Selecting the correct sample size

[#1]

Hi All,

Lets assume I have a measurement of 30 location on a particular table top. I would like to sample the measurement of these 30 locations using only 5 samples, is JMP able to assist me on determining which measurement location should i be selecting in order to get the closest representative of the overall 30 measurement location

Irfan

[#2]

For a given problem, JMP will be able to choose the most efficient sampling scheme, provided you can adequately describe the limitations. e.g. the samples need to come from the edge, middle and corner plus more than 1 measure is required at each location to understand variability OR more locations is valuable, etc.

The challenge is it will probably require more sampling than you originally considered to have a good chance of success (1, 5 and 10 are very common human choices of sample size). You need to clearly define WHY you are sampling and WHAT you consider to be success.

[#3]

Hi Stephen,

Above is an example of my measurement location. If I were to select only 5 location to measure, how do I select which 5 location measurement that gives the best statistical representation of the all 23 measurement location. Is there a way to find out ?

Rgrds

Irfan

[#4]

Are all locations considered equal? Is number 12 (the centre) special in any way? One sampling scheme would be sampling at random from the different 'zones'. Are the locations rotatable (i.e 1 = 9 = 23)? You can run simulations based on historic data to compare how well any sampling scheme estimates the 'true' value if all locations are considered.