Dear friends,

I am not if this is the right way to go about posting here but I need some assistance. Does anyone here have experience in surveys? I need some guidance. I am designing a nationwide survey on students dietary habits. Let's say the country is divided into 5 parishes with the following number of schools and students:

Parishes----Schools-----School population

A -----------20 ---------8,000

B ------------9 ---------20,000

C -----------40 ---------10,000

D -----------10 ---------20,000

E -----------6 ----------6,000

1. How do I select a reasonable nationwide sample of students from

the entire school population for this study?

2. Parish Based Approach.

Would it be reasonable enough if I randomly select a specific number

of schools (for example 5 schools) from each parish then add up

the number students from these five schools and randomly choose a

determined amount of students for the study? What should be my

sample size?

Suggestions Please.

Thanks in advance.