Create \(\beta\) matrix from vector of \(\beta\) for \(\beta_k : k \neq j\)
multinom_beta_vector_to_matrix.RdCreate \(\beta\) matrix from vector of \(\beta\) for \(\beta_k : k \neq j\)
Arguments
- values
A vector containing the values for all \(\beta_k\), with \(k \neq j\), as well as all \(\beta_{k0}, for k = 1, \dots, J\). In particular, this vector should be so that the first \((J-2)(p+1)\) entries are \(\beta_{10}, \beta_{1}^{\top}, \beta_{20}, \beta_{2}^{\top}, \dots, \beta_{(j-1)0}, \beta_{j-1}^{\top}, \beta_{(j+1)0}, \beta_{j+1}^{\top}, \dots, \beta_{(J-1)0}, \beta_{J-1}^{\top}, \beta_{j0}\). Then, the \((J-2)(p+1) + 1\) entry should be \(\beta_{j0}\).
- p
This should be the number of covariates.
- J
This should be the number of categories.
- null_j
This specifies for which category you have set \(\beta_j = 0\).
- beta_j_null
This is the null hypothesized value for \(\beta_j\), which is by default set to be \(\beta_j = 0\).