Reply
Mon 2 Sep, 2013 07:10 am
Hello, what does it mean if the p-value is <0.05 (statistically significant) but the confidence interval contains a ZERO? For instance, the mean subtotal score +1.31 was for placebo vs. -3.98 was for rotigotine; p<0.0001; 95% CI: -7.60, 2.96)...
@sieunbae,
What were the sample sizes? Were they approximately equal? Were the scores reasonably normally distributed? What analysis did you perform to calculate the p-value? I'd say you need to be looking at a non-parametric analysis to see if some of the assumptions of the original analysis model were violated.
Stumble It!
Tweet This
Bookmark on Delicious
Share on Facebook
Share on MySpace