+ Reply to Thread
Results 1 to 2 of 2

Thread: which test to use ?

  1. #1
    Points: 12,976, Level: 74
    Level completed: 32%, Points required for next Level: 274

    Thanked 2 Times in 2 Posts

    which test to use ?


    I am running a quality analysis. I have a can of some liquid material, and I analyze it's characteristics.

    At time 0, 30 samples from this can were taken, and a few measures were taken.

    at time 1, other 30 samples were taken, and the same measures were taken.

    The researcher wants to know if there is a significant difference between the first group (time 0) and the second (time 1). He wants to see affect of time. I only have 2 time points, and the sample is not paired, the second sample is different, but from same big can.

    Can I assume independence ? I mean, both samples are from same big can, but they are independent. A paired t-test is out of the question. Can I use a normal t-test ?
    (under assumptions of normality and equality of variance of course)

    anything more appropriate ?

    thank you

  2. #2
    Points: 266, Level: 5
    Level completed: 32%, Points required for next Level: 34

    Portland, Oregon
    Thanked 0 Times in 0 Posts

    Re: which test to use ?

    Hi Yankel,
    I just have some questions before I say, "independant t-test"
    1. What kind of statistical software are you using or are you familiar with? (e.g. Matlab, SPSS, R, SAS, Excel, etc...)
    2. What kind of "measures" are you taking?
    (a) Are the 30 measures taken on the same "dependant" variable? (e.g. concentration, temperature, viscoscity)
    (b) Are the 30 measures ordinal, continuous, or nominal?

+ Reply to Thread


Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts

Advertise on Talk Stats