\documentclass[aspectratio=169]{beamer}

\usepackage{listings}
\usepackage[utf8,latin1]{inputenc}
\usepackage[style = apa, backend = biber, natbib = true]{biblatex}
\usepackage{tikz}
\addbibresource{lit.bib}

\makeatletter \def\newblock{\beamer@newblock} \makeatother

\beamertemplatenavigationsymbolsempty
\setbeamertemplate{itemize items}[circle]
\setbeamertemplate{section in toc}[circle]
\mode<beamer>{\setbeamercolor{math text displayed}{fg=iwmgray}}
\setbeamercolor{block body}{bg=iwmorange!50!white}
\setbeamercolor{block title}{fg=white, bg=iwmorange}

% Definitions for biblatex
\setbeamercolor{bibliography entry note}{fg=iwmgray}
\setbeamercolor{bibliography entry author}{fg=iwmgray}
\setbeamertemplate{bibliography item}{}

\definecolor{iwmorange}{RGB}{255,105,0}
\definecolor{iwmgray}{RGB}{67,79,79}
\definecolor{iwmblue}{RGB}{60,180,220}
\definecolor{iwmgreen}{RGB}{145,200,110}
\definecolor{iwmpurple}{RGB}{120,0,75}

\setbeamercolor{title}{fg=iwmorange}
\setbeamercolor{frametitle}{fg=iwmorange}
\setbeamercolor{structure}{fg=iwmorange}
\setbeamercolor{normal text}{fg=iwmgray}
\setbeamercolor{author}{fg=iwmgray}
\setbeamercolor{date}{fg=iwmgray}

\lstset{language = R,%
  basicstyle = \ttfamily\color{iwmgray},
  frame = single,
  rulecolor = \color{iwmgray},
  commentstyle = \slshape\color{iwmgreen},
  keywordstyle = \bfseries\color{iwmgray},
  identifierstyle = \color{iwmpurple},
  stringstyle = \color{iwmblue},
  numbers = none,%left,numberstyle = \tiny,
  basewidth = {.5em, .4em},
  showstringspaces = false,
  emphstyle = \color{red!50!white}}

\title{Introduction to mixed-effects models}
\subtitle{(for longitudinal data)}
\author{Nora Wickelmaier}
\institute{\includegraphics[scale=.2]{../figures/iwm_logo_rgb}}
\date{2026-04-28}

\AtBeginSection[]{
  \frame{
    \tableofcontents[sectionstyle=show/hide, subsectionstyle=show/show/hide]}}

\setbeamertemplate{headline}{
 \begin{beamercolorbox}{section in head}
   \vskip5pt\insertsectionnavigationhorizontal{\paperwidth}{}{}\vskip2pt
 \end{beamercolorbox}
}

\setbeamertemplate{footline}{\vskip-2pt\hfill\insertframenumber$\;$\vskip2pt}

\begin{document}

\begin{frame}{}
\thispagestyle{empty}
\titlepage
\end{frame}

\begin{frame}{Plan for today}
  \begin{itemize}[<+->]
    \item We will walk through an example for a longitudinal data set (6 time
      points per subject)
    \item I will explain the general concepts with the slides
    \item We will switch to R and use the lme4 package to fit the models
    \item You will use R to fit the model and try out different specifications
    \item We will discuss the results
    \item All the materials are here:
      \url{https://gitea.iwm-tuebingen.de/nwickelmaier/lead_longitudinal}
      \\~\\
    \item[$\to$] Try to code along in R! Ask as many questions as possible
  \end{itemize}
\end{frame}

\begin{frame}{Outline}
\tableofcontents
\end{frame}

\section[Introduction]{Introduction to longitudinal data}

\begin{frame}[fragile]{Longitudinal data}
  \begin{itemize}
    \item Consist of repeated measurements on the same subject taken over time
    \item Are a frequent use case for mixed-effects models
    \item Contain time as a predictor:
          time trends within and between subjects are of interest
  \end{itemize}
  \begin{lstlisting}
library("lme4")
data("sleepstudy")
?sleepstudy
str(sleepstudy)
summary(sleepstudy)
head(sleepstudy)
  \end{lstlisting}
\nocite{Bates10lme4, Bates15}
\end{frame}

\begin{frame}{Sleep study}
  \begin{itemize}
    \item Average reaction time per day for subjects in a sleep deprivation
      study
    \item On day 0, the subjects had their normal amount of sleep
    \item Starting that night they were restricted to 3 hours of sleep per
      night
    \item Observations represent the average reaction time on a series of
      tests given each day to each subject
  \end{itemize}

