+ Reply to Thread
Results 1 to 4 of 4

Thread: Expected values K-S test for Normality

  1. #1
    Points: 53, Level: 1
    Level completed: 6%, Points required for next Level: 47

    Posts
    4
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Expected values K-S test for Normality




    Hi all,

    I do have a question, given are 12 observed values (see SPSS outprint in attachment)
    4,1
    4,3
    4,6
    4,9
    5,0
    5,1
    5,1
    5,6
    5,6
    5,6
    6,0
    6,4

    I have no idea how to calculate the expected values for this K-S test. Can someone help me a bit, this is a test for the normal distribution.

    The result is 0,1369

    btw:
    Just to clarify......the Java right here is solo...so it's Solo/Java

    Greetings,
    Java/solo
    Attached Thumbnails Attached Thumbnails Click image for larger version

Name:	ScreenHunter_295 Oct. 01 20.02.jpg‎
Views:	11
Size:	65.4 KB
ID:	4799   Click image for larger version

Name:	ScreenHunter_297 Oct. 01 20.02.jpg‎
Views:	9
Size:	16.1 KB
ID:	4800   Click image for larger version

Name:	ScreenHunter_298 Oct. 01 20.03.jpg‎
Views:	7
Size:	17.8 KB
ID:	4801   Click image for larger version

Name:	ScreenHunter_296 Oct. 01 20.02.jpg‎
Views:	4
Size:	28.6 KB
ID:	4802  

  2. #2
    Points: 53, Level: 1
    Level completed: 6%, Points required for next Level: 47

    Posts
    4
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Expected values K-S test for Normality

    About the data: the observed values are storage times (in days) for foodstuff. In that case it is a 2 sided K-S test for normality (Goodness-of-Fit). We did see it with Chi square and the Kolmogorov-Smirnov table.

    Note: in SPSS the answer is 0,143, not the result mentioned above which is a result from the textbook and might be wrong.
    The question is what kind of formula is used by SPSS to obtain this result ?
    Any help is greatly appreciated !!
    solo

  3. #3
    Super Moderator
    Points: 13,151, Level: 74
    Level completed: 76%, Points required for next Level: 99
    Dragan's Avatar
    Location
    Illinois, US
    Posts
    2,014
    Thanks
    0
    Thanked 223 Times in 192 Posts

    Re: Expected values K-S test for Normality

    Quote Originally Posted by Java View Post
    About the data: the observed values are storage times (in days) for foodstuff. In that case it is a 2 sided K-S test for normality (Goodness-of-Fit). We did see it with Chi square and the Kolmogorov-Smirnov table.

    Note: in SPSS the answer is 0,143, not the result mentioned above which is a result from the textbook and might be wrong.
    The question is what kind of formula is used by SPSS to obtain this result ?
    Any help is greatly appreciated !!
    solo
    Click on "Help" then search "test of normality" and click on "Examine Algorithm".

    Note that SPSS is using the Dallal and Wilkinson (Dallal and Wilkinson, 1986) correction to the critical values for testing normality that was reported by Lilliefors compared to what you are most likely computing based on your textbook.

  4. The Following User Says Thank You to Dragan For This Useful Post:

    Java (10-06-2014)

  5. #4
    Points: 53, Level: 1
    Level completed: 6%, Points required for next Level: 47

    Posts
    4
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Expected values K-S test for Normality


    Thanks a lot,

    I'm not familiar with Lilliefors test so I did search it on the internet. Not sure whether this is the solution of the problem. The highest value is 0,1424 but this is lower than the critical value 0,242 in the Lilliefors table.

    In this case we accept the Null hypothesis. In other words: the values follow the Normal Distribution.

    solo
    Attached Images  
    Last edited by Java; 10-08-2014 at 10:24 AM. Reason: Answer is 100% correct, no remarks needed.

+ Reply to Thread

           




Tags for this 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