Can I measure the significance of correlation between BMI and no. of organ changes?
This may be something I could figure out on my own, but it would take forever. I would GREATLY appreciate it if you could help me out.
Let's focus on two columns named "BMI" and "number of skin changes". I got a nice graph out of this which showed that in patients with scleroderma, patients with higher BMI are less likely to develop skin changes). Now, I wonder, is there any way to check if the correlation is significant or not? I don't want to just randomly choose graphs for my research work. Thanks in advance!
Re: Can I measure the significance of correlation between BMI and no. of organ change
You could use pearman's rho correlation coefficient.
The threshold for statistical significance could be a
problem, though. It sounds like you checked a large
number of bivariate relationships and then decided to
test one relationship which looked interesting? If so,
you have to take into account the complete number
of checks, by using a corrected signficance level
(Bonferroni correction perhaps) instead of the usual