A function of class "nonlin" to specify a log-multiplicative row-column association models with transitional
layer effect with one or several dimensions in the formula argument to gnm. RCTransSymm
allows specifying a variant with symmetric (homogeneous) row and column scores.
RCTrans(row, col, layer, inst = NULL)
RCTransSymm(row, col, layer, inst = NULL)A list with the required components of a "nonlin" function:
the expressions passed to Mult
a function to create a deparsed mathematical expression of the term, given labels for the predictors.
the call to use as a prefix for parameter labels.
the levels of the row variable
the levels of the column variable
the levels of the layer variable
a positive integer specifying the instance number of the term
Milan Bouchet-Valat
This function is used by rcL.trans to fit an experimental model.
RCTrans combines its arguments in the following way:
$$ RCTrans(i, j, k) = (\mu^S_i + \psi_k \mu^V_i) (\nu^S_j + \psi_k \nu^V_j)$$
where \(RCTrans(i, j, k)\) is the skew association for the cell at the intersection of row i, column j
and layer k of the table.
RCTransSymm is similar, but forces \(\mu^S_i\) and \(\nu^S_i\) (respectively \(\mu^V_i\) and
\(\nu^V_i\)) to be equal for identical values of i (diagonal cells).
rcL.trans