Skip to contents

This function summarises posterior predictives for observed data (by report and reference date). The functionality of this function can be used directly on the output of epinowcast() using the supplied summary.epinowcast() method.

Usage

enw_pp_summary(fit, diff_obs, probs = c(0.05, 0.2, 0.35, 0.5, 0.65, 0.8, 0.95))

Arguments

fit

A cmdstanr fit object.

diff_obs

A data.frame of observed data with at least a date variable reference_date, and a grouping variable .group.

probs

A vector of numeric probabilities to produce quantile summaries for. By default these are the 5%, 20%, 80%, and 95% quantiles which are also the minimum set required for plotting functions to work.

Value

A data.table summarising the posterior predictions.

Examples

fit <- enw_example("nowcast")
enw_pp_summary(fit$fit[[1]], fit$new_confirm[[1]], probs = c(0.5))
#>      reference_date report_date .group max_confirm location age_group confirm
#>              <IDat>      <IDat>  <num>       <int>   <fctr>    <fctr>   <int>
#>   1:     2021-07-13  2021-07-13      1          59       DE       00+      21
#>   2:     2021-07-13  2021-07-14      1          59       DE       00+      33
#>   3:     2021-07-13  2021-07-15      1          59       DE       00+      36
#>   4:     2021-07-13  2021-07-16      1          59       DE       00+      40
#>   5:     2021-07-13  2021-07-17      1          59       DE       00+      43
#>  ---                                                                         
#> 626:     2021-08-20  2021-08-21      1         171       DE       00+     159
#> 627:     2021-08-20  2021-08-22      1         171       DE       00+     171
#> 628:     2021-08-21  2021-08-21      1         112       DE       00+      69
#> 629:     2021-08-21  2021-08-22      1         112       DE       00+     112
#> 630:     2021-08-22  2021-08-22      1          45       DE       00+      45
#>      cum_prop_reported delay new_confirm prop_reported   mean median        sd
#>                  <num> <num>       <int>         <num>  <num>  <num>     <num>
#>   1:         0.3559322     0          21    0.35593220 19.818     18  8.997768
#>   2:         0.5593220     1          12    0.20338983 20.808     19  9.249903
#>   3:         0.6101695     2           3    0.05084746  5.894      5  3.385887
#>   4:         0.6779661     3           4    0.06779661  4.209      4  2.753707
#>   5:         0.7288136     4           3    0.05084746  2.454      2  1.870664
#>  ---                                                                          
#> 626:         0.9298246     1          61    0.35672515 80.300     75 34.009714
#> 627:         1.0000000     2          12    0.07017544 12.721     12  6.182182
#> 628:         0.6160714     0          69    0.61607143 75.275     71 32.177737
#> 629:         1.0000000     1          43    0.38392857 47.607     45 21.042085
#> 630:         1.0000000     0          45    1.00000000 40.819     38 19.833043
#>          mad   q50      rhat  ess_bulk ess_tail
#>        <num> <num>     <num>     <num>    <num>
#>   1:  8.8956    18 1.0019355 1061.4434 992.3891
#>   2:  8.8956    19 1.0042792  666.2820 963.7879
#>   3:  2.9652     5 1.0005725 1045.8014 911.8297
#>   4:  2.9652     4 0.9990272  883.7513 983.1110
#>   5:  1.4826     2 0.9998082  968.8058 951.5574
#>  ---                                           
#> 626: 31.1346    75 1.0054516 1084.5743 947.1035
#> 627:  5.9304    12 1.0001721 1002.8719 967.7479
#> 628: 29.6520    71 1.0006111 1053.0376 977.8959
#> 629: 19.2738    45 1.0053457  947.7744 832.7111
#> 630: 17.7912    38 0.9990299 1049.2785 994.5472