iSixSigma

Using proportional data

Six Sigma – iSixSigma Forums Old Forums General Using proportional data

Viewing 4 posts - 1 through 4 (of 4 total)
  • Author
    Posts
  • #51060

    newbie
    Participant

    I have read that rate data can be considered continuous if both variables are continuous (ie distance / time).  Is this statistically sound and are there any practical concerns if using data in this form? 
    Example:  I am dealing in “continuous” ratios, would I run an attribute chart or am I free to use any appropriate continuous chart?  Etc.
    Thanks!

    0
    #176411

    Severino
    Participant

    Is np>5?

    0
    #176437

    Michael Mead
    Participant

    There are many cases where either chart is correct. It is a matter of choice.
    Generally you get more information from control charts using continuous data. Large sample sizes are needed to detect process shifts using attribute data.  However, if the data is discrete, often you will get false signals on a chart for continuous data.
    I recommend starting with the continuous approach. If you find your chart has a lot of shifts due to small changes in the input data, try an attribute chart.
    Good luck.
     

    0
    #176441

    Jonathon Andell
    Participant

    I’d want some more details, but isn’t distance divided by time usually called either velocity (if treated as a vector) or speed (if treated as a scalar)? If that’s what you are measuring, your Y variable is in fact continuous.
    If I am missing something here, please provide more details.

    0
Viewing 4 posts - 1 through 4 (of 4 total)

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