Use with simulated portfolio data to generate under-reporting stats for specified scenarios.

sim_ur_scenarios(
  df_portf,
  extra_ur_sites = 3,
  ur_rate = c(0.25, 0.5),
  r = 1000,
  poisson_test = FALSE,
  prob_lower = TRUE,
  parallel = FALSE,
  progress = TRUE,
  site_aggr_args = list(),
  eval_sites_args = list()
)

Arguments

df_portf

dataframe as returned by sim_test_data_portfolio

extra_ur_sites

numeric, set maximum number of additional under-reporting sites, see details Default: 3

ur_rate

numeric vector, set under-reporting rates for scenarios Default: c(0.25, 0.5)

r

integer, denotes number of simulations, default = 1000

poisson_test

logical, calculates poisson.test pvalue

prob_lower

logical, calculates probability for getting a lower value

parallel

logical, use parallel processing see details, Default: FALSE

progress

logical, show progress bar, Default: TRUE

site_aggr_args

named list of parameters passed to site_aggr, Default: list()

eval_sites_args

named list of parameters passed to eval_sites, Default: list()

Value

dataframe with the following columns:

study_id

study identification

site_number

site identification

n_pat

number of patients at site

n_pat_with_med75

number of patients at site with visit_med75

visit_med75

median(max(visit)) * 0.75

mean_ae_site_med75

mean AE at visit_med75 site level

mean_ae_study_med75

mean AE at visit_med75 study level

n_pat_with_med75_study

number of patients at site with visit_med75 at study excl site

extra_ur_sites

additional sites with under-reporting patients

frac_pat_with_ur

ratio of patients in study that are under-reporting

ur_rate

under-reporting rate

pval

p-value as returned by poisson.test

prob_low

bootstrapped probability for having mean_ae_site_med75 or lower

pval_adj

adjusted p-values

prob_low_adj

adjusted bootstrapped probability for having mean_ae_site_med75 or lower

pval_prob_ur

probability under-reporting as 1 - pval_adj, poisson.test (use as benchmark)

prob_low_prob_ur

probability under-reporting as 1 - prob_low_adj, bootstrapped (use)

Details

The function will apply under-reporting scenarios to each site. Reducing the number of AEs by a given under-reporting (ur_rate) for all patients at the site and add the corresponding under-reporting statistics. Since the under-reporting probability is also affected by the number of other sites that are under-reporting we additionally calculate under-reporting statistics in a scenario where additional under reporting sites are present. For this we use the median number of patients per site at the study to calculate the final number of patients for which we lower the AEs in a given under-reporting scenario. We use the furrr package to implement parallel processing as these simulations can take a long time to run. For this to work we need to specify the plan for how the code should run, e.g. plan(multisession, workers = 18)

Examples

# \donttest{
df_visit1 <- sim_test_data_study(n_pat = 100, n_sites = 10,
                                 frac_site_with_ur = 0.4, ur_rate = 0.6)

df_visit1$study_id <- "A"

df_visit2 <- sim_test_data_study(n_pat = 100, n_sites = 10,
                                 frac_site_with_ur = 0.2, ur_rate = 0.1)

df_visit2$study_id <- "B"

df_visit <- dplyr::bind_rows(df_visit1, df_visit2)

df_site_max <- df_visit %>%
  dplyr::group_by(study_id, site_number, patnum) %>%
  dplyr::summarise(max_visit = max(visit),
            max_ae = max(n_ae),
            .groups = "drop")

df_config <- get_config(df_site_max)

df_config
#> # A tibble: 20 × 6
#>    study_id ae_per_visit_mean site_number max_visit_sd max_visit_mean n_pat
#>    <chr>                <dbl> <chr>              <dbl>          <dbl> <int>
#>  1 0001                 0.416 0001                3.39           18.2    10
#>  2 0001                 0.416 0002                2.72           19.6    10
#>  3 0001                 0.416 0003                2.12           19.6    10
#>  4 0001                 0.416 0004                3.92           18.4    10
#>  5 0001                 0.416 0005                3.63           19.9    10
#>  6 0001                 0.416 0006                3.83           20      10
#>  7 0001                 0.416 0007                2.69           21.1    10
#>  8 0001                 0.416 0008                4.24           19      10
#>  9 0001                 0.416 0009                3.59           21.3    10
#> 10 0001                 0.416 0010                2.95           19.7    10
#> 11 0002                 0.468 0001                4.42           20      10
#> 12 0002                 0.468 0002                4.03           21.4    10
#> 13 0002                 0.468 0003                4.13           20.2    10
#> 14 0002                 0.468 0004                2.58           18.3    10
#> 15 0002                 0.468 0005                4.64           17.8    10
#> 16 0002                 0.468 0006                2.37           17.6    10
#> 17 0002                 0.468 0007                4.80           19.8    10
#> 18 0002                 0.468 0008                2              20      10
#> 19 0002                 0.468 0009                3.17           19.5    10
#> 20 0002                 0.468 0010                6.57           19.9    10

