diff --git a/R/data.R b/R/data.R
index a3b265bb..3d905321 100644
--- a/R/data.R
+++ b/R/data.R
@@ -50,10 +50,44 @@ NULL
 
 
 #' @name PAP.adh
-#' @title Biweekly Mean Therapy Adherence of OSA Patients over 1 Year
+#' @title Weekly Mean PAP Therapy Usage of OSA Patients in the First 3 Months
 #' @description
-#' A simulated longitudinal dataset comprising 500 patients with obstructive sleep apnea (OSA) during their
-#' first year on CPAP therapy.
+#' A simulated longitudinal dataset comprising 301 patients with obstructive sleep apnea (OSA) during their first 91 days (13 weeks) of PAP therapy.
+#' The longitudinal patterns were inspired by the adherence patterns reported by Yi et al. (2022), interpolated to weekly hours of usage.
+#' @format A `data.frame` comprising longitudinal data of 500 patients, each having 26 observations over a period of 1 year.
+#' Each row represents a patient observation interval (two weeks), with columns:
+#' \describe{
+#'   \item{Patient}{`integer`: The patient identifier, where each level represents a simulated patient.}
+#'   \item{Week}{`integer`: The week number, starting from 1.}
+#'   \item{UsageHours}{`numeric`: The mean hours of usage in the respective week.
+#'   Greater than or equal to zero, and typically around 4-6 hours.}
+#'   \item{Group}{`factor`: The reference group (i.e., adherence pattern) from which this patient was generated.}
+#' }
+#'
+#' \insertRef{yi2022identifying}{latrend}
+#' @seealso [latrend-data] [PAP.adh1y]
+#' @examples
+#' data(PAP.adh)
+#'
+#' if (require("ggplot2")) {
+#'   plotTrajectories(PAP.adh, id = "Patient", time = "Week", response = "UsageHours")
+#'
+#'   # plot according to cluster ground truth
+#'   plotTrajectories(
+#'     PAP.adh,
+#'     id = "Patient",
+#'     time = "Week",
+#'     response = "UsageHours",
+#'     cluster = "Group"
+#'   )
+#' }
+"PAP.adh"
+
+
+#' @name PAP.adh1y
+#' @title Biweekly Mean PAP Therapy Adherence of OSA Patients over 1 Year
+#' @description
+#' A simulated longitudinal dataset comprising 500 patients with obstructive sleep apnea (OSA) during their first year on CPAP therapy.
 #' The dataset contains the patient usage hours, averaged over 2-week periods.
 #'
 #' The daily usage data underlying the downsampled dataset was simulated based on 7 different adherence patterns.
@@ -77,25 +111,20 @@ NULL
 #' \insertRef{aloia2008time}{latrend}
 #' @seealso [latrend-data]
 #' @examples
-#' data(PAP.adh)
+#' data(PAP.adh1y)
 #'
 #' if (require("ggplot2")) {
-#'   plotTrajectories(PAP.adh, id = "Patient", time = "Biweek", response = "UsageHours")
+#'   plotTrajectories(PAP.adh1y, id = "Patient", time = "Biweek", response = "UsageHours")
 #'
 #'   # plot according to cluster ground truth
 #'   plotTrajectories(
-#'     PAP.adh,
+#'     PAP.adh1y,
 #'     id = "Patient",
 #'     time = "Biweek",
 #'     response = "UsageHours",
 #'     cluster = "Group"
 #'   )
 #' }
-"PAP.adh"
-
-#' @rdname PAP.adh
-#' @description The `PAP.adh1y` dataset is a subset of `PAP.adh`, comprising only patients who used therapy for at least 1 year.
-#' The subset does not contain the Non-users and Early drop-out groups.
 "PAP.adh1y"
 