  \vfill
  A data frame with 180 observations on the following 3 variables\\~\\

  \begin{tabular}{ll}
    \hline
     \texttt{Reaction} & Average reaction time (ms) \\
     \texttt{Days} & Number of days of sleep deprivation \\
     \texttt{Subject} & Subject number on which the observation was made \\
     \hline
  \end{tabular}
\end{frame}


\begin{frame}[fragile]{Visualization of data}
  \begin{columns}
    \begin{column}{.53\textwidth}
      \includegraphics[scale=.8]{../figures/sleep_box}
    \end{column}
    \begin{column}{.55\textwidth}
\begin{lstlisting}
boxplot(Reaction ~ Days, sleepstudy)
\end{lstlisting}
    \end{column}
  \end{columns}
\end{frame}

\begin{frame}[fragile]{Visualization of individual data}
  \begin{columns}
    \begin{column}{.53\textwidth}
      \includegraphics[scale=.5]{../figures/sleep_subjects}
    \end{column}
    \begin{column}{.55\textwidth}
\begin{lstlisting}
library("lattice")

xyplot(Reaction ~ Days | Subject,
  data = sleepstudy,
  type = c("g", "b"),
  xlab = "Days of sleep deprivation",
  ylab = "Average reaction time (ms)",
  aspect = "xy")
\end{lstlisting}
    \end{column}
  \end{columns}
\end{frame}

\begin{frame}{Random intercept model}
  \begin{columns}
    \begin{column}{.5\textwidth}
  \begin{itemize}
\item The random intercept model adds a random intercept for each subject
\[
  y_{ij} = \beta_0 + \beta_1\,Days_{ij} + \upsilon_{0i} + \varepsilon_i
\]
with $\upsilon_{0i} \overset{iid}{\sim} N(0, \sigma^2_{\upsilon})$,
      $\varepsilon_{ij} \overset{iid}{\sim} N(0, \sigma^2_\varepsilon)$
    \item The slope is identical for each subject (and the population)
  \end{itemize}
      \vspace{2.2cm}
    \end{column}
    \begin{column}{.5\textwidth}
      \includegraphics[scale=.5]{../figures/sleep_random_intercept}
    \end{column}
  \end{columns}
\end{frame}


