Simulate AE under-reporting probabilities.
Usage
simaerep(
df_visit,
r = 1000,
check = TRUE,
under_only = TRUE,
visit_med75 = TRUE,
inframe = FALSE,
progress = TRUE,
mult_corr = TRUE,
param_site_aggr = list(method = "med75_adj", min_pat_pool = 0.2),
param_sim_sites = list(r = 1000, poisson_test = FALSE, prob_lower = TRUE),
param_eval_sites = list(method = "BH"),
env = parent.frame(),
event_names = c("ae")
)Arguments
- df_visit
Data frame with columns: study_id, site_number, patnum, visit, n_ae.
- r
Integer or tbl_object, number of repetitions for bootstrap simulation. Pass a tbl object referring to a table with one column and as many rows as desired repetitions. Default: 1000.
- check
Logical, perform data check and attempt repair with
check_df_visit(). Computationally expensive on large data sets. Default: TRUE.- under_only
Logical, compute under-reporting probabilities only. Supersedes under_only parameter passed to
eval_sites()andsim_sites(). Default: TRUE.- visit_med75
Logical, should evaluation point visit_med75 be used. Default: TRUE.
- inframe
Logical, only table operations to be used; does not require visit_med75. Compatible with dbplyr supported database backends.
- progress
Logical, display progress bar. Default: TRUE.
- mult_corr
Logical, multiplicity correction, Default: TRUE
- param_site_aggr
List of parameters passed to
site_aggr(). Default: list(method = "med75_adj", min_pat_pool = 0.2).- param_sim_sites
List of parameters passed to
sim_sites(). Default: list(r = 1000, poisson_test = FALSE, prob_lower = TRUE).- param_eval_sites
List of parameters passed to
eval_sites(). Default: list(method = "BH").- env
Optional, provide environment of original visit data. Default: parent.frame().
- event_names
vector, contains the event names, default = "ae"
Details
Executes site_aggr(), sim_sites(), and eval_sites() on original
visit data and stores all intermediate results. Stores lazy reference to
original visit data for facilitated plotting using generic plot(x).
Examples
df_visit <- sim_test_data_study(
n_pat = 100,
n_sites = 5,
frac_site_with_ur = 0.4,
ur_rate = 0.6
)
df_visit$study_id <- "A"
aerep <- simaerep(df_visit)
aerep
#> simaerep object:
#> Check aerep$df_eval prob_low_prob_ur column for under-reporting probabililty.
#> Plot results using plot() generic.
str(aerep)
#> List of 12
#> $ visit :List of 4
#> ..$ dim : int [1:2] 1972 9
#> ..$ df_summary : tibble [1 × 5] (S3: tbl_df/tbl/data.frame)
#> .. ..$ n_studies : int 1
#> .. ..$ n_sites : int 5
#> .. ..$ n_patients: int 100
#> .. ..$ n_visits : int 1972
#> .. ..$ n_aes : int 705
#> ..$ str_call : chr "df_visit"
#> ..$ event_names: chr "ae"
#> ..- attr(*, "class")= chr "orivisit"
#> $ df_site : tibble [5 × 6] (S3: tbl_df/tbl/data.frame)
#> ..$ study_id : chr [1:5] "A" "A" "A" "A" ...
#> ..$ site_number : chr [1:5] "S0001" "S0002" "S0003" "S0004" ...
#> ..$ n_pat : int [1:5] 20 20 20 20 20
#> ..$ n_pat_with_med75 : num [1:5] 18 18 17 20 16
#> ..$ visit_med75 : Named num [1:5] 17 15 16 15 16
#> .. ..- attr(*, "names")= chr [1:5] "80%" "80%" "80%" "80%" ...
#> ..$ mean_ae_site_med75: num [1:5] 3.11 2.56 8.53 6.4 8.38
#> $ df_sim_sites : tibble [5 × 9] (S3: tbl_df/tbl/data.frame)
#> ..$ study_id : chr [1:5] "A" "A" "A" "A" ...
#> ..$ site_number : chr [1:5] "S0001" "S0002" "S0003" "S0004" ...
#> ..$ n_pat : int [1:5] 20 20 20 20 20
#> ..$ n_pat_with_med75 : num [1:5] 18 18 17 20 16
#> ..$ visit_med75 : Named num [1:5] 17 15 16 15 16
#> .. ..- attr(*, "names")= chr [1:5] "80%" "80%" "80%" "80%" ...
#> ..$ mean_ae_site_med75 : num [1:5] 3.11 2.56 8.53 6.4 8.38
#> ..$ mean_ae_study_med75 : num [1:5] 7.03 6.21 5.26 5.21 5.34
#> ..$ n_pat_with_med75_study: int [1:5] 59 72 66 70 67
#> ..$ prob_low : num [1:5] 0 0 1 1 1
#> $ df_eval : tibble [5 × 11] (S3: tbl_df/tbl/data.frame)
#> ..$ study_id : chr [1:5] "A" "A" "A" "A" ...
#> ..$ site_number : chr [1:5] "S0001" "S0002" "S0003" "S0004" ...
#> ..$ n_pat : int [1:5] 20 20 20 20 20
#> ..$ n_pat_with_med75 : num [1:5] 18 18 17 20 16
#> ..$ visit_med75 : Named num [1:5] 17 15 16 15 16
#> .. ..- attr(*, "names")= chr [1:5] "80%" "80%" "80%" "80%" ...