df_portf <- sim_test_data_portfolio(df_config)

df_portf
#> # A tibble: 3,815 × 8
#>    study_id ae_per_visit_mean site_number max_visit…¹ max_v…² patnum visit  n_ae
#>    <chr>                <dbl> <chr>             <dbl>   <dbl> <chr>  <int> <int>
#>  1 0001                 0.416 0001               3.39    18.2 0001       1     1
#>  2 0001                 0.416 0001               3.39    18.2 0001       2     1
#>  3 0001                 0.416 0001               3.39    18.2 0001       3     1
#>  4 0001                 0.416 0001               3.39    18.2 0001       4     1
#>  5 0001                 0.416 0001               3.39    18.2 0001       5     2
#>  6 0001                 0.416 0001               3.39    18.2 0001       6     3
#>  7 0001                 0.416 0001               3.39    18.2 0001       7     4
#>  8 0001                 0.416 0001               3.39    18.2 0001       8     4
#>  9 0001                 0.416 0001               3.39    18.2 0001       9     4
#> 10 0001                 0.416 0001               3.39    18.2 0001      10     5
#> # … with 3,805 more rows, and abbreviated variable names ¹​max_visit_sd,
#> #   ²​max_visit_mean

df_scen <- sim_ur_scenarios(df_portf,
                            extra_ur_sites = 2,
                            ur_rate = c(0.5, 1))
#> aggregating site level
#> prepping for simulation
#> generating scenarios
#> getting under-reporting stats
#> evaluating stats


df_scen
#> # A tibble: 140 × 14
#>    study…¹ site_…² n_pat n_pat…³ visit…⁴ mean_…⁵ mean_…⁶ n_pat…⁷ extra…⁸ frac_…⁹
#>    <chr>   <chr>   <int>   <int>   <dbl>   <dbl>   <dbl>   <int>   <dbl>   <dbl>
#>  1 0001    0001       10      10      12    5.9     4.74      88       0   0    
#>  2 0001    0001       10      10      12    2.95    4.74      88       0   0.102
#>  3 0001    0001       10      10      12    0       4.74      88       0   0.102
#>  4 0001    0001       10      10      12    2.95    4.53      88       1   0.202
#>  5 0001    0001       10      10      12    0       4.33      88       1   0.202
#>  6 0001    0001       10      10      12    2.95    4.24      88       2   0.302
#>  7 0001    0001       10      10      12    0       3.75      88       2   0.302
#>  8 0001    0002       10       9      15    4.78    6.52      79       0   0    
#>  9 0001    0002       10       9      15    2.39    6.52      79       0   0.102
#> 10 0001    0002       10       9      15    0       6.52      79       0   0.102
#> # … with 130 more rows, 4 more variables: ur_rate <dbl>, prob_low <dbl>,
#> #   prob_low_adj <dbl>, prob_low_prob_ur <dbl>, and abbreviated variable names
#> #   ¹​study_id, ²​site_number, ³​n_pat_with_med75, ⁴​visit_med75,
#> #   ⁵​mean_ae_site_med75, ⁶​mean_ae_study_med75, ⁷​n_pat_with_med75_study,
#> #   ⁸​extra_ur_sites, ⁹​frac_pat_with_ur

df_perf <- get_portf_perf(df_scen)

df_perf
#> # A tibble: 27 × 5
#>      fpr thresh extra_ur_sites ur_rate   tpr
#>    <dbl>  <dbl>          <dbl>   <dbl> <dbl>
#>  1 0.001  0.990              0     0    0.05
#>  2 0.001  0.990              1     0    0.05
#>  3 0.001  0.990              2     0    0.05
#>  4 0.001  0.990              0     0.5  1   
#>  5 0.001  0.990              1     0.5  0.9 
#>  6 0.001  0.990              2     0.5  0.85
#>  7 0.001  0.990              0     1    1   
#>  8 0.001  0.990              1     1    1   
#>  9 0.001  0.990              2     1    1   
#> 10 0.01   0.961              0     0    0.05
#> # … with 17 more rows
# }