+ Reply to Thread
Results 1 to 5 of 5

Thread: Calculating 95% confidence interval from mean, SD and number of subjects

  1. #1
    Points: 430, Level: 8
    Level completed: 60%, Points required for next Level: 20

    Posts
    2
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Calculating 95% confidence interval from mean, SD and number of subjects




    Dear All
    I have been asked to present some information from a series of published articles according to Mean (+/- 95% Confidence Interval).

    The statistical summaries are generally presented as:
    Number of subjects (n)
    Mean (X)
    Standard deviation of the mean (sd)

    How do I calculate the 95% confidence intervals from just this information? Do I need the actual raw data??
    Thanks, best wishes
    David

  2. #2
    ggplot2orBust
    Points: 36,643, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    User with most referrers
    trinker's Avatar
    Location
    Buffalo, NY
    Posts
    4,007
    Thanks
    1,418
    Thanked 776 Times in 691 Posts

    Re: Calculating 95% confidence interval from mean, SD and number of subjects



    where:
    s = standard deviation of sample
    = mean of sample
    n = sample size

    Links on confidence interval of mean and standard error
    "If you torture the data long enough it will eventually confess."
    -Ronald Harry Coase -

  3. The Following User Says Thank You to trinker For This Useful Post:

    drhealy (01-13-2012)

  4. #3
    Beep
    Points: 63,852, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Discussion EnderPosting AwardCommunity AwardFrequent PosterActivity Award
    Dason's Avatar
    Location
    Ames, IA
    Posts
    11,359
    Thanks
    268
    Thanked 2,207 Times in 1,886 Posts

    Re: Calculating 95% confidence interval from mean, SD and number of subjects

    Quote Originally Posted by trinker View Post


    where:
    s = standard deviation of sample
    = mean of sample
    n = sample size

    Links on confidence interval of mean and standard error
    Note that this is technically if you knew the population standard deviation. Since it sounds like this is being computed from the data you should probably use whatever the corresponding t-quantile is instead of 1.96. But if your sample size is large enough it will be close enough to essentially not matter.

  5. The Following 2 Users Say Thank You to Dason For This Useful Post:

    drhealy (01-13-2012), trinker (01-13-2012)

  6. #4
    Points: 430, Level: 8
    Level completed: 60%, Points required for next Level: 20

    Posts
    2
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Re: Calculating 95% confidence interval from mean, SD and number of subjects

    To clarify; I am compiling a data chart summarizing a lot of very small studies (eg. n of 30).
    eg. study A of 30 subjects found a mean of 20.2 with an sd of 6, study B of 42 subjects found a mean of 27 with an sd of 4, etc.
    How do I find /calculate the t-quantile to place into the calculation?

  7. #5
    ggplot2orBust
    Points: 36,643, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    User with most referrers
    trinker's Avatar
    Location
    Buffalo, NY
    Posts
    4,007
    Thanks
    1,418
    Thanked 776 Times in 691 Posts

    Re: Calculating 95% confidence interval from mean, SD and number of subjects


    look it up in chart (CHART LINK HERE) or use a program/calculator. Excel will figure it out for you (LINK)
    "If you torture the data long enough it will eventually confess."
    -Ronald Harry Coase -

  8. The Following User Says Thank You to trinker For This Useful Post:

    drhealy (01-13-2012)

+ 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