\begin{frame}{Fixed and random effects for random intercept model}
% m1 <- lmer(Reaction ~ Days + (1 | Subject), sleepstudy)
% tab <- cbind(
%   sleepstudy[, c("Subject", "Days", "Reaction")],
%   yhat = fixef(m1)["(Intercept)"] +
%          fixef(m1)["Days"] * sleepstudy[["Days"]] +
%          ranef(m1)[["Subject"]][["(Intercept)"]][sleepstudy[["Subject"]]] +
%          resid(m1),
%   Intercept = fixef(m1)["(Intercept)"],
%   Slope = fixef(m1)["Days"] * sleepstudy[["Days"]],
%   SubInt = ranef(m1)[["Subject"]][["(Intercept)"]][sleepstudy[["Subject"]]],
%   Resid = resid(m1)
% )
% tab <- cbind(
%   sleepstudy[, c("Subject", "Days", "Reaction")],
%   Intercept = fixef(m1)["(Intercept)"] |> unname(),
%   Slope = fixef(m1)["Days"] |> unname(),
%   SubInt = ranef(m1)[["Subject"]][["(Intercept)"]][sleepstudy[["Subject"]]],
%   Resid = resid(m1)
% )
% print(
%   xtable(tab[tab$Subject %in% c("308", "309", "310"), ],
%          digits = c(NA, 0, 0, 0, 1, 1, 1, 1)),
%   include.rownames = FALSE, math.style.negative = TRUE)
% )
% latex table generated in R 4.5.2 by xtable 1.8-8 package
% Thu Mar  5 11:18:32 2026
\centering\footnotesize
\begin{tabular}{ccccccc}
  \hline
 Subject & Days & Reaction & Fixed     &       & Random &       \\
 \cline{4-5}
 \cline{6-7}
         &      &          & Intercept & Slope & SubInt & Resid \\
  \hline
 308 & 0 & 250 & 251.4 & 10.5 & 40.8 & $-$42.6 \\
 308 & 1 & 259 & 251.4 & 10.5 & 40.8 & $-$44.0 \\
 308 & 2 & 251 & 251.4 & 10.5 & 40.8 & $-$62.3 \\
  \vdots & \vdots & \vdots & \vdots & \vdots & \vdots & \vdots\\
 308 & 8 & 431 & 251.4 & 10.5 & 40.8 & 54.7 \\
 308 & 9 & 466 & 251.4 & 10.5 & 40.8 & 80.0 \\
  \hline
 309 & 0 & 223 & 251.4 & 10.5 & $-$77.8 & 49.2 \\
 309 & 1 & 205 & 251.4 & 10.5 & $-$77.8 & 21.2 \\
 309 & 2 & 203 & 251.4 & 10.5 & $-$77.8 & 8.5 \\
  \vdots & \vdots & \vdots & \vdots & \vdots & \vdots & \vdots\\
  \hline
 310 & 0 & 199 & 251.4 & 10.5 & $-$63.1 & 10.8 \\
 310 & 1 & 194 & 251.4 & 10.5 & $-$63.1 & $-$4.4 \\
 310 & 2 & 234 & 251.4 & 10.5 & $-$63.1 & 25.1 \\
  \vdots & \vdots & \vdots & \vdots & \vdots & \vdots & \vdots\\
   \hline
     &   &   &   &   & $\sigma^2_{\upsilon}$ & $\sigma^2_\varepsilon$\\
\end{tabular}
\end{frame}

\begin{frame}[fragile]{Random slope model}
  \begin{columns}
    \begin{column}{.5\textwidth}
  \begin{itemize}
\item The random slope model adds a random intercept and a random slope for each
  subject
\[
  y_{ij} = \beta_0 + \beta_1\,Days_{ij} + \upsilon_{0i} +
      \upsilon_{1i}\,Days_{ij} + \varepsilon_{ij}
\]
with
\begin{align*}
  \begin{pmatrix} \upsilon_{0i}\\ \upsilon_{1i} \end{pmatrix} &\overset{iid}{\sim}
    N \left(\begin{pmatrix} 0\\ 0 \end{pmatrix}, \, \mathbf{\Sigma}_\upsilon =
      \begin{pmatrix}
        \sigma^2_{\upsilon_0} & \sigma_{\upsilon_0 \upsilon_1} \\
        \sigma_{\upsilon_0 \upsilon_1} & \sigma^2_{\upsilon_1} \\
      \end{pmatrix} \right)
    \\
  \varepsilon_{ij} & \overset{iid}{\sim} N(0, \sigma^2_\varepsilon)
\end{align*}
      \vspace{-.5cm}
    \item Individual slopes for each subject
  \end{itemize}
    \end{column}
    \begin{column}{.5\textwidth}
      \includegraphics[scale=.5]{../figures/sleep_random_slope}
    \end{column}
  \end{columns}
\end{frame}


