Skip to main content
Cross Validated

Return to Answer

added 6 characters in body
Source Link
User1865345
User1865345
  • 10.3k
  • 12
  • 23
  • 40

First, I would expand it to 13 columns.

Then, while you could do some measure of association for each combination of products, that would give you $12*11/2 = 66$$12\times 11/2 = 66$ measures. Hard to interpret, prone to type 1 error.

I would look into multivariate approaches such as cluster analysis. This thread is a good place to start.

First, I would expand it to 13 columns.

Then, while you could do some measure of association for each combination of products, that would give you $12*11/2 = 66$ measures. Hard to interpret, prone to type 1 error.

I would look into multivariate approaches such as cluster analysis. This thread is a good place to start.

First, I would expand it to 13 columns.

Then, while you could do some measure of association for each combination of products, that would give you $12\times 11/2 = 66$ measures. Hard to interpret, prone to type 1 error.

I would look into multivariate approaches such as cluster analysis. This thread is a good place to start.

Source Link
Peter Flom
Peter Flom
  • 128.1k
  • 36
  • 184
  • 424

First, I would expand it to 13 columns.

Then, while you could do some measure of association for each combination of products, that would give you $12*11/2 = 66$ measures. Hard to interpret, prone to type 1 error.

I would look into multivariate approaches such as cluster analysis. This thread is a good place to start.