 #' @export
diff --git a/data-raw/PAP.adh.R b/data-raw/PAP.adh.R
new file mode 100644
index 00000000..e76ae8d0
--- /dev/null
+++ b/data-raw/PAP.adh.R
@@ -0,0 +1,116 @@
+library(magrittr)
+library(assertthat)
+library(data.table)
+library(latrend)
+
+# Cluster 1: "adherers"
+# y = 385, 326, 281
+# Cluster 2: "improvers"
+# y = 256, 297, 365
+# Cluster 3: "non-adherers"
+# y = 175, 137, 107
+
+# convert daily usage-hour variance to weekly usage minutes SD
+matrix(rnorm(1e6 * 7L, sd = 1.5 * 60), ncol = 1e6L) %>% colMeans() %>% sd()
+
+# define group trajectories
+groupTrajMat = cbind(
+  Adherers = approx(x = c(1, 4, 13), y = c(385, 328, 281), xout = 1:13, method = 'linear')$y,
+  Improvers = approx(x = c(1, 4, 13), y = c(256, 293, 365), xout = 1:13, method = 'linear')$y,
+  `Non-adherers` = approx(x = c(1, 4, 13), y = c(176, 138, 108), xout = 1:13, method = 'linear')$y
+)
+
+cluster1Data = generateLongData(
+  sizes = 162L,
+  id = 'Patient',
+  cluster = ~ Week + Adherers,
+  random = ~ 1,
+  data = data.frame(Week = 1:13, Adherers = groupTrajMat[, 'Adherers']),
+  clusterCoefs = cbind(c(0, 0, 1)),
+  clusterNames = 'Adherer',
+  randomScales = cbind(62.7),
+  noiseScales = 23,
+  seed = 1L
+)
+
+plotTrajectories(cluster1Data, time = 'Week', id = 'Patient', cluster = 'Class', response = 'Value') +
+  expand_limits(y = 0) +
+  scale_x_continuous(breaks = seq(1, 13, by = 2))
+
+cluster2Data = generateLongData(
+  sizes = 56L,
+  id = 'Patient',
+  cluster = ~ Week + Adherers,
+  random = ~ 1,
+  data = data.frame(Week = 1:13, Adherers = groupTrajMat[, 'Improvers']),
+  clusterCoefs = cbind(c(0, 0, 1)),
+  clusterNames = 'Improver',
+  randomScales = cbind(68.9),
+  noiseScales = 43,
+  seed = 2L
+) %>%
+  .[, Patient := Patient + max(cluster1Data$Patient)]
+
+cluster3Data = generateLongData(
+  sizes = 83L,
+  id = 'Patient',
+  cluster = ~ Week + Adherers,
+  random = ~ 1,
+  data = data.frame(Week = 1:13, Adherers = groupTrajMat[, 'Non-adherers']),
+  clusterCoefs = cbind(c(0, 0, 1)),
+  clusterNames = 'Non-adherer',
+  randomScales = cbind(53.7),
+  noiseScales = 34,
+  seed = 3L
+) %>%
+  .[, Patient := Patient + max(cluster2Data$Patient)]
+
+dataset = rbind(cluster1Data, cluster2Data, cluster3Data) %>%
+  .[, UsageHours := fifelse(Value > 0, Value / 60, 0)] %>%
+  setnames('Class', 'Group')
+
+plotTrajectories(dataset, time = 'Week', id = 'Patient', cluster = 'Group', response = 'UsageHours') +
+  expand_limits(y = 0) +
+  scale_x_continuous(breaks = seq(1, 13, by = 2))
+
+PAP.adh = subset(dataset, select = c('Patient', 'Week', 'UsageHours', 'Group')) %>%
+  as.data.frame()
+head(PAP.adh)
+stopifnot(uniqueN(PAP.adh$Patient) == 301)
+
+usethis::use_data(PAP.adh, overwrite = TRUE)
+
+
+# parallel
+nCores <- parallel::detectCores(logical = FALSE)
+if (.Platform$OS.type == "windows") {
+  cl <- parallel::makeCluster(nCores)
+  doParallel::registerDoParallel(cl)
+} else {
+  doMC::registerDoMC(nCores)
+}
+
+# test gbtm
+options(latrend.id = "Patient", latrend.time = "Week")
+gbtmMethod <- lcMethodLcmmGBTM(
+  fixed = UsageHours ~ Week,
+  mixture = ~ Week,
+  maxiter = 20, #not recommended; used for speed
+  idiag = TRUE
+)
+gbtmMethods <- lcMethods(gbtmMethod, nClusters = 1:5)
+gbtmList <- latrendBatch(gbtmMethods, data = PAP.adh, parallel = TRUE)
+
+plotMetric(gbtmList, c("Dunn", "WMAE", "BIC", "estimationTime"))
+
+# test gmm
+gmmMethod <- lcMethodLcmmGMM(
+  fixed = UsageHours ~ Week,
+  mixture = ~ Week,
+  idiag = TRUE
+)
+gmmMethods <- lcMethods(gmmMethod, nClusters = 1:5)
+system.time({
+  gmmList <- latrendBatch(gmmMethods, data = PAP.adh, parallel = TRUE)
+})
+plotMetric(gmmList, c("Dunn", "WMAE", "BIC", "estimationTime"))
diff --git a/data-raw/osa-adherence-data.R b/data-raw/PAP.adh1y.R
similarity index 95%
rename from data-raw/osa-adherence-data.R
rename to data-raw/PAP.adh1y.R
index 0b26daaf..2bc698a9 100644
--- a/data-raw/osa-adherence-data.R
+++ b/data-raw/PAP.adh1y.R
@@ -245,13 +245,5 @@ plotTrajectories(dataset, id = 'Patient', time = 'Biweek', response = 'UsageHour
 dataset[, Biweek := as.integer(Biweek)]
 dataset[, MaxDay := as.integer(MaxDay)]
 
