Parameter estimates for higher dimensions

• For higher dimensions the story is similar. Consider independence in two dimensions:
  
  $$\log F_{ij} = \lambda_0 + \lambda_i^A + \lambda_j^B$$
  
  

• Remembering that $\lambda_1 = 0$ for rows and columns:
  

  	1	2	3
  1	$\lambda_0$	$\lambda_0 + \lambda_2^B$	$\lambda_0 + \lambda_3^B$
  2	$\lambda_0 + \lambda_2^A$	$\lambda_0 + \lambda_2^A + \lambda_2^B$	$\lambda_0 + \lambda_2^A + \lambda_3^B$
  3	$\lambda_0 + \lambda_3^A$	$\lambda_0 + \lambda_3^A + \lambda_2^B$	$\lambda_0 + \lambda_3^A + \lambda_3^B$