nav[aria-label="Primary Navigation"] { padding: 0; & ul { list-style: none; width: 100%; display: flex; flex-direction: row; justify-content: start; align-items: start; gap: 30px; padding: 0; & li { margin: 0; } & ul li { list-style: none; } } }

How do I do a Chi-Square test with duplicate rows of data?

LimitedInfo

I'm trying to do a Chi-Square test. I have multiple rows of data for individual restaurants. I only need one row per restaurant because the type of cuisine for each restaurant is constant between months. Should I reformat the data or is there a way to do the Chi-Square test with the data in the picture?

(I wouldn't have to worrry about this problem if I had the same number of months per restaurant, however I do not.)

Accepted answers

Mark_Bailey

This is a quick way with a summary table.

Select Tables > Summary.
Select Ticket, Cuisine, and Sig, then click Group.
Click OK.

Now use the new summary table,

Select Analyze > Fit Y by X
Select Cuisine and click Y
Select Sig and click X
Click OK.

Your mosaic plot and contingency table should depict the conditional probabilities and the Chi square test should be at the bottom.

All comments

Mark_Bailey

I test of what, in terms of the variables you show in the picture of the data table?

LimitedInfo

A test of whether there is a significant difference in the frequency of cuisine type between Sig of 0 restaurants and Sig of 1 restaurants.

Mark_Bailey

This is a quick way with a summary table.

Select Tables > Summary.
Select Ticket, Cuisine, and Sig, then click Group.
Click OK.

Now use the new summary table,

Select Analyze > Fit Y by X
Select Cuisine and click Y
Select Sig and click X
Click OK.

Your mosaic plot and contingency table should depict the conditional probabilities and the Chi square test should be at the bottom.