diff --git a/transform.Rmd b/transform.Rmd
index 3193d91..ae032c5 100644
--- a/transform.Rmd
+++ b/transform.Rmd
@@ -837,7 +837,7 @@ Grouping is most useful in conjunction with `summarise()`, but you can also do c
     ```{r}
     flights_sml %>% 
       group_by(year, month, day) %>%
-      filter(rank(arr_delay) < 10)
+      filter(rank(desc(arr_delay)) < 10)
     ```
 
 *   Find all groups bigger than a threshold: