07-19-2016 09:08 PM
Basic SAS 9.4 user here. My dilemma - My dependent variable is disease (0=absent, 1=present). My indepedent variable (vitd) is not normally distributed though my sample size is over 3000. I'm trying to use geometric mean (GM) to describe "vitd" and use it in a log regression model. However, I don't have expereince with using GM. If anyone could help me with any of my questions, that would be great!
1) If I'm describing my data using GM, I should report standard error (SE) and not coefficient of variation, correct?
2) In using a T test, I used the following code to get the GM and p, however, I only get the coefficient of variation and not the SE. How can I get the SE? I don't know how to use proc surveymeans to stratify my data by class, so I'm using the following:
proc ttest data=work.run1 alpha=0.05 dist=lognormal;
class disease; /*disease has 2 categories*/
3) In my logistic regression model, I want to use the continuous variable "vitd" which isn't normally distributed. Do I have to log transform then add it to the model or can I use it as is? If it's the former, can you please suggest how I can I do this.
My understanding is that it doesn't need to be normal. As of now, this is my code for my adjusted model (assuming I use the variable without log transforming it):
proc logistic data=work.run1;
class gender (param=ref ref='0');
model DR = vitd3 age gender;
4) Lastly, I'm used to comparing based on the means and sds. How would I interpret the GM between those with disease versus those without disease?
Thanks in advance!!