iSixSigma

Russell

Activity

  • Russell replied to the topic Are percentages continuous data? in the forum General 13 years ago

    Percentages are not continuous however are often considered in that format. Try this to get an indication of what happens when you ‘normalize’ the data,  Make a set of normal data – say 100 data points – of defects with opportunities. This would be similiar to the count data that you have – then covert it to a percentage. Now run a 1 sample t…[Read more]

  • Russell replied to the topic Hypothesis testing in the forum General 14 years, 8 months ago

    Right on target, the key is to draw a line in the sand and determine your defect range. You have done that so it all makes good logical sense.

  • The advice is sound and accurate.
    Just something to note is that if you go back and look at the data in a grahical format (distribution) it will be skewed. This is ‘normal’ for data that has a boundary / target of 0.
    Do not expect to see a standard bell curve for the data distribution.

  • Russell replied to the topic Time/Work Study in the forum General 17 years, 5 months ago

    Sean
    I would like to be included when you send it out.
    Thanks in advance!
    Russell

  • Web based training is available from a lot of places – you should also look into what support structure is also available. As far as the ASQ test and certification as a ASQ SSBB – give it a rest. One person that was involved in  the Ford 8D as a Master Trainer did not have any use for SS four years ago. He has never been trained in SS, never did…[Read more]

  • Russell replied to the topic Cycle Time Reduction in the forum General 19 years, 3 months ago

    Stan:
    Total Agreement. The use of simulators is great but only as good as the input that you put into the program. I use simulators both in projects and training but not until the improvement phase of a DMAIC  project. It is used earlier in DFSS projects but that is another route and not one that you sound like you are using. 
    Get the team m…[Read more]

  • Russell replied to the topic Design Of Experiments in the forum General 19 years, 3 months ago

    If you have Minitab version 13 or higher (I believe 14 is just about to be released) then you can specify which factors you want. Generate the spreadsheet and if the factors that you want are not the ones listed for interactions tudy you can change the factor names easily. I would also investigate the correlation levels between the factors and l…[Read more]

  • Russell replied to the topic Design Of Experiments in the forum General 19 years, 3 months ago

    If you use a statistical package such as Minitab it will generate the DOE spreadsheet for you. (This is the easiest way to determine which interactions will be confounded). By running the DOE at res IV / 32 runs you can have most two way interactions freed of confounding. Without knowing the process that is being DOE’ed it is difficult to…[Read more]

  • Please:  I have met a few of the ‘certified’ BB and MBB’s that were ‘trained’ through on line e-distance programs. If you get the opportunity to do so ask them about team work, DOE, mentoring experiences, etc.
    Their exposure to people that have practiced and had successful projects has been limited (basically non-existent) and their project…[Read more]

  • Please:  I have met a few of the ‘certified’ BB and MBB’s that were ‘trained’ through on line e-distance programs. If you get the opportunity to do so ask them about team work, DOE, mentoring experiences, etc.
    Their exposure to people that have practiced and had successful projects has been limited (basically non-existent) and their project…[Read more]

  • Total agreement with you Mike. Our company has a policy that no project (SS / Lean) will result in emp[loyee dismisssal. Use the program to prevent future hiring or to allow for attrition (retirement) to have no impact BUT if you were to fired because someone else ran a project that showed how to eliminate a BB – what would be your response and…[Read more]

  • The program that we implemented in 1998 had the same issues that you are facing. The proposal that we accepted was that the BB’s after certification received the base rate + 10%. Additional bonuses are dependant on success rates in projects.

  • I have had to perform DOE using attribute response for refrigeration systems leaks (defects). The response measured was leak / no leak. Since any leak would result in a defective product to the customer there was no allowance for  transforming the data top variable, including the application of a Likert…[Read more]

  • Terry:If you would like to send me your email address I can discuss with you the plus / minus of Six Sigma deployment in a smaller company. I work for one of the companies that Mile Carnell has listed – he works with the consultant company that provided our initial training.My e,mail is [email protected]

  • Russell replied to the topic Negative Sigma in the forum General 20 years, 7 months ago

    I agree with you. When calculating sigma levels in Excel if the defect rate is high enough I have had a negative sigma score. I guess the real issue may be that if a process is bad enough to generate a negative sigma why is in existence??

  • Russell replied to the topic six sigma is crap in the forum General 20 years, 7 months ago

    My, my – do I detect the tone of someone who did not get selected in the deployment of a Six Sigma Program?
    I was one of those people that used to develop solutions to problems in 5 heartbeats (or less)- on the same problems every week. Why – because for the majority of issues a band aid can be applied for that time BUT you need to identify and…[Read more]

  • Russell replied to the topic measureable quality in the forum General 20 years, 8 months ago

    COPQ = Cost Of Poor Quality
    What is the cost of the defect or process inefficiencies – includes items that ar easily, and sonetimes not so easily, quantifiable such as repair costs, service costs, warranty costs, customer dissatisfaction.
    Hard dollars are normally easy to calculate – it is the soft dollars that make COPOQ more difficult – can…[Read more]

  • Russell replied to the topic measureable quality in the forum General 20 years, 8 months ago

    Ken:I believe that I may have expressed the information incorrectly.Look at the metrics this way – I made 1000000 units with 1000 bad = 1000 PPM = $100000. This makes the cost of PPM defect $100.
    Project resulted in 65% defect reduction (1000 to 350 bad) = 3500 PPM. Based on original PPM COPQ the process should have moved to $35000 COPQ, however,…[Read more]

  • Do you feel that Six Sigma has made a difference?
    Yes – enough said.
    Is it really the methodology or is it the manipulation of the numbers through the software?
    The answer to that is dependant upon a number of factors – the quality of the BB, the ethics of the person or company. I like to use the expression – figures can lie and liars can…[Read more]

  • Russell replied to the topic measureable quality in the forum General 20 years, 8 months ago

    No offense to Ken but hard (or soft) dollars is not the best way for quantitative measurements for a successful project. If your management group has had experience / training / education in the Six Sigma methodology or a quality engineering trained group, then they will understand and appreciate the true benefit of the reduced PPM or improved…[Read more]