what does this mean? (Stats)

Debate and discussion of any biological questions not pertaining to a particular topic.

Moderators: honeev, Leonid, amiradm, BioTeam

Post Reply
biology_06er
Coral
Coral
Posts: 260
Joined: Tue Mar 21, 2006 9:33 am

what does this mean? (Stats)

Post by biology_06er » Wed May 05, 2010 8:10 am

Hi there,

Everytime I read articles I never understand the statistical methods used...example this sentance:

"in threshold analyses the authors found that those in the top decile of total zinc intake (15mg+/day) were significantly less likely to develop early AMD (RR 0.54; 95% CI 0.30-0.97 P=0.041)...what does relative risk actually mean..i have googled these terms but still dont really understand so hoping someone here can explain simply for me. I read that the lower the P value (less than 1 means its statis. sig??)...is that right?....as for RR/CI can somone please explain..

also...the sentance "antiox intakes were analysied as continuous variables (per standard deviation) and as tertiles, the lowest tertile was the referent group". what is a tertile...it doesn't even exist on dictionary.com :S...does it just mean group as in the highest tertile for zinc (highest group having the highest intake of zinc??)

Thanks and hopefully someone can explain the above,
b_06er

User avatar
JackBean
Inland Taipan
Inland Taipan
Posts: 5694
Joined: Mon Sep 14, 2009 7:12 pm

Post by JackBean » Wed May 05, 2010 9:01 am

significance shown by p-value differers. As clinical trial can be happy for anything under 0.1, that's significant for them, usually it's 0.01 or 0.001 ;) Of course, the lower, the more realiable is it. Best is, if you get 0 (so low, that it can't be expressed as 1E...)
http://www.biolib.cz/en/main/

Cis or trans? That's what matters.

Post Reply

Who is online

Users browsing this forum: No registered users and 15 guests