\begin{frame}{Fixed and random effects for random slope model}
% m2 <- lmer(Reaction ~ Days + (Days | Subject), sleepstudy)
% tab <- cbind(
%   sleepstudy[, c("Subject", "Days", "Reaction")],
%   yhat = fixef(m2)["(Intercept)"] +
%          fixef(m2)["Days"] * sleepstudy[["Days"]] +
%          ranef(m2)[["Subject"]][["(Intercept)"]][sleepstudy[["Subject"]]] +
%          ranef(m2)[["Subject"]][["Days"]][sleepstudy[["Subject"]]] *
%                     sleepstudy[["Days"]] +
%          resid(m2),
%   Intercept = fixef(m2)["(Intercept)"],
%   Slope = fixef(m2)["Days"] * sleepstudy[["Days"]],
%   SubInt = ranef(m2)[["Subject"]][["(Intercept)"]][sleepstudy[["Subject"]]],
%   SubSlp = ranef(m2)[["Subject"]][["Days"]][sleepstudy[["Subject"]]] *
%                     sleepstudy[["Days"]],
%   Resid = resid(m2)
% )
% tab <- cbind(
%   sleepstudy[, c("Subject", "Days", "Reaction")],
%   Intercept = fixef(m2)["(Intercept)"] |> unname(),
%   Slope = fixef(m2)["Days"] |> unname(),
%   SubInt = ranef(m2)[["Subject"]][["(Intercept)"]][sleepstudy[["Subject"]]],
%   SubSlp = ranef(m2)[["Subject"]][["Days"]][sleepstudy[["Subject"]]],
%   Resid = resid(m2)
% )
% print(
%   xtable(tab[tab$Subject %in% c("308", "309", "310"), ],
%          digits = c(NA, 0, 0, 0, 1, 1, 1, 1, 1)),
%   include.rownames = FALSE, math.style.negative = TRUE)
% )
% latex table generated in R 4.5.2 by xtable 1.8-8 package
% Thu Mar  5 11:18:32 2026
\centering\footnotesize
\begin{tabular}{cccccccc}
  \hline
 Subject & Days & Reaction & Fixed     &       & Random &       & \\
 \cline{4-5}
 \cline{6-8}
         &      &          & Intercept & Slope & SubInt & SubSlp & Resid \\
  \hline
 308 & 0 & 250 & 251.4 & 10.5 & 2.3 & 9.2 & $-$4.1 \\
 308 & 1 & 259 & 251.4 & 10.5 & 2.3 & 9.2 & $-$14.6 \\
 308 & 2 & 251 & 251.4 & 10.5 & 2.3 & 9.2 & $-$42.2 \\
  \vdots & \vdots & \vdots & \vdots & \vdots & \vdots & \vdots & \vdots \\
 308 & 8 & 431 & 251.4 & 10.5 & 2.3 & 9.2 & 19.6 \\
 308 & 9 & 466 & 251.4 & 10.5 & 2.3 & 9.2 & 35.7 \\
  \hline
 309 & 0 & 223 & 251.4 & 10.5 & $-$40.4 & $-$8.6 & 11.7 \\
 309 & 1 & 205 & 251.4 & 10.5 & $-$40.4 & $-$8.6 & $-$7.6 \\
 309 & 2 & 203 & 251.4 & 10.5 & $-$40.4 & $-$8.6 & $-$11.7 \\
  \vdots & \vdots & \vdots & \vdots & \vdots & \vdots & \vdots & \vdots \\
  \hline
 310 & 0 & 199 & 251.4 & 10.5 & $-$39.0 & $-$5.4 & $-$13.4 \\
 310 & 1 & 194 & 251.4 & 10.5 & $-$39.0 & $-$5.4 & $-$23.1 \\
 310 & 2 & 234 & 251.4 & 10.5 & $-$39.0 & $-$5.4 & 11.8 \\
 \vdots & \vdots & \vdots & \vdots & \vdots & \vdots & \vdots & \vdots \\
   \hline
 &&&&& $\sigma^2_{\upsilon_0}$ & $\sigma^2_{\upsilon_1}$ &
       $\sigma^2_\varepsilon$\\[-6pt]
 &&&&& \multicolumn{2}{c}{$\sigma_{\upsilon_0\upsilon_1}$} & \\
\end{tabular}
\end{frame}

\begin{frame}{Partial pooling}
  \begin{columns}
    \begin{column}{.5\textwidth}
      \includegraphics[scale=.5]{../figures/sleep_shrinkfit}
    \end{column}
    \begin{column}{.5\textwidth}
      \begin{itemize}
        \item Within-subject regression line shows regression line fitted to
          data for each individual
        \item Population regression line shows fixed effects for mixed-effects
          model
        \item Mixed model regression line shows individual regression lines as
          predicted by mixed-effects models
      \end{itemize}
    \end{column}
  \end{columns}
\end{frame}

