ANOVA or what?

[Kamil Toth <kamiltoth@yahoo.com>]

Folks:

I need an urgent help. I need to analyze the dataset in the field that sort of new to me, but I am sure is fairly transparent for many of you, bio-statistical and epidemiological gurus.

I have two data sets which we will call "treatment" and "control". Each of them contains 24 data points subdivided into four categories called: "weak", "mild", "moderate", "strong". There is no quantitative measure associated with these names but they assumed to be ordered. There are 6 (unordered) replicates in each of theses categories.  I need to estimate the effect of treatment vs control. I understand that there are many approaches possible (I thought about ANOVA, logistic regression,...). In the situation I currently find myself now, the preference would be toward method which is readily available in S-PLUS, and easy to interpret: first I need to understand myself what I am doing and then to clearly explain to non-statistical people.

 

What would you, smart people, recommend?

 

Looking forward for an advise, examples, references, ideas.

 

 

Thanks

 

Kamil Toth  

 

 

---

No need to miss a message. Get email on-the-go 
with Yahoo! Mail for Mobile. Get started.