iSixSigma

Urgently need help regarding DOE and ANOVA

Six Sigma – iSixSigma Forums Old Forums General Urgently need help regarding DOE and ANOVA

Viewing 5 posts - 1 through 5 (of 5 total)
  • Author
    Posts
  • #52606

    Moin
    Participant

    Hi,
    I am doing my final year project on utilizing six sigma to reduce the rejections and rework, the scope of my project is concerned with attribute data (number of circuit defects in the wire harness of a car, number of taping defects in the wire harness etc.) . I am asked by my project advisor to use ANOVA for this project in the analyze phase of the DMAIC and Design of Experiments (DOE) in the Improve phase. i have no idea how to do that for attribute data. Also i only have 15-25 more days to wind up my project. I also want to know that is it necessary to use ANOVA and DOE in the DMAIC philosophy? Are there any other techniques that can be used or is it necessary that they must be included for a successful six sigma project?
    I shall be very thankful to u if u help me regarding this issue. Any books, reference materials etc. will be a great helpThank You
    Moin

    0
    #185196

    Anand Paropkari
    Participant

    The nature of data really mandates one or other tool and NOT Six Sigma methodology as such. According to your query you rather collecting variable data (no. of ….).
    Use ANOVA if you can’t confidently identify the root cause(s) by other methods.

    0
    #185234

    mcintosh
    Participant

    Moin,Your first question cannot be answered without knowing more about the data. Is X discrete or continuous? How many defects are possible? If Y is attribute data then it is discrete, and you would normally do some other test, such as chi-squared. However, defect data often has enough possible levels that it can be treated as continuous, in which case an ANOVA might work. Another approach would be to perform an ANOM using a Poisson distribution (if you have access to Minitab, this is offered as one of the options).To answer your second question: no, DOE and ANOVA are not, generally, required elements of Six Sigma. You use the tools that make sense for the data. What is important is that you understand the factors that need to be controlled, and that you have the data and analysis to support the investment in process changes. The key questions you have to answer are “how do you know I should make these changes” and “show me the data.” If the answer to the first is not some variant of a hypothesis test (ANOVA, chi-squared test, etc.) or you don’t have the data to support that analysis, then you haven’t done your job.Any Six Sigma text should make this clear. Personally, I’m a fan of Pyzdek’s Six Sigma Handbook, though I don’t have it at hand to reference a specific paragraph.That said, your project advisor may have reasons for requiring ANOVA; you should talk with him/her about this.

    0
    #185235

    Craig
    Participant

    Don’t try to force the application of specific tools.
    I grabbed one of my text books from the shelf, sneezed from the dust, and opened to chapter 10 (Categorical data analysis). The text is “Statistical Methods and Data Analysis” by Ott and Longnecker. You could look at differences in your response by shift, day of the week, etc.  You would of course have to know the underlying distribution of the data (ie binomial)
     

    0
    #185236

    Severino
    Participant

    I think your first step is to request an extension for your project.  I doubt very much you will be able to get through the last three stages of DMAIC in 15 – 20 days and do an acceptable job.

    0
Viewing 5 posts - 1 through 5 (of 5 total)

The forum ‘General’ is closed to new topics and replies.