\section[Growth curve model]{Example: Depression and Imipramin}


\begin{frame}{Quadratic time trends}
  \begin{columns}
    \begin{column}{.35\textwidth}
    \begin{itemize}
    \item A lot of times the assumption of a linear time trend is too
      simple
    \item Change is not happening unbraked linearly but flattens out
    \end{itemize}
    \end{column}
    \begin{column}{.65\textwidth}
      \includegraphics[width=9cm]{../figures/quad}
    \end{column}
  \end{columns}
\end{frame}

\begin{frame}{Quadratic time trends}
  \begin{itemize}
    \item Quadratic regression model
\begin{align*}
  y_{ij} &= b_{0i} + b_{1i}\,t_{ij} + b_{2i}\,t^2_{ij} + \varepsilon_{ij}\\
         &= b_{0i} + (b_{1i} + b_{2i}\,t_{ij}) t_{ij}  + \varepsilon_{ij}
\end{align*}
    \item The linear change depends on time $t$
\[
  \frac{\partial y}{\partial t} = b_{1i} + 2b_{2i} \, t
\]
    \item The intercept $t = -b_{1i}/(2 b_{2i})$ is the point in time when a
      positive (negative) trend becomes negative (postive)
  \end{itemize}
\end{frame}

\begin{frame}{Depression and Imipramin \citep{ReisbyGram77}}
  \begin{itemize}
    \item \citet{ReisbyGram77} studied the effect of Imipramin on 66
      inpatients treated for depression
    \item Depression was measured with the Hamilton depression rating scale
      (HDRS)
    \item Additionally, the concentration of Imipramin and its metabolite
      Desipramin was measured in their blood plasma
    \item Patients were classified into endogenous and non-endogenous
      depressed
    \item Depression was measured weekly for 6 time points; the effect of
      the antidepressant was observed starting at week 2 for four weeks
  \end{itemize}
  \vfill
\end{frame}

\begin{frame}{Descriptive statistics}
\begin{columns}
\begin{column}{.55\textwidth}
  \includegraphics[scale=.8]{../figures/hdrs-box}
\end{column}
\begin{column}{.6\textwidth}
  HDRS score\\[1ex]
  {\footnotesize
\begin{tabular}{rrrrrrr}
  \hline
  $t$ & W0 & W1 & W2 & W3 & W4 & W5 \\
  \hline
  $M$  & 23.44 & 21.84 & 18.31 & 16.42 & 13.62 & 11.95 \\
  $SD$ &  4.53 & 4.70  & 5.49  & 6.42  & 6.97  & 7.22 \\
  $n$  & 61    & 63    & 65    & 65    & 63    & 58    \\
  \hline
\end{tabular}
  }

  \vspace{.5cm}
  Empirical correlation matrix of HDRS score\\[1ex]
  {\footnotesize
\begin{tabular}{rrrrrrr}
  \hline
   & W0 & W1 & W2 & W3 & W4 & W5 \\
  \hline
  Week 0 &   1 & .49 & .41 & .33 & .23 & .18 \\
  Week 1 & .49 &   1 & .49 & .41 & .31 & .22 \\
  Week 2 & .41 & .49 &   1 & .74 & .67 & .46 \\
  Week 3 & .33 & .41 & .74 &   1 & .82 & .57 \\
  Week 4 & .23 & .31 & .67 & .82 &   1 & .65 \\
  Week 5 & .18 & .22 & .46 & .57 & .65 &   1 \\
  \hline
\end{tabular}
  }

  \vspace{1cm}
\end{column}
\end{columns}
\end{frame}

\begin{frame}{Predictions random slope model}
  \begin{columns}
    \begin{column}{.6\textwidth}
    \includegraphics[scale=.5]{../figures/hdrs-ind_pred-randomslope}
    \end{column}
  \begin{column}{.4\textwidth}
  \[
    y_{ij} = \beta_0 + \beta_1 time + \upsilon_{0i} + \upsilon_{1i} time +
    \varepsilon_{ij}
  \]
with
\begin{align*}
  \begin{pmatrix} \upsilon_{0i}\\ \upsilon_{1i} \end{pmatrix} &\overset{iid}\sim
    N \left(\begin{pmatrix} 0\\ 0 \end{pmatrix}, \, \boldsymbol{\Sigma}_\upsilon =
      \begin{pmatrix}
        \sigma^2_{\upsilon_0} & \sigma_{\upsilon_0 \upsilon_1} \\
        \sigma_{\upsilon_0 \upsilon_1} & \sigma^2_{\upsilon_1} \\
      \end{pmatrix} \right)\\
  \boldsymbol{\varepsilon}_i &\overset{iid}\sim N(\mathbf{0}, \, \sigma^2
  \mathbf{I}_{n_i})
\end{align*}
  \end{column}
\end{columns}
\end{frame}