-PAP.adh = as.data.frame(dataset)
-usethis::use_data(PAP.adh, overwrite = TRUE)
-
-# PAP.adh1y
-PAP.adh1y = as.data.frame(
-  dataset[not(Group %in% c('Early drop-outs', 'Non-users'))]
-)
-PAP.adh1y$Patient = factor(PAP.adh1y$Patient)
-PAP.adh1y$Group = factor(PAP.adh1y$Group)
+PAP.adh1y = as.data.frame(dataset)
 usethis::use_data(PAP.adh1y, overwrite = TRUE)
diff --git a/data/PAP.adh.rda b/data/PAP.adh.rda
index 74e8a61d..be55ac0b 100644
Binary files a/data/PAP.adh.rda and b/data/PAP.adh.rda differ
diff --git a/data/PAP.adh1y.rda b/data/PAP.adh1y.rda
index c9f6b7fb..3f88bbb3 100644
Binary files a/data/PAP.adh1y.rda and b/data/PAP.adh1y.rda differ
diff --git a/inst/REFERENCES.bib b/inst/REFERENCES.bib
index 2667c868..0d8f0d44 100644
--- a/inst/REFERENCES.bib
+++ b/inst/REFERENCES.bib
@@ -434,4 +434,16 @@ @Article{denteuling2021comparison
   timestamp = {2021-03-25},
 }
 
+@Article{yi2022identifying,
+  author           = {Yi, Huijie and Dong, Xiaosong and Shang, Shaomei and Zhang, Chi and Xu, Liyue and Han, Fang},
+  journal          = {Frontiers in Neurology},
+  title            = {Identifying longitudinal patterns of {CPAP} treatment in {OSA} using growth mixture modeling: Disease characteristics and psychological determinants},
+  year             = {2022},
+  month            = nov,
+  pages            = {1063461},
+  volume           = {13},
+  doi              = {10.3389/fneur.2022.1063461},
+  modificationdate = {2023-03-10T11:31:38},
+}
+
 @Comment{jabref-meta: databaseType:bibtex;}
diff --git a/man/PAP.adh.Rd b/man/PAP.adh.Rd
index ffe71c16..82cdb497 100644
--- a/man/PAP.adh.Rd
+++ b/man/PAP.adh.Rd
@@ -3,65 +3,44 @@
 \docType{data}
 \name{PAP.adh}
 \alias{PAP.adh}
-\alias{PAP.adh1y}
-\title{Biweekly Mean Therapy Adherence of OSA Patients over 1 Year}
+\title{Weekly Mean PAP Therapy Usage of OSA Patients in the First 3 Months}
 \format{
 A \code{data.frame} comprising longitudinal data of 500 patients, each having 26 observations over a period of 1 year.
 Each row represents a patient observation interval (two weeks), with columns:
 \describe{
-\item{Patient}{\code{factor}: The patient identifier, where each level represents a simulated patient.}
-\item{Biweek}{\code{integer}: Two-week interval index. Starts from 1.}
-\item{MaxDay}{\code{integer}: The last day used for the aggregation of the respective interval, \code{integer}}
+\item{Patient}{\code{integer}: The patient identifier, where each level represents a simulated patient.}
+\item{Week}{\code{integer}: The week number, starting from 1.}
 \item{UsageHours}{\code{numeric}: The mean hours of usage in the respective week.
 Greater than or equal to zero, and typically around 4-6 hours.}
 \item{Group}{\code{factor}: The reference group (i.e., adherence pattern) from which this patient was generated.}
 }
 
