8  summarizing data exercises

8.1 Setup

library(dplyr)
dm <- readRDS("data/dm.rds")
ae <- readRDS("data/ae.rds")

8.2 Exercise 1

Count the number of overall adverse events per subject and sort the output such that the subject with the highest overall number of adverse events appears first.

Show solution

ae %>% 
  group_by(USUBJID) %>% 
  summarise(n_ae = n()) %>% 
  arrange(desc(n_ae))

# A tibble: 225 × 2
   USUBJID      n_ae
   <chr>       <int>
 1 01-701-1302    23
 2 01-717-1004    19
 3 01-704-1266    16
 4 01-709-1029    16
 5 01-718-1427    16
 6 01-701-1192    15
 7 01-701-1275    15
 8 01-709-1309    15
 9 01-713-1179    15
10 01-711-1143    14
# … with 215 more rows

8.3 Exercise 2

Count the overall number of serious adverse events per treatment arm (ACTARM).

Show solution

ae %>% 
  filter(AESER == "Y") %>% 
  group_by(ACTARM) %>% 
  summarise(n = n())

# A tibble: 2 × 2
  ACTARM                   n
  <chr>                <int>
1 Xanomeline High Dose     1
2 Xanomeline Low Dose      2

8.4 Exercise 3

Find the lowest and highest AGE per treatment arm.

Show solution

dm %>% 
  group_by(ARM) %>% 
  summarise(youngest = min(AGE, na.rm = TRUE), oldest = max(AGE, na.rm = TRUE))

# A tibble: 4 × 3
  ARM                  youngest oldest
  <chr>                   <int>  <int>
1 Placebo                    52     89
2 Screen Failure             50     89
3 Xanomeline High Dose       56     88
4 Xanomeline Low Dose        51     88