#> ..$ mean_ae_site_med75 : num [1:5] 3.11 2.56 8.53 6.4 8.38
#> ..$ mean_ae_study_med75 : num [1:5] 7.03 6.21 5.26 5.21 5.34
#> ..$ n_pat_with_med75_study: int [1:5] 59 72 66 70 67
#> ..$ prob_low : num [1:5] 0 0 1 1 1
#> ..$ prob_low_adj : num [1:5] 0 0 1 1 1
#> ..$ prob_low_prob_ur : num [1:5] 1 1 0 0 0
#> $ r : num 1000
#> $ visit_med75 : logi TRUE
#> $ inframe : logi FALSE
#> $ under_only : logi TRUE
#> $ param_site_aggr :List of 2
#> ..$ method : chr "med75_adj"
#> ..$ min_pat_pool: num 0.2
#> $ param_sim_sites :List of 4
#> ..$ r : num 1000
#> ..$ poisson_test: logi FALSE
#> ..$ prob_lower : logi TRUE
#> ..$ under_only : logi TRUE
#> $ param_eval_sites:List of 2
#> ..$ method : chr "BH"
#> ..$ under_only: logi TRUE
#> $ event_names : chr "ae"
#> - attr(*, "class")= chr "simaerep"
df_visit_events_test <- sim_test_data_events(n_pat = 100, n_sites = 5,
ae_per_visit_mean = c(0.4, 0.5), event_names = c("ae", "pd"))
aerep_events <- simaerep(df_visit_events_test, inframe = TRUE,event_names = c("ae", "pd"))
aerep_events
#> simaerep object:
#> Check aerep$df_eval prob_low_prob_ur column for under-reporting probabililty.
#> Plot results using plot() generic.
# \donttest{
# In-frame table operations
simaerep(df_visit, inframe = TRUE, visit_med75 = FALSE, under_only = FALSE)$df_eval
#> # A tibble: 5 × 13
#> study_id site_number events events_per_visit_site visits n_pat
#> <chr> <chr> <dbl> <dbl> <dbl> <int>
#> 1 A S0001 76 0.183 415 20
#> 2 A S0002 75 0.186 403 20
#> 3 A S0003 187 0.496 377 20
#> 4 A S0004 180 0.453 397 20
#> 5 A S0005 187 0.492 380 20
#> # ℹ 7 more variables: events_per_visit_study <dbl>, prob_low <dbl>,
#> # prob_low_adj <dbl>, prob_low_prob_ur <dbl>, prob_high <dbl>,
#> # prob_high_adj <dbl>, prob_high_prob_or <dbl>
simaerep(df_visit, inframe = TRUE, visit_med75 = TRUE, under_only = FALSE)$df_eval
#> # A tibble: 5 × 15
#> study_id site_number events events_per_visit_site visits n_pat
#> <chr> <chr> <dbl> <dbl> <dbl> <int>
#> 1 A S0001 56 0.183 306 18
#> 2 A S0002 46 0.170 270 18
#> 3 A S0003 145 0.533 272 17
#> 4 A S0004 128 0.427 300 20
#> 5 A S0005 134 0.523 256 16
#> # ℹ 9 more variables: events_per_visit_study <dbl>, prob_low <dbl>,
#> # prob_low_adj <dbl>, prob_low_prob_ur <dbl>, prob_high <dbl>,
#> # prob_high_adj <dbl>, prob_high_prob_or <dbl>, n_pat_with_med75 <dbl>,
#> # visit_med75 <dbl>
# Database example
con <- DBI::dbConnect(duckdb::duckdb(), dbdir = ":memory:")
df_r <- tibble::tibble(rep = seq(1, 1000))
dplyr::copy_to(con, df_visit, "visit")
dplyr::copy_to(con, df_r, "r")
tbl_visit <- dplyr::tbl(con, "visit")
tbl_r <- dplyr::tbl(con, "r")
simaerep(tbl_visit, r = tbl_r, inframe = TRUE, visit_med75 = FALSE, under_only = FALSE)$df_eval
#> # Source: SQL [?? x 13]
#> # Database: DuckDB v1.2.1 [koneswab@Darwin 23.6.0:R 4.4.1/:memory:]
#> # Ordered by: study_id, site_number
#> study_id site_number events events_per_visit_site visits n_pat
#> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
#> 1 A S0002 75 0.186 403 20
#> 2 A S0001 76 0.183 415 20
#> 3 A S0003 187 0.496 377 20
#> 4 A S0005 187 0.492 380 20
#> 5 A S0004 180 0.453 397 20
#> # ℹ 7 more variables: events_per_visit_study <dbl>, prob_low <dbl>,
#> # prob_low_adj <dbl>, prob_low_prob_ur <dbl>, prob_high <dbl>,
#> # prob_high_adj <dbl>, prob_high_prob_or <dbl>
simaerep(tbl_visit, r = tbl_r, inframe = TRUE, visit_med75 = TRUE, under_only = FALSE)$df_eval
#> # Source: SQL [?? x 15]
#> # Database: DuckDB v1.2.1 [koneswab@Darwin 23.6.0:R 4.4.1/:memory:]
#> # Ordered by: study_id, site_number
#> study_id site_number events events_per_visit_site visits n_pat
#> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
#> 1 A S0004 128 0.427 300 20
#> 2 A S0001 56 0.183 306 18
#> 3 A S0002 46 0.170 270 18
#> 4 A S0005 134 0.523 256 16
#> 5 A S0003 145 0.533 272 17
#> # ℹ 9 more variables: events_per_visit_study <dbl>, prob_low <dbl>,
#> # prob_low_adj <dbl>, prob_low_prob_ur <dbl>, prob_high <dbl>,
#> # prob_high_adj <dbl>, prob_high_prob_or <dbl>, n_pat_with_med75 <dbl>,
#> # visit_med75 <int>
DBI::dbDisconnect(con)
# }