Hypothesis Testing

[matoma]

We didn't get to go over this very in depth in class so I'm a little confused as to how to go about this question. I'm assuming proc glm for the first question? I attached some descriptive statistics I performed on the data set. 

1. Test the null hypothesis that there is no difference between the cholesterol of the diabetes group and the non-diabetes group. (HINT: Check the normality of cholesterol first)
2. Using correlation coefficient >0.9 (or <-0.9) as the cutoff criterion, test the null hypothesis that there is no collinearity problem between BMI and age.

[PaigeMiller]

1. PROC GLM

2. PROC CORR

Although I think setting a correlation of 0.9 is a poor cutoff to determine if there is no collinearity problem.

[matoma]

proc glm data=mergec;

class diabetes cholesterol;

model cholesterol=diabetes;

run;

This is what I performed but I'm not sure I got the class and model components correct

[PaigeMiller · Accepted solution]

Cholesterol is not a CLASS variable.