Advertisement
If you have a new account but are having problems posting or verifying your account, please email us on hello@boards.ie for help. Thanks :)
Hello all! Please ensure that you are posting a new thread or question in the appropriate forum. The Feedback forum is overwhelmed with questions that are having to be moved elsewhere. If you need help to verify your account contact hello@boards.ie

SPSS normal distribution

Options
  • 29-08-2010 3:06pm
    #1
    qt9ukbg60ivjrn
    Closed Accounts Posts: 384 ✭✭


    Hi,

    I need some help with this.

    I ran a test of normality on my samples is spss. The Shaprio-wilk "sig" reading is 0.00 so since it's less than 0.5 my sample isn't normally distributed.

    Looking at my Q-Q plot, shows this too.

    What is the significance of the fact that my sample isn't normally distributed? Can i still reject/accept null hypotheses in a t-test? Or am i jumping ahead of myself? If my sample fails a normal distribution test it should be thrown in the bin??

    Also, my shapiro-wilks sig is 0.00, not even 0.01 or .02. Could this mean the data is entered wrong?

    THanks


Comments

  • Options
    #2
    2Scoops
    Registered Users Posts: 1,845 ✭✭✭2Scoops


    I wouldn't live or die by what Shapiro-Wilks says, tbh. The fact that it's 0.0 probably means it's zero for several decimal places and got truncated - try pasting into Excel to check.

    Your options are to ignore Shapiro and look for other signs of normality (skewness, kurtosis, or just looking at it!) and if they're all clear, go with the t-test. If it's definitely not normally distributed, use a non-parametric equivalent of the t-test to test your hypothesis.


  • Options
    #3
    qt9ukbg60ivjrn
    Closed Accounts Posts: 384 ✭✭qt9ukbg60ivjrn


    Thanks for the response Scoops.


Advertisement