\begin{frame}[fragile]{}
  \begin{block}{Exercise}
    \begin{itemize}
      \item What would be a possible extension of this model?\pause
      \item Write down the model equations
        \begin{itemize}
          \item What changes for the fixed effects?
          \item How do the variance components for the random effects change?
        \end{itemize}\pause
      \item How can we interpret the random quadratic effects for this model?\pause
      \item How do we add (random) quadratic effects to a random slope model
        using \texttt{lme4::lmer()}?\pause
      \item Fit this growth curve model in R\pause
    \end{itemize}
  \end{block}
    \begin{lstlisting}
dat      <- read.table("data/reisby.txt", header = TRUE)
dat$id   <- factor(dat$id)
dat$diag <- factor(dat$diag, levels = c("nonen", "endog"))
dat      <- na.omit(dat)     # drop missing values
    \end{lstlisting}
\end{frame}

\begin{frame}[fragile]{Model with quadratic trend}
  \begin{itemize}
    \item Model with quadratic individual and quadratic group trend
      \[
 y_{ij} = \beta_0 + \beta_1\,t_{ij} + \beta_2\,t^2_{ij} + \upsilon_{0i} +
      \upsilon_1\,t_{ij} + \upsilon_2\,t^2_{ij} + \varepsilon_{ij}
      \]
with
\begin{align*}
  \begin{pmatrix}
    \upsilon_{0i}\\
    \upsilon_{1i}\\
    \upsilon_{2i}
  \end{pmatrix} &\overset{iid}{\sim}
  N \left(\begin{pmatrix}
      0\\ 0\\ 0
  \end{pmatrix}, \,
  \begin{pmatrix}
    \sigma^2_{\upsilon_0} & \sigma_{\upsilon_0 \upsilon_1} & \sigma_{\upsilon_0 \upsilon_2}\\
    \sigma_{\upsilon_0 \upsilon_1} & \sigma^2_{\upsilon_1} & \sigma_{\upsilon_1 \upsilon_2}\\
    \sigma_{\upsilon_0 \upsilon_2} & \sigma_{\upsilon_1 \upsilon_2} & \sigma^2_{\upsilon_2}\\
      \end{pmatrix} \right) \\
  \boldsymbol{\varepsilon}_i &\overset{iid}{\sim} N(\mathbf{0}, \, \sigma^2 \mathbf{I}_{n_i})
\end{align*}
  \end{itemize}
\vspace{-.5cm}
\end{frame}

\begin{frame}[fragile]{Model with quadratic trend}
  \begin{lstlisting}
library("lme4")

# random intercept model
lme1 <- lmer(hamd ~ week + (1 | id), data = dat, REML = FALSE)

# random slope model
lme2 <- lmer(hamd ~ week + (week | id), data = dat, REML = FALSE)

# model with quadratic time trend
lme3 <- lmer(hamd ~ week + I(week^2) + (week + I(week^2) | id),
             data = dat, REML = FALSE)
  \end{lstlisting}
\end{frame}

\begin{frame}{Model predictions}
\begin{columns}
\begin{column}{6cm}
\includegraphics[width=6cm]{../figures/hdrs-quad}
\end{column}
%
\begin{column}{5cm}
  \begin{itemize}
    \item Averaged over persons an approximately linear trend is obtained,
      $\hat{\beta}_1 = -2.63$, $\hat{\beta}_2 = 0.05$
    \item Some of the predicted individual trends are strongly nonlinear
  \end{itemize}
\end{column}
\end{columns}
  \begin{itemize}
    \item Test against a model without individual quadratic trends\\[2ex]

H$_0$: $\sigma^2_{\upsilon_2} = \sigma_{\upsilon_0 \upsilon_2} =
\sigma_{\upsilon_1 \upsilon_2} = 0$ \qquad
$G^2(3) = 10.98$, $p = .012$
  \end{itemize}
\end{frame}

\begin{frame}[fragile]{Model predictions}
  \begin{columns}
    \begin{column}{8cm}
      \includegraphics[scale=.5]{../figures/hdrs-ind_pred-quad}
    \end{column}
    \begin{column}{6cm}
      \begin{lstlisting}
xyplot(
  hamd + predict(lme3)
     ~ week | id,
  data = dat,
  type = c("p", "l", "g"),
  pch = 16,
  distribute.type = TRUE,
  ylab = "HDRS score",
  xlab = "Time (Week)")
      \end{lstlisting}
    \end{column}
  \end{columns}
\end{frame}

