iSixSigma

comparing populations

Six Sigma – iSixSigma Forums Old Forums Healthcare comparing populations

Viewing 2 posts - 1 through 2 (of 2 total)
  • Author
    Posts
  • #25816

    Madmax
    Participant

    I think this is an easy one. I would like to calculate a statisically significant sample size in comparing 2 designs.  I would like to assure that the new design produces fewer failures. Any suggestions.

    0
    #62518

    Robert Butler
    Participant

     What you are describing is the calculation of a sample size to compare two proportions.  What you meant to ask is for a given difference in proportions what is the sample size needed to be sure that if the difference is significant you will be at least 80% certain that this significant difference is real
      To answer this you will have to have an estimate of the proportions.  If the old design produces 20% failures and you think the new design will produce 15% failures then these become the proportions you will use for the sample size calculation.

    0
Viewing 2 posts - 1 through 2 (of 2 total)

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