iSixSigma

Handling of Scanty data

Six Sigma – iSixSigma Forums Old Forums General Handling of Scanty data

Viewing 3 posts - 1 through 3 (of 3 total)
  • Author
    Posts
  • #36003

    chhabra
    Participant

    HI all
    I am doing an attribute data analysis for types of errors.But the problem is that the data is very smaal in numbers,i.e. the data is scanty and i am not getting as how to proceed.Can some one tell me what and how I can draw inferences from that data?
    Thanks n Regards
    Amit

    0
    #102611

    Darth
    Participant

    How are you defining small?Β  Unfortunately, discrete data requires pretty large numbers to draw any inferences.Β  What type of analysis are you planning to do?Β  Basic means, s.d. and confidence intervals can be done but the CI is going to be pretty wide and likely not much value.Β  If you are doing hypothesis testing, a small number will affect your Power and conclusions about the null hypothesisΒ could be affected.Β Β  Even a control chart will be affected if you don’t have enough data to calculate valid control limits.

    0
    #102671

    bobf
    Participant

    Try plotting the elapsed time in days or hours between the events you are measuring, on an I chart (aka X, moving Range chart)

    0
Viewing 3 posts - 1 through 3 (of 3 total)

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