diff --git a/NAMESPACE b/NAMESPACE
index eb4dd76..0df1d3f 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -17,8 +17,6 @@ export(edc_data_warn)
 export(edc_data_warnings)
 export(edc_db_to_excel)
 export(edc_example)
-export(edc_example_ae)
-export(edc_example_mixed)
 export(edc_example_plot)
 export(edc_inform_code)
 export(edc_lookup)
diff --git a/man/data_example.Rd b/man/data_example.Rd
deleted file mode 100644
index d106785..0000000
--- a/man/data_example.Rd
+++ /dev/null
@@ -1,33 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/data.R
-\name{data_example}
-\alias{data_example}
-\alias{edc_example_mixed}
-\alias{edc_example}
-\alias{edc_example_plot}
-\alias{edc_example_ae}
-\title{Example databases}
-\usage{
-edc_example_mixed(N = 100, seed = 42)
-
-edc_example(N = 50, seed = 42, outdated = FALSE)
-
-edc_example_ae(N = 50, seed = 42)
-}
-\arguments{
-\item{N}{the number of patients}
-
-\item{seed}{the random seed}
-
-\item{outdated}{simulate times after the data extraction date}
-}
-\value{
-a list of tables
-}
-\description{
-List of tables used in EDCimport examples:
-\itemize{
-\item \code{edc_example()} can be used as the result of reading functions (such as \code{\link[=read_trialmaster]{read_trialmaster()}} or \code{\link[=read_all_sas]{read_all_sas()}}) and to test \code{\link[=edc_swimmerplot]{edc_swimmerplot()}}
-\item \code{edc_example_mixed()} can be used to test \code{\link[=split_mixed_datasets]{split_mixed_datasets()}}
-}
-}
diff --git a/man/edc_data_warn.Rd b/man/edc_data_warn.Rd
index 553a0fb..f9e86c5 100644
--- a/man/edc_data_warn.Rd
+++ b/man/edc_data_warn.Rd
@@ -54,30 +54,30 @@ Use \code{edc_data_warnings()} to generate the table for such a file.
 library(dplyr)
 tm = edc_example()
 load_list(tm)
-db0 \%>\% 
+enrol \%>\% 
   filter(age>70) \%>\% 
   edc_data_warn("Age should not be >70", issue_n=1)
 
-db0 \%>\% 
+enrol \%>\% 
   filter(age<25) \%>\% 
   edc_data_warn("Age should not be <25", issue_n=2)
 
 db1 \%>\% 
-  filter(n()>1, .by=SUBJID) \%>\% 
+  filter(n()>1, .by=subjid) \%>\% 
   edc_data_warn("There are duplicated patients in `db1` ({nrow(.data)} rows)", issue_n=3)
 
-db0 \%>\% 
+enrol \%>\% 
   filter(age<25) \%>\% 
   edc_data_warn("Age should not be <25", issue_n=NULL)
   
 edc_data_warnings()
 
 \dontrun{
-db0 \%>\% 
+enrol \%>\% 
   filter(age<25) \%>\% 
   edc_data_warn("Age should not be <25", csv_path="check/check_age_25.csv")
   
