+ Reply to Thread
Results 1 to 5 of 5

Thread: Standard error bar question.

  1. #1
    Points: 30, Level: 1
    Level completed: 60%, Points required for next Level: 20

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Standard error bar question.




    Im doing a lab on mitosis and have calculated the SE already for all the categories. I am almost certain that when the instructions state ( 2 SE) for the error bars that you multiply the SE by 2 and use that value for ur error bars. Most of my group members don't agree with me.
    Attached Thumbnails Attached Thumbnails Click image for larger version

Name:	Screenshot_20170221-095541.jpg‎
Views:	22
Size:	30.0 KB
ID:	6473   Click image for larger version

Name:	Screenshot_20170221-095553.jpg‎
Views:	20
Size:	24.2 KB
ID:	6474  

  2. #2
    Omega Contributor
    Points: 38,303, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,993
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Standard error bar question.

    Agreed with the +/- 2*SE, which would be your 95% confidence interval. Just call them that and the reviewer will understand without abiguity.
    Stop cowardice, ban guns!

  3. #3
    Points: 30, Level: 1
    Level completed: 60%, Points required for next Level: 20

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Standard error bar question.

    I agree, so I would multiply the SE by two and use those values for my error bars

  4. #4
    Omega Contributor
    Points: 38,303, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,993
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Standard error bar question.

    I didn't stare too hard at your attachments, but if you are looking at means - YES. The bars would represent your 95% confidence intervals for each mean. Of note, sometimes these whiskers mean different things based on the procedure used, so it is always nice to provide a legend describing what your whiskers represent.
    Stop cowardice, ban guns!

  5. #5
    Points: 1,741, Level: 24
    Level completed: 41%, Points required for next Level: 59

    Posts
    230
    Thanks
    37
    Thanked 68 Times in 59 Posts

    Re: Standard error bar question.


    Quote Originally Posted by Rsahu1919 View Post
    I agree, so I would multiply the SE by two and use those values for my error bars
    I would probably look up the critical t-values to multiply the SE by for your case. Unless you have a very large degrees of freedom, the appropriate t-value will be meaningfully larger in magnitude than 2 for a 95% level of confidence. On top of that, 2 is already a "rough estimate" of the "actual" +/-1.96 that's rounded from the z-distribution. Essentially, you're "approximating" the 1.96 with a 2, and that's assuming you have enough degrees of freedom to justify going off the z-distribution (which, judging from that picture, your largest group seems to be around 10 or so, and you probably can't get away with using the z-distribution).
    Last edited by ondansetron; 02-21-2017 at 02:06 PM.

+ 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