Understanding statistical significant in assignment

#1
Hi everyone!
I'm completely new here, so forgive me if I don't follow codex on how to post or formulating the question.

I have a school assignment in my first course in statistics, and I don't really understand what the "customer" wants to be calculated.

The data consists of rows of different subdiagnosis (all within the same main diagnosis) and columns of 4 different groups. I am to calculate if there is a statistical significant difference in the rows of subdiagnosis between the 4 different columns. Can anyone here please explain what this mean? If I understand the problem, I'll figure out which tests and so on to perform, but the first step is of course understanding the problem.

I apologize if my question is too vague, please tell me and I will try to assist with more detailed information.

Kind regards
Hanna
 
Last edited:

Karabiner

TS Contributor
#2
Suppose you only have 2 diagnoses (A and B) and 2 groups (1 and 2).
The question could be wheter the respective proportions of A and B are
identical between Groups 1 and 2. You can do this constructing/using a 2x2
frequency table.

Suppose you have 2 groups and 3 diagnoses A B C. The question could
be whether the respective proportions of the diagnoses in group 1 is identical
to proportions in group 2.

You can expand this to multiple groups and more diagnoses. What you analyse
here is a 4x4 table of frequencies.

With kind regards

Karabiner