+ Reply to Thread
Results 1 to 5 of 5

Thread: attrition: comparing *surviving* sample to original

  1. #1
    Points: 4,215, Level: 41
    Level completed: 33%, Points required for next Level: 135

    Posts
    10
    Thanks
    0
    Thanked 0 Times in 0 Posts

    attrition: comparing *surviving* sample to original




    Hi,
    I have a question about attrition analyses in longitudinal databases.

    I know that I can compare the subjects who dropped out ("nonresponders") to those who responded, but what I'd like to do is to determine whether the surviving sample is representative of the original sample. If I do t-tests on demographic data comparing the surviving sample to the original sample, I violate the assumption of non-independence (they are the same subjects). Is there a way to do this correctly?

    Thank you!

    Lisa

  2. #2
    Points: 4,215, Level: 41
    Level completed: 33%, Points required for next Level: 135

    Posts
    10
    Thanks
    0
    Thanked 0 Times in 0 Posts
    My strong feeling is that it is not possible to compare the surviving group with the original (since they are the same), and that it is much more informative to compare nonresponders to responders. This would be how I would address the problem of attrition. However, someone has asked me whether it is possible to do it the other way (surviving vs. original). Any help on this would be greatly appreciated.

  3. #3
    Points: 4,215, Level: 41
    Level completed: 33%, Points required for next Level: 135

    Posts
    10
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Unhappy

    Any chance BioStatMatt could help me out with this question?

  4. #4
    TS Contributor
    Points: 4,575, Level: 43
    Level completed: 13%, Points required for next Level: 175

    Location
    Nashville, TN
    Posts
    177
    Thanks
    0
    Thanked 0 Times in 0 Posts
    foerverpostdoc, I don't know if I'm the best person to answer this question, but I'll tell you what I think.

    Now, the original population can be considered a mixture of individuals, those nonresponders, and those that remain in the study. So the mean for a given attribute of the original population is a weighted mean of the nonresponder mean and the mean for the group who remained in the study.

    This indicates that the difference in the mean for the group who remained in the study and the original mean can only be due to the effect of the nonresponders.

    Hence, the remaining subsample will be representative of the mixture population only if the remaining subsample and the nonresponder subsample are alike.

    So, I think you could make your argument by testing the remaining subsample against the nonresponders as is consistent with your initial thinking. If you find that these two groups are different, you can be fairly confident that a each subgroup will be different from the mixture of the two.

    let me know if this helps,

    ~Matt

  5. #5
    Points: 4,215, Level: 41
    Level completed: 33%, Points required for next Level: 135

    Posts
    10
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Thanks, yes that was helpful!

+ Reply to Thread

           




Similar Threads

  1. Comparing means from SAME sample
    By HumanParticipantResearch in forum Statistical Research
    Replies: 0
    Last Post: 09-01-2010, 01:35 PM
  2. Comparing Known Population to Sample Normality?
    By heather_s in forum Statistics
    Replies: 1
    Last Post: 01-02-2010, 09:48 PM
  3. comparing different sample sizes
    By lou_be in forum Statistics
    Replies: 2
    Last Post: 03-02-2009, 03:46 PM
  4. Attrition Rules-of-Thumb
    By ceperras in forum Statistics
    Replies: 0
    Last Post: 11-27-2007, 08:30 PM
  5. Comparing a sample with a mean
    By eraserhead in forum Statistics
    Replies: 1
    Last Post: 06-06-2007, 11:50 AM

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