Skip to contents

Standardised outputs are outputs from models with covariates, that are defined by marginalising (averaging) over covariate values in a given population, rather than being conditional on a given covariate value.

Usage

standardise_to(new_data)

standardize_to(new_data)

Arguments

new_data

Data frame with covariate values to predict for

Details

Standardised outputs are produced from a Monte Carlo sample from the joint distribution of parameters \(\theta\) and covariate values \(X\), \(p(X,\theta) = p(\theta|X)p(X)\), where \(p(X)\) is defined by the empirical distribution of covariates in the standard population. This joint sample is obtained by concatenating samples of covariate-specific outputs.

Hence applying an output function \(g()\) (such as the transition probability) to this sample produces a sample from the posterior of \(\int g(\theta|X) dX\): the average transition probability (say) for a heterogeneous population.

Examples


nd <- data.frame(sex=c("female","male"))

## gender-specific outputs
qdf(infsim_modelc, new_data = nd)
#> # A tibble: 4 × 5
#>    from    to    posterior sex     mode
#>   <int> <int>   <rvar[1d]> <chr>  <dbl>
#> 1     1     2  0.69 ± 0.34 female 0.623
#> 2     1     2  0.78 ± 0.37 male   0.704
#> 3     2     1  4.20 ± 1.89 female 3.84 
#> 4     2     1  4.20 ± 1.89 male   3.84 

## averaged over men and women in the same proportions as are in `nd`
## in this case, `nd` has two rows, so we take a 50/50 average
qdf(infsim_modelc, new_data = standardise_to(nd))
#> # A tibble: 2 × 4
#>    from    to    posterior  mode
#>   <int> <int>   <rvar[1d]> <dbl>
#> 1     1     2  0.73 ± 0.36 0.663
#> 2     2     1  4.20 ± 1.89 3.84