% \begin{frame}[fragile]{Implied marginal covariance matrix}
% Predicted
% \begin{align*}
%   \mathbf{Z}_i \boldsymbol{\hat\Sigma}_\upsilon \mathbf{Z}'_i +
%     \hat\sigma^2 \mathbf{I}_{n_i} &=
%   \begin{pmatrix}
%     20.96 & 9.41 & 8.16 & 6.68 & 4.98 & 3.06 \\
%     9.41 & 23.86 & 15.57 & 16.08 & 14.88 & 11.97 \\
%     8.16 & 15.57 & 31.07 & 23.11 & 23.26 & 20.98 \\
%     6.68 & 16.08 & 23.11 & 38.31 & 30.12 & 30.09 \\
%     4.98 & 14.88 & 23.26 & 30.12 & 45.98 & 39.29 \\
%     3.06 & 11.97 & 20.98 & 30.09 & 39.29 & 59.11
%   \end{pmatrix}\\
%   %
%   \intertext{Observed}
%   %
%   \widehat{Cov}(\mathbf{y}_i) &=
%   \begin{pmatrix}
%     20.55 & 10.11 & 10.14 & 10.09 & 7.19 & 6.28 \\
%     10.11 & 22.07 & 12.28 & 12.55 & 10.26 & 7.72 \\
%     10.14 & 12.28 & 30.09 & 25.13 & 24.63 & 18.38 \\
%     10.09 & 12.55 & 25.13 & 41.15 & 37.34 & 23.99 \\
%     7.19 & 10.26 & 24.63 & 37.34 & 48.59 & 30.51 \\
%     6.28 & 7.72 & 18.38 & 23.99 & 30.51 & 52.12 \\
%   \end{pmatrix}\\
% \end{align*}
% % \vspace{-1cm}
% % \begin{lstlisting}
% % getVarCov(lme3, type="marginal")  # predicted cov. matrix
% %
% % var.d <- crossprod(getME(lme3,"Lambdat"))
% % Zt <- getME(lme3, "Zt")
% % vr <- sigma(lme3)^2
% %
% % var.b <- vr*(t(Zt) %*% var.d %*% Zt)
% % sI <- vr * Diagonal(nrow(dat2))
% % var.y <- var.b + sI
% %
% % \end{lstlisting}
% \end{frame}

\begin{frame}{Centering variables}
  \begin{itemize}
    \item If multiples of the time variables ($t$, $t^2$, $t^3$, etc.) are
      entered into the regression equation, multicollinearity can become a
      problem
    \item For example, $t = 0, 1, 2, 3$ and $t^2 = 0, 1, 4, 9$ correlate almost
      perfectly
    \item By centering the variables, this problem can be diminished: $(t -
      \bar{t}) = -1.5, -0.5, 0.5,  1.5$ and $(t - \bar{t})^2 = 2.25, 0.25, 0.25,
      2.25$ are uncorrelated
    \item By centering variables the interpretation of the intercept in a linear
      model changes:
  \begin{itemize}
    \item Uncentered intercepts represent the difference to the first time
    point ($t = 0$)
    \item Centered intercepts represent the difference after half of the
    time
  \end{itemize}
  \end{itemize}
\end{frame}

\begin{frame}{}
  \begin{block}{Exercise}
    \begin{itemize}
      \item Center time\pause
      \item Compare the correlation between time and time$^2$ with and without
        centering\pause
      \item Refit the model with quadratic effects when time is centered\pause
      \item Which parameters change?
        \begin{itemize}
          \item What changes for the fixed effects?
          \item How do the variance components for the random effects change?
        \end{itemize}\pause
      \item \emph{Why} do the variance components for the random effects change?
    \end{itemize}
  \end{block}
\end{frame}

\begin{frame}[fragile]{Analysis with centered time variable}
\begin{lstlisting}
dat$week_c <- dat$week - mean(dat$week)
cor(dat$week, dat$week^2)       # 0.96
cor(dat$week_c, dat$week_c^2)   # 0.01

# random slope model
lme2c <- lmer(hamd ~ week_c + (week_c | id), data = dat, REML = FALSE)

# model with quadratic time trend
lme3c <- lmer(hamd ~ week_c + I(week_c^2) + (week_c + I(week_c^2)|id),
              data = dat, REML = FALSE)
\end{lstlisting}
%  \begin{itemize}
%    \item When comparing the estimated parameters, it becomes obvious that not
%      only the intercept changes but the estimates for the (co)variances do as
%      well
%    \item Why?\pause
%      ~Be sure to make an informed choice when centering your
%      variables!
%  \end{itemize}
  \nocite{Alday2025, Hedeker2006}
\end{frame}

\begin{frame}[fragile]{Investigating random effects structure}
  \begin{itemize}
    \item In order to get a better understanding of the necessary random effects
      it might be a good idea to take a closer look at them
    \item Two plots often used are the so-called caterpillar and shrinkage plots
    \item Play around with different models and compare how, e.\,g., the
      caterpillar plots change with and without covariances in the model!
  \end{itemize}
  \vfill
\begin{lstlisting}
library("lattice")
dotplot(ranef(lme3), scales = list( x = list(relation = "free")))$id
\end{lstlisting}
\end{frame}


\begin{frame}[fragile]%{Investigating random effects structure}
  {Caterpillar plot}
    \begin{columns}
      \begin{column}{1.13\textwidth}
        \includegraphics[scale=.31]{../figures/hdrs-caterpillar}
      \end{column}
  \end{columns}
\end{frame}

\begin{frame}[fragile]%{Investigating random effects structure}
  {Shrinkage plots}
  \begin{columns}
    \begin{column}{.35\textwidth}
      \includegraphics[scale=.35]{../figures/hdrs_shrinkage_int-week}
    \end{column}
    \begin{column}{.35\textwidth}
      \includegraphics[scale=.35]{../figures/hdrs_shrinkage_int-weeksq}
    \end{column}
    \begin{column}{.35\textwidth}
      \includegraphics[scale=.35]{../figures/hdrs_shrinkage_week-weeksq}
    \end{column}
  \end{columns}
\end{frame}

% \begin{frame}{Higher-order polynomials}
%   \begin{itemize}
%     \item Nonlinear time trends can be modelled in a flexibel and parsimonious
%       way by using higher-order polynomials
%     \item For example, saddle or reversal points in a time trend can be
%       described
%     \item Polynomials have the advantage that the regression model stays linear
%       in its parameters
%     \item They have the disadvantage that extrapolated values can quickly be
%       outside of a range that can still be interpreted in a meaningful way
%   \end{itemize}
% \end{frame}
%
% \begin{frame}{Cubic time trends}
% \begin{center}
% \includegraphics[width=9cm]{../figures/cubic}
% \end{center}
% \end{frame}
%
% \begin{frame}{Polynomial regression: Extrapolation}
% \begin{center}
% \includegraphics[width=9cm]{../figures/cubic-gone-bad}
% \end{center}
% \end{frame}

\begin{frame}{What we learned today\dots}
  {\dots and how to go on}
  \pause
  \begin{enumerate}[<+->]
    \item We learned
      \begin{itemize}
        \item The basic concept of random effects and why to include them in a
          model
        \item How to model data collected over several time points
        \item How to compute mixed-effects model with quadratic time trends in R
          using \texttt{lmer()} from the lme4 package
        \item How to interpret parameters in mixed-effects model with quadratic
          effects
      \end{itemize}
    \item Next steps
      \begin{itemize}
        \item Do this exercise
          \url{https://gitea.iwm-tuebingen.de/nwickelmaier/lead_longitudinal/src/branch/master/exercises/schizo.md}
        \item It has a very similar structure than the depression dataset and
          this will help you to generalize the concepts we learned today
        \item You can send questions to me and even make an appointment with me
          to go over your solution
      \end{itemize}
  \end{enumerate}
\end{frame}

\appendix
%\begin{frame}[allowframebreaks]{References}
\begin{frame}{References}
  \printbibliography
  \vfill
\end{frame}

\end{document}