Sign in to follow this  
Followers 0
late-start

Any statisticians around???

Rate this topic

21 posts in this topic

View Postask me anything icon14.gif

 

View PostI just sent you a pm... I'm no PHD but I may be able to take a crack at it...smile.gif

 

Since you've asked.

 

 

Looking at a sample of 67 subjects; where I'm comparing findings on liver biopsy and labs to a marker of angiogenesis(VEGF). Primary goal is to show that VEGF changes with stage of fibrosis(4 different groups based on stage, so ordinal); which I've done using Kruskal-Wallis test as it's nonparametric. It showed that its stat. significantly different. I now need to evaluate the other independent variables to determine if there are any other covariants or important factors.

 

 

I'm having difficulty trying to determine the correct means to do it all. I used ANCOVA to determine if Grade is important with Stage as a covariant and vice versa. I need to do a multivariate analysis of the remaining factors but not quite sure how to do it; especially as I have both ordinal and continues data as independent variables. Any thoughts??

 

 

VEGF is the dependent variable and is continuos.

 

 

Independent Variables

 

Stage of fibrosis (4 groups, ordinal)

 

Grade of inflammation (4 groups, ordinal)

 

Age (continuous)

 

a bunch of lab values (all continuous)

Share this post


Link to post
Share on other sites

I seem to recall, during my stats classes, that there are some public access software to address the testing of the variables. Drop Santiago II a pm and run it past him. He recently finished his doctorate. Scott

Share this post


Link to post
Share on other sites
View PostI seem to recall, during my stats classes, that there are some public access software to address the testing of the variables. Drop Santiago II a pm and run it past him. He recently finished his doctorate. Scott

 

Yeah Scott, one thing that got me PO'd about that article was that at a cursory glance, it didn't seem to have any sources for models... some of the poli-sci models I saw did have links to software for modeling, but I wanted to be sure I was looking up a bio-stat-based one...

 

hell, I may even PM Santiago IIbiggrin.gif

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to register here in order to participate.

Create an account

Sign up for a new account in our community. It's easy!


Register a new account

Sign in

Already have an account? Sign in here.


Sign In Now
Sign in to follow this  
Followers 0

  • Recently Browsing   0 members

    No registered users viewing this page.