-An object of class \code{data.frame} with 9880 rows and 5 columns.
-}
-\source{
-This dataset was generated based on the cluster-specific descriptive statistics table provided in Aloia et al. (2008),
-with some adjustments made in order to improve cluster separation for demonstration purposes.
-
-\insertRef{aloia2008time}{latrend}
+\insertRef{yi2022identifying}{latrend}
 }
 \usage{
 PAP.adh
-
-PAP.adh1y
 }
 \description{
-A simulated longitudinal dataset comprising 500 patients with obstructive sleep apnea (OSA) during their
-first year on CPAP therapy.
-The dataset contains the patient usage hours, averaged over 2-week periods.
-
-The daily usage data underlying the downsampled dataset was simulated based on 7 different adherence patterns.
-The defined adherence patterns were inspired by the adherence patterns identified by Aloia et al. (2008), with slight adjustments
-
-The \code{PAP.adh1y} dataset is a subset of \code{PAP.adh}, comprising only patients who used therapy for at least 1 year.
-The subset does not contain the Non-users and Early drop-out groups.
-}
-\note{
-This dataset is only intended for demonstration purposes.
-While the data format will remain the same, the data content is subject to change in future versions.
+A simulated longitudinal dataset comprising 301 patients with obstructive sleep apnea (OSA) during their first 91 days (13 weeks) of PAP therapy.
+The longitudinal patterns were inspired by the adherence patterns reported by Yi et al. (2022), interpolated to weekly hours of usage.
 }
 \examples{
 data(PAP.adh)
 
 if (require("ggplot2")) {
-  plotTrajectories(PAP.adh, id = "Patient", time = "Biweek", response = "UsageHours")
+  plotTrajectories(PAP.adh, id = "Patient", time = "Week", response = "UsageHours")
 
   # plot according to cluster ground truth
   plotTrajectories(
     PAP.adh,
     id = "Patient",
-    time = "Biweek",
+    time = "Week",
     response = "UsageHours",
     cluster = "Group"
   )
 }
 }
 \seealso{
-\link{latrend-data}
+\link{latrend-data} \link{PAP.adh1y}
 }
 \keyword{datasets}
diff --git a/man/PAP.adh1y.Rd b/man/PAP.adh1y.Rd
new file mode 100644
index 00000000..b9fb069c
--- /dev/null
+++ b/man/PAP.adh1y.Rd
@@ -0,0 +1,58 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/data.R
+\docType{data}
+\name{PAP.adh1y}
+\alias{PAP.adh1y}
+\title{Biweekly Mean PAP Therapy Adherence of OSA Patients over 1 Year}
+\format{
+A \code{data.frame} comprising longitudinal data of 500 patients, each having 26 observations over a period of 1 year.
+Each row represents a patient observation interval (two weeks), with columns:
+\describe{
+\item{Patient}{\code{factor}: The patient identifier, where each level represents a simulated patient.}
+\item{Biweek}{\code{integer}: Two-week interval index. Starts from 1.}
+\item{MaxDay}{\code{integer}: The last day used for the aggregation of the respective interval, \code{integer}}
+\item{UsageHours}{\code{numeric}: The mean hours of usage in the respective week.
+Greater than or equal to zero, and typically around 4-6 hours.}
+\item{Group}{\code{factor}: The reference group (i.e., adherence pattern) from which this patient was generated.}
+}
+}
+\source{
+This dataset was generated based on the cluster-specific descriptive statistics table provided in Aloia et al. (2008),
+with some adjustments made in order to improve cluster separation for demonstration purposes.
+
+\insertRef{aloia2008time}{latrend}
+}
+\usage{
+PAP.adh1y
+}
+\description{
+A simulated longitudinal dataset comprising 500 patients with obstructive sleep apnea (OSA) during their first year on CPAP therapy.
+The dataset contains the patient usage hours, averaged over 2-week periods.
+
+The daily usage data underlying the downsampled dataset was simulated based on 7 different adherence patterns.
+The defined adherence patterns were inspired by the adherence patterns identified by Aloia et al. (2008), with slight adjustments
+}
+\note{
+This dataset is only intended for demonstration purposes.
+While the data format will remain the same, the data content is subject to change in future versions.
+}
+\examples{
+data(PAP.adh1y)
+
+if (require("ggplot2")) {
+  plotTrajectories(PAP.adh1y, id = "Patient", time = "Biweek", response = "UsageHours")
+
+  # plot according to cluster ground truth
+  plotTrajectories(
+    PAP.adh1y,
+    id = "Patient",
+    time = "Biweek",
+    response = "UsageHours",
+    cluster = "Group"
+  )
+}
+}
+\seealso{
+\link{latrend-data}
+}
+\keyword{datasets}
diff --git a/man/plot-lcModel-method.Rd b/man/plot-lcModel-method.Rd
index 2085975b..36751c4b 100644
--- a/man/plot-lcModel-method.Rd
+++ b/man/plot-lcModel-method.Rd
@@ -6,7 +6,7 @@
 \alias{plot,lcModel-method}
 \title{Plot a lcModel}
 \usage{
-\S4method{plot}{lcModel}(x, y, ...)
+\S4method{plot}{lcModel,ANY}(x, y, ...)
 }
 \arguments{
 \item{x}{The \code{lcModel} object.}
diff --git a/man/plot-lcModels-method.Rd b/man/plot-lcModels-method.Rd
index 160f09eb..4534a076 100644
--- a/man/plot-lcModels-method.Rd
+++ b/man/plot-lcModels-method.Rd
@@ -6,7 +6,7 @@
 \alias{plot,lcModels-method}
 \title{Grid plot for a list of models}
 \usage{
-\S4method{plot}{lcModels}(x, y, ..., subset, gridArgs = list())
+\S4method{plot}{lcModels,ANY}(x, y, ..., subset, gridArgs = list())
 }
 \arguments{
 \item{x}{The \code{lcModels} object.}
diff --git a/tests/testthat/test-data.R b/tests/testthat/test-data.R
index ebf098f9..9717a63d 100644
--- a/tests/testthat/test-data.R
+++ b/tests/testthat/test-data.R
@@ -2,35 +2,48 @@ test_that('PAP.adh structure', {
   data(PAP.adh)
 
