1. ## 95% ci

Hi I am trying to interpret a journal article about the results of whether drinking cokes leads to child hyperactivity, the sample taken from a group of children where there are three sub groups as: never drink, drink 1-2 times/week and more than 1-2 times/week
the baseline is set at those who never drink.
The result goes as follows:

Hyperactivity:
Never 13.4
Light 10.1
Heavy 12.6

I want to know why when they calculate the OR, using the never group as baseline, the OR for light group 0.73 (0.58 to 0.91) and the OR for heavy is 0.92 (0.61 to 1.39). What I got for light group is 10.1/13.4 = 0.75 and for heavy group was 12.6/13.4 = 0.94

Also, how to they calculate the CI?
Thanks

2. ## Re: 95% ci

It's weird that they would calculate OR's, when RR's would be fine here. What you calculated was the RR (relative risk). Odds ratios are calculated as the ratio of Odds, which requires probabilities (or odds) of an event. There's probably something you're missing.

3. ## Re: 95% ci

What method is being used (the only one I know that uses it is logistic regression)?

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts