iSixSigma

Sample size calculation given machine accuracy

Six Sigma – iSixSigma Forums Old Forums General Sample size calculation given machine accuracy

Viewing 8 posts - 1 through 8 (of 8 total)
  • Author
    Posts
  • #43038

    Tinoco
    Participant

    I have been struggling in determining the required sample size given a machine’s accuracy.  The testing will consist simply of checking the parts dimensions, and the machine’s accuracy is given in these terms.  The population size is also known.  Any help with this subject would be great. Thanks.

    0
    #136194

    Benjamin Bantum
    Participant

    I always use 14.

    0
    #136195

    Impecunious
    Participant

    Sample size is a function of a few key properties: the minimum difference you want to detect, your desired power, the standard deviation of the data, and your desired confidence level.
    The detectable difference seems odd to many people at first glance, but it’s simply the smallest difference that you “have” to detect to be meaningful for your particular purpose.  For example, if your engineers begin to care when a part’s width is more than 0.5″ from some specification, then your minimum difference would be 0.5.  All else equal, the smaller the difference you want to detect, the larger your sample size will need to be.
    Power is the probability that you’ll correctly reject the null hypothesis when you should.  Power is generally set somewhere between 0.7 and 0.85, although your particular situation may dictate otherwise.

    0
    #136206

    Griswold
    Participant

    Anthony,
    What’s your email address.  I will send you a little sample calculator from excel.  I use it from time-to-time.  But I think it will suit your needs.
    chip

    0
    #136209

    Tinoco
    Participant

    Hi Chip,
    Thanks for your response. My email is [email protected]
    Thanks.

    0
    #136215

    Griswold
    Participant

    Anthony,
    I sent you the file, let me know how you make out.  The post previous to this is on target as well.  If you have minitab you can do the same thing and see the different power levels.  The file I sent you is establishing the sampling amount at a 95% CI.  There are two sheets, one for discrete data and one for continous.  The curve on the chart to the right starts going to the right, that’s when increasing you sample size has a diminishing return.
    Good luck,
    Chip

    0
    #136470

    Eugene Lanning
    Participant

    I’m looking at how often samples should be taken from a machine.  Currently 5 samples are taken each hour, independent of production rate, standard deviation, confidence level desired, or anything else.  Could the spreadsheet mentioned help bring some rigor into this situation.  I also have access to MINITAB.  Is there an ANSI std for this problem?
    The spreadsheet may be fwd to [email protected]
     

    0
    #136683

    R.M.Parkhi
    Participant

    1. Machine accuracy as per manufacture’s recomendation is a prime requirement.
    2. Since you the job accuracy, you start producing the jobs till you achieve 80 % of the total spread of the specs. This is more than sufficient. You should carry out Multi-vari analysis for the same.This will help you to identify the root-causes of variations viz. within job, job to job & temporal i.e. time related. Attack no. one & no. two causes to reduce the variations to obtain CPk of 1.67.
    You may get details in the book ” World Class Quality ” by Mr. Keki Bhote, publishers American Management Association.
    With regards,
    R.M.Parkhi 

    0
Viewing 8 posts - 1 through 8 (of 8 total)

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