-db0 \%>\% 
+enrol \%>\% 
   filter(age<25) \%>\% 
   edc_data_stop("Age should *never* be <25")
 }
diff --git a/man/edc_example.Rd b/man/edc_example.Rd
new file mode 100644
index 0000000..b92b398
--- /dev/null
+++ b/man/edc_example.Rd
@@ -0,0 +1,22 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/data.R
+\name{edc_example}
+\alias{edc_example}
+\alias{edc_example_plot}
+\title{Example database}
+\usage{
+edc_example(N = 50, seed = 42, outdated = FALSE)
+}
+\arguments{
+\item{N}{the number of patients}
+
+\item{seed}{the random seed}
+
+\item{outdated}{whether to simulate times after the data extraction date}
+}
+\value{
+A list of tables of class \code{edc_database}.
+}
+\description{
+A list of tables that simulates the extraction of a clinical database. Used in \code{EDCimport} examples and tests.
+}
diff --git a/man/edc_swimmerplot.Rd b/man/edc_swimmerplot.Rd
index b0057c2..8225001 100644
--- a/man/edc_swimmerplot.Rd
+++ b/man/edc_swimmerplot.Rd
@@ -49,9 +49,9 @@ Join all tables from \code{.lookup$dataset} on \code{id}
 tm = edc_example_plot()
 load_list(tm)
 p = edc_swimmerplot(.lookup, id_lim=c(5,45))
-p2 = edc_swimmerplot(.lookup, origin="db0$date_naissance", time_unit="weeks", 
+p2 = edc_swimmerplot(.lookup, origin="enrol$date_naissance", time_unit="weeks", 
                      exclude=c("DB1$DATE2", "db3$.*"))
-p3 = edc_swimmerplot(.lookup, group="db0$group", aes_color="label")
+p3 = edc_swimmerplot(.lookup, group="enrol$group", aes_color="label")
 \dontrun{
 #save the plotly plot as HTML to share it
 save_plotly(p, "edc_swimmerplot.html")
diff --git a/man/edc_warn_patient_diffs.Rd b/man/edc_warn_patient_diffs.Rd
index ea9832c..7749108 100644
--- a/man/edc_warn_patient_diffs.Rd
+++ b/man/edc_warn_patient_diffs.Rd
@@ -34,10 +34,10 @@ Compare a subject ID vector to the study's reference subject ID (usually somethi
 \examples{
 tm = edc_example()
 load_list(tm)
-options(edc_subjid_ref=db0$SUBJID)
+options(edc_subjid_ref=enrol$subjid)
 #usually, you set something like:
 #options(edc_subjid_ref=enrolres$subjid)
 edc_warn_patient_diffs(db1)
-db1 \%>\% dplyr::filter(SUBJID>1) \%>\% edc_warn_patient_diffs()
-edc_warn_patient_diffs(c(db1$SUBJID, 99, 999))
+db1 \%>\% dplyr::filter(subjid>1) \%>\% edc_warn_patient_diffs()
+edc_warn_patient_diffs(c(db1$subjid, 99, 999))
 }
diff --git a/man/harmonize_subjid.Rd b/man/harmonize_subjid.Rd
index bca2dfd..a64e3f3 100644
--- a/man/harmonize_subjid.Rd
+++ b/man/harmonize_subjid.Rd
@@ -23,10 +23,10 @@ be performed on the levels.
 }
 \examples{
 db = edc_example()
-db$db0 = head(db$db0, 10)
-db$db0$SUBJID \%>\% head()
+db$enrol = head(db$enrol, 10)
+db$enrol$subjid \%>\% head()
 db = harmonize_subjid(db)
-db$db0$SUBJID \%>\% head()
+db$enrol$subjid \%>\% head()
 db = harmonize_subjid(db, preprocess=function(x) paste0("#", x))
-db$db0$SUBJID \%>\% head()
+db$enrol$subjid \%>\% head()
 }
diff --git a/man/select_distinct.Rd b/man/select_distinct.Rd
index 2bc7fe5..7e70800 100644
--- a/man/select_distinct.Rd
+++ b/man/select_distinct.Rd
@@ -19,8 +19,10 @@ Select all columns that has only one level for a given grouping scope.
 Useful when dealing with mixed datasets containing both long data and repeated short data.
 }
 \examples{
-tm = edc_example_ae()
-tm$ae \%>\% names
-tm$ae \%>\% select_distinct() \%>\% names
-tm$ae \%>\% select_distinct(.by=subjid) \%>\% names
+db = edc_example()
+db$ae \%>\% colnames()
+#`crfname` has one level for the whole dataset
+db$ae \%>\% select_distinct() \%>\% colnames()
+#`n_ae` has one level per patient
+db$ae \%>\% select_distinct(.by=subjid) \%>\% colnames()
 }
diff --git a/man/split_mixed_datasets.Rd b/man/split_mixed_datasets.Rd
index 2a17d27..11542b6 100644
--- a/man/split_mixed_datasets.Rd
+++ b/man/split_mixed_datasets.Rd
@@ -16,7 +16,7 @@ split_mixed_datasets(
 \arguments{
 \item{datasets}{a dataframe or a list of dataframes to split. Default to all the datasets from \code{.lookup}.}
 
-\item{id}{the patient identifier, probably "SUBJID". Should be shared by all datasets. Case-insensitive.}
+\item{id}{the patient identifier, probably "subjid". Should be shared by all datasets. Case-insensitive.}
 
 \item{...}{not used}
 
@@ -45,8 +45,8 @@ print(long_mixed_short)
 print(long_mixed_long) 
 
 #alternatively, get the code and only use the datasets you need
-split_mixed_datasets(tm, id="SUBJID", output_code=TRUE)
+split_mixed_datasets(tm, id="subjid", output_code=TRUE)
 filename = tempfile("mixed_code", fileext=".R")
-split_mixed_datasets(tm, id="SUBJID", output_code=filename)
+split_mixed_datasets(tm, id="subjid", output_code=filename)
 readLines(filename)
 }