #67363

    boettler
    Member

    Terry,

    Your memory is right on. I looked in several statistics books and only one index listed Simpson’s paradox: “Mathematical Statistics” by Steven F. Arnold of Penn State University.

    Dr. Arnold gives an example in which two samples of 100 patients are taken and a different diet is given to each. The proportion of heart attacks for people on diet A are statistically less than the proportion on diet B. However, it turns out that the sample that got diet B had 75 smokers, while the sample that got diet A had only 25 smokers. In the example, diet B was better for both the smokers and non-smokers separately. The only reason diet A looked better was that the occurence of heart attacks was much higher among smokers than non-smokers, and the paradoxical result was due to over-representation of smokers on diet A.

    He describes Simpson’s paradox in general as “the phenomenon…wherein the mean of sample A can be lower than the mean of sample B for each of two subpopulations and still be higher for the whole population.” He also points out that “Simpson’s paradox can occur for continuous data as well as discrete data.”

    By the way, he points out that it would be extremely unlikely to get such an imbalance of smokers in a truly random sample.

    Rob

    0
    #66927

    boettler
    Member

    Alexander,

    The sample standard deviation is the correct estimate of the population standard deviation. The sample standard deviation divided by the square root of the sample size is the estimate of the standard deviation (a.k.a. the standard error) of the sample mean.

    Rob

    0
    #66854

    boettler
    Member

    Hi Tyler,

    A distribution does not have to be normal in order to be stable or in control. It just has to have a consistent pattern of variation. Some processes tend to have normal type distributions, whereas others do not. Also, as you improve the process, the pattern of variation may change shape. It sounds like this is what you have encountered in your projects.

    Rob

    0
    #66734

    boettler
    Member

    Green Belt training gives the team members the tools they need to attack the problem. The team member should understand the Quality tools and the team building tools before he is asked to be on ateam. For teams to work at their peak, the team has to be prepared from the beginning of the project. Time is so valuable when it comes to project team time. Teams get bogged down early when they have only one process expert (Black Belt)and the team is made up of all subject matter experts. A Black Belt struggles to keep the team focused on the process and still lead the team through the subject matter when solving problems that do not have easy solutions. Many different agendas are present during any early meeting and the team has only one try to get through each of those mine fields. Each team member must also sell the solution that is arrived at so he must have training in selling Change. He may have to work with other groups away from the team also. The team will build confidence in their solutions faster if they can function as a team and not as a group of agendas being manipulated by an outsider (Black Belt).

    0
    #66503

    boettler
    Member

    I could probably answer a question about time series plots. Also Minitab has a great customer support team who could help you. For contact info, check out the Minitab web site:

    http://www.minitab.com/contacts/contact.asp

    Rob

    0
Viewing 100 posts - 1 through 100 (of 105 total)