Parameters of a list of multinomial logit models

Create a list containing the parameters of multiple fitted multinomial logit models. Can be used to parameterize state transitions in a discrete time transition model by passing to the params field of a CohortDtstmTrans object.

params_mlogit_list(...)

Arguments

...

Objects of class params_mlogit, which can be named.

Value

An object of class params_mlogit_list, which is a list containing params_mlogit objects.

See also

summary.params_mlogit_list(), params_mlogit(), CohortDtstmTrans

Examples

# Consider a sick-sicker model

params <- params_mlogit_list(
  ## Transitions from sick state (sick -> sicker, sick -> death)
  sick = params_mlogit(
    coefs = list(
      sicker = data.frame(
        intercept = c(-0.33, -.2),
        treat = c(log(.75), log(.8))
      ),
      death = data.frame(
        intercept = c(-1, -1.2),
        treat = c(log(.6), log(.65))
      )
    )
  ),
  
  ## Transitions from sicker state (sicker -> death)
  sicker = params_mlogit(
    coefs = list(
      death = data.frame(
        intercept = c(-1.5, -1.4),
        treat = c(log(.5), log(.55))
      )
    )
  )
)
summary(params)
#>      from     to      term       mean         sd       2.5%      97.5%
#>    <char> <char>    <char>      <num>      <num>      <num>      <num>
#> 1:   sick sicker intercept -0.2650000 0.09192388 -0.3267500 -0.2032500
#> 2:   sick sicker     treat -0.2554128 0.04563563 -0.2860686 -0.2247570
#> 3:   sick  death intercept -1.1000000 0.14142136 -1.1950000 -1.0050000
#> 4:   sick  death     treat -0.4708043 0.05659874 -0.5088246 -0.4327840
#> 5: sicker  death intercept -1.4500000 0.07071068 -1.4975000 -1.4025000
#> 6: sicker  death     treat -0.6454921 0.06739447 -0.6907644 -0.6002198
params
#> A "params_mlogit_list" object
#> 
#> Summary of coefficients:
#>      from     to      term       mean         sd       2.5%      97.5%
#>    <char> <char>    <char>      <num>      <num>      <num>      <num>
#> 1:   sick sicker intercept -0.2650000 0.09192388 -0.3267500 -0.2032500
#> 2:   sick sicker     treat -0.2554128 0.04563563 -0.2860686 -0.2247570
#> 3:   sick  death intercept -1.1000000 0.14142136 -1.1950000 -1.0050000
#> 4:   sick  death     treat -0.4708043 0.05659874 -0.5088246 -0.4327840
#> 5: sicker  death intercept -1.4500000 0.07071068 -1.4975000 -1.4025000
#> 6: sicker  death     treat -0.6454921 0.06739447 -0.6907644 -0.6002198
#> 
#> Number of parameter samples: 2
#> Number of starting (non-absorbing) states: 2
#> Number of transitions by starting state: 2 1