June 25, 2007

Error Bars

Posted by Eric at 10:23 am | Category: Literature, Science

Via Small Things Considered, I found a very nice summary article on how to use Error bars in experimental biology. It has very little math, but does a good job in emphasizing the different roles of standard deviation, standard error, and the confidence interval, as well as how to eyeball the significance level of differences using both CIs and standard error bars. Plus, it mentioned something I hadn’t realized previously:

The CIs (or SEs) do not give the information needed to assess the significance of the differences between means of the same group at different times because they are not sensitive to correlations within the group.

Very useful. This is in my permanent library.

Follow the comments thread by the RSS 2.0 feed. You can leave a response, or trackback from your own site.

One Response to “Error Bars”

  1. Ben Says:
    June 25th, 2007 at 6:05 pm

    I’m oftentimes surprised that most people aren’t aware of that. Multivariable regressions and statistical analyses are more or less useless if two of the variables being studied are dependent on each other.

Leave a Reply