Multinomial probabilities and conditional odds ratios

Softmax probabilities (equation 5.3) and the conditional odds ratio exp(xb_m - xb_n) (equation 5.4). Mirrors ca5e3 / ca5e4.

Usage

morie_mlogit_probs(xbs)

Arguments

xbs

Linear predictor per category (reference category 0).

Value

List with probs and a function-free or_matrix of pairwise conditional odds ratios.

Examples

V <- c(1, 2, 3, 4, 5, 6, 7, 8)
morie_mlogit_probs(V)
#> $probs
#> [1] 0.0005766128 0.0015673960 0.0042606241 0.0115815771 0.0314819905
#> [6] 0.0855769227 0.2326221940 0.6323326828
#> 
#> $or_matrix
#>             [,1]        [,2]        [,3]        [,4]        [,5]        [,6]
#> [1,]    1.000000   0.3678794   0.1353353  0.04978707  0.01831564 0.006737947
#> [2,]    2.718282   1.0000000   0.3678794  0.13533528  0.04978707 0.018315639
#> [3,]    7.389056   2.7182818   1.0000000  0.36787944  0.13533528 0.049787068
#> [4,]   20.085537   7.3890561   2.7182818  1.00000000  0.36787944 0.135335283
#> [5,]   54.598150  20.0855369   7.3890561  2.71828183  1.00000000 0.367879441
#> [6,]  148.413159  54.5981500  20.0855369  7.38905610  2.71828183 1.000000000
#> [7,]  403.428793 148.4131591  54.5981500 20.08553692  7.38905610 2.718281828
#> [8,] 1096.633158 403.4287935 148.4131591 54.59815003 20.08553692 7.389056099
#>             [,7]        [,8]
#> [1,] 0.002478752 0.000911882
#> [2,] 0.006737947 0.002478752
#> [3,] 0.018315639 0.006737947
#> [4,] 0.049787068 0.018315639
#> [5,] 0.135335283 0.049787068
#> [6,] 0.367879441 0.135335283
#> [7,] 1.000000000 0.367879441
#> [8,] 2.718281828 1.000000000
#>