   expect_is(PAP.adh, 'data.frame')
-  expect_named(PAP.adh, c('Patient', 'Biweek', 'MaxDay', 'UsageHours', 'Group'))
-  expect_is(PAP.adh$Patient, 'factor')
-  expect_is(PAP.adh$Biweek, 'integer')
-  expect_is(PAP.adh$MaxDay, 'integer')
+  expect_named(PAP.adh, c('Patient', 'Week', 'UsageHours', 'Group'))
+  expect_is(PAP.adh$Patient, 'integer')
+  expect_is(PAP.adh$Week, 'integer')
   expect_is(PAP.adh$UsageHours, 'numeric')
   expect_is(PAP.adh$Group, 'factor')
 })
 
 test_that('PAP.adh content', {
-  expect_gte(min(PAP.adh$UsageHours), 0)
-  expect_true(noNA(PAP.adh$Patient))
-  expect_equal(uniqueN(PAP.adh$Patient), nlevels(PAP.adh$Patient))
-  expect_equal(uniqueN(PAP.adh$Group), nlevels(PAP.adh$Group))
-  expect_true(noNA(PAP.adh$Biweek))
-  expect_true(noNA(PAP.adh$UsageHours))
-  expect_equal(min(PAP.adh$Biweek), 1)
-  expect_equal(max(PAP.adh$Biweek), 26)
+  with(PAP.adh, {
+    expect_gte(min(UsageHours), 0)
+    expect_true(noNA(Patient))
+    expect_equal(uniqueN(Patient), 301)
+    expect_equal(nlevels(Group), 3)
+    expect_equal(uniqueN(Group), nlevels(Group))
+    expect_true(noNA(Week))
+    expect_true(noNA(UsageHours))
+    expect_equal(min(Week), 1)
+    expect_equal(max(Week), 13)
+  })
 })
 
 test_that('PAP.adh1y', {
-  data(PAP.adh)
   data(PAP.adh1y)
 
-  expect_lt(nlevels(PAP.adh1y$Patient), nlevels(PAP.adh$Patient))
-  expect_lt(nlevels(PAP.adh1y$Group), nlevels(PAP.adh$Group))
-
-  # check for empty levels
-  expect_equal(uniqueN(PAP.adh1y$Patient), nlevels(PAP.adh1y$Patient))
-  expect_equal(uniqueN(PAP.adh1y$Group), nlevels(PAP.adh1y$Group))
+  expect_is(PAP.adh1y, 'data.frame')
+  expect_named(PAP.adh1y, c('Patient', 'Biweek', 'MaxDay', 'UsageHours', 'Group'))
+  expect_is(PAP.adh1y$Patient, 'factor')
+  expect_is(PAP.adh1y$Biweek, 'integer')
+  expect_is(PAP.adh1y$MaxDay, 'integer')
+  expect_is(PAP.adh1y$UsageHours, 'numeric')
+  expect_is(PAP.adh1y$Group, 'factor')
+})
 
-  expect_true(all(levels(PAP.adh1y) %in% levels(PAP.adh)))
+test_that('PAP.adh1y content', {
+  with(PAP.adh1y, {
+    expect_gte(min(UsageHours), 0)
+    expect_true(noNA(Patient))
+    expect_equal(uniqueN(Patient), nlevels(Patient))
+    expect_equal(uniqueN(Group), nlevels(Group))
+    expect_true(noNA(Biweek))
+    expect_true(noNA(UsageHours))
+    expect_equal(min(Biweek), 1)
+    expect_equal(max(Biweek), 26)
+  })
 })