FRIDAY, FEBRUARY 23, 2018
Font Size
Topic Building a Model to Measure Process

Building a Model to Measure Process

Home Forums General Forums Methodology Building a Model to Measure Process

This topic contains 6 replies, has 5 voices, and was last updated by  Ronald 1 month ago.

Viewing 7 posts - 1 through 7 (of 7 total)
  • Author
    Posts
  • #700637 Reply

    Doug

    My boss has tasked me to build a audit model that can measure output BEFORE implementing a project/process.

    We’ve already created a process model for the product.

    Now he asking to create a process measuring template/formula that will define output before moving forward on the project.

    I’m stumped. Is there a tool L6 has that can measure return on investment before deciding to move forward on a projects?

    #700655 Reply

    Is he/she referencing your regressions or other predictive measures that would estimate how the output would change if the X’s are changed as recommended by the findings?

    That could be the model.

    #700674 Reply

    Doug

    No. We won’t be referencing regressions.

    I’m pretty new to this so, forgive me for sounding so novice.
    What L6 tool would you suggest can estimate how the output could change if the X variably changes.

    I have the output data on multiple-X projects.

    If I’m asking this correct, I need to provide a method/formula that can loosely predetermine an Xs output based off of previous referenced data(prior to implementation).

    I work for a newspaper and the boss wants to determine if the Return on Investment is worth the effort on future proposed products. {In other words…Before we begin, is it worth the time & money?}

    #700730 Reply

    You said ” I need to provide a method/formula that can loosely predetermine an Xs output based off of previous referenced data(prior to implementation).” which, based on my reading of that statement, says you can choose various and sundry measured variable connected with prior projects and for each of those projects you have a measured ROI. The issue then becomes one of running tests of the changes in those X’s to see if they correlate with ROI changes.

    If you won’t be referencing regressions then I don’t see how you expect to generate predictions. What you a describing is a situation where you are trying to relate measured inputs to a measured output – ROI. That is going to require statements of either percent changes in ROI or odds of increasing ROI. Both of those use predictive equations to describe the outcome.

    The biggest issue is going to be one of prior data. If we assume one ROI for each project then you are either going to have to have a lot of projects or a few project each with the same kind and low number of X’s.

    #700802 Reply

    Hi Doug, I may be able to assist you with a trying a Process Simulation, i.e. a model where we can map out the stages of the process, the variation in X and the rules around how this effects return. We could try using a Monte Carlo approach to allow you to model the variation in X over multiple runs to determine the likelihood of an outcome.

    Is the variation in X something that we can quantify in terms of a percentage likelihood or occurrence at different levels? As above we would also need to know how X links to return.

    #700816 Reply

    If your organization has really adopted a continuous improvement philosophy they shouldn’t care much about the numbers before the “I” phase unless the cost of getting to “I” is substantial. If you can’t convince your management to let you do “DMA” without ROI numbers, which sounds like your situation, I advise you to work with someone in your finance department who can help you come up with the numbers and reasonable risk considerations of your assumptions so you can present it to management. It’s a big mistake to try to do this on your own if you don’t have financial project management experience. Otherwise management will surely question your numbers and assumptions and shoot you down unless the project is compelling. And if was compelling you probably wouldn’t have been asked to do this in the first place.

    #701860 Reply

    Ronald

    Doug,
    Have you created a Detailed Process Map defining the inputs and outputs of each step of your process? A Detailed process map is one of the first steps in any six sigma venture. Before you start clearly define the beginning and end points of your process.
    Is this a internal administrative processor a factory machining or assembly process?

    If you are unclear what a Detailed Process Map is just google it there are plenty of good examples out there.
    Let me know how you do!

Viewing 7 posts - 1 through 7 (of 7 total)

Register Now

  • Stop this in-your-face notice
  • Reserve your username
  • Follow people you like, learn from
  • Extend your profile
  • Gain reputation for your contributions
  • No annoying captchas across site
And much more! C'mon, register now.

Reply To: Building a Model to Measure Process
Your information:






5S and Lean eBooks

Find the Perfect Six Sigma Job

Six Sigma Statistical and Graphical Analysis with SigmaXL
Six Sigma Online Certification: White, Yellow, Green and Black Belt
Lean and Six Sigma Project Examples
GAGEpack for Quality Assurance
Six Sigma Online Certification: White, Yellow, Green and Black Belt

Login Form