Jump to content

  • Log in with Facebook Log in with Twitter Log in with Windows Live Log In with Google      Sign In   
  • Create Account

Submit your paper to J Biol Methods today!
Photo
- - - - -

error bars when presenting data as (% of control)


  • Please log in to reply
7 replies to this topic

#1 yobou

yobou

    Enthusiast

  • Active Members
  • PipPipPipPipPip
  • 89 posts
1
Neutral

Posted 26 February 2013 - 10:52 PM

Dear All
when presenting data as (% of control) how can we add error bars in this case? I mean the error bars would represent what? If I make the error bars represent standard deviation, they are not visible on the chart because its value is small compared to the scale used. So what should be done in these cases?
thanks

Edited by yobou, 26 February 2013 - 10:53 PM.


#2 pcrman

pcrman

    Epigenetist

  • Global Moderators
  • PipPipPipPipPipPipPipPipPipPip
  • 1,165 posts
68
Excellent

Posted 26 February 2013 - 10:57 PM

Error bars represent deviation (SD or SEM), but cannot represent % of control. Can you give some example data?

#3 yobou

yobou

    Enthusiast

  • Active Members
  • PipPipPipPipPip
  • 89 posts
1
Neutral

Posted 26 February 2013 - 11:25 PM

I want to send you an excel file. could you give your email

#4 pcrman

pcrman

    Epigenetist

  • Global Moderators
  • PipPipPipPipPipPipPipPipPipPip
  • 1,165 posts
68
Excellent

Posted 26 February 2013 - 11:42 PM

you can PM me as attachment. thanks.

#5 yobou

yobou

    Enthusiast

  • Active Members
  • PipPipPipPipPip
  • 89 posts
1
Neutral

Posted 26 February 2013 - 11:51 PM

plz check ur PM

#6 doxorubicin

doxorubicin

    Veteran

  • Moderators
  • PipPipPipPipPipPipPipPipPipPip
  • 192 posts
15
Good

Posted 27 February 2013 - 03:21 AM

The easy way:
When you convert to "% of control", you multiply all values by: 100/[control value]. Just multiply all of your standard errors by this same exact value. It's just changing the scale of your graph, like changing from inches to cms.

#7 hobglobin

hobglobin

    Growing old is mandatory, growing up is optional...

  • Global Moderators
  • PipPipPipPipPipPipPipPipPipPip
  • 5,548 posts
104
Excellent

Posted 27 February 2013 - 09:01 AM

The easy way:
When you convert to "% of control", you multiply all values by: 100/[control value]. Just multiply all of your standard errors by this same exact value. It's just changing the scale of your graph, like changing from inches to cms.

but this won't solve the problem what the error bars finally show...

One must presume that long and short arguments contribute to the same end. - Epicurus
...except casandra's that belong to the funniest, most interesting and imaginative (or over-imaginative?) ones, I suppose.

That is....if she posts at all.


#8 pcrman

pcrman

    Epigenetist

  • Global Moderators
  • PipPipPipPipPipPipPipPipPipPip
  • 1,165 posts
68
Excellent

Posted 27 February 2013 - 10:03 AM

From the data yobou passed me I know he(she) has done one experiment which includes a control, other 3 treatments with 3 repeats in each treatment. In this case, he can do a plot of the actual measurement with error bars. But if he wants to plot as value relative to control, he needs to repeat his experiment at least another time, so that he can SD for the %of control values.




Home - About - Terms of Service - Privacy - Contact Us

©1999-2013 Protocol Online, All rights reserved.