Initialized repository

01_intro/01_intro.tex

@@ -0,0 +1,306 @@
+\documentclass[aspectratio=169]{beamer}
+
+\usepackage[utf8,latin1]{inputenc}
+\usepackage[style = apa, backend = biber, natbib = true]{biblatex}
+\addbibresource{../literature/lit.bib}
+
+\usepackage{multirow}
+\usepackage{color, colortbl}
+
+\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}
+\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}
+
+\newcommand{\vect}[1]{\mathbf{#1}}
+\newcommand{\mat}[1]{\mathbf{#1}}
+\newcommand{\gvect}[1]{\boldsymbol{#1}}
+\newcommand{\gmat}[1]{\boldsymbol{#1}}
+
+\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}
+
+\title{Good habits and best practices for effective research data
+management}
+\author{Nora Wickelmaier}
+\date{May 13, 2024}
+
+\begin{document}
+
+\begin{frame}{}
+\thispagestyle{empty}
+\titlepage
+\end{frame}
+
+\section{Introduction}
+
+\begin{frame}{Habits}
+  \begin{quote}
+    ``In the beginning, creating a new habit is more critical than actually
+    achieving a goal.''
+  \end{quote}
+  \vspace{.5cm}
+
+  Six ideas for building the habits you want
+  \begin{enumerate}
+    \item Start your habit change process by building awareness
+    \item All change begins with making choices
+    \item Attach a new habit or behavior to something you already do regularly
+    \item Gain clarity about what you want to do and how you will do it
+    \item Start with a simple step
+    \item Remember the ``why''
+  \end{enumerate}
+  \vfill
+  \flushright{\tiny \url{https://www.psychologytoday.com/us/blog/flourish-and-thrive/202002/6-powerful-ways-build-new-habits}}
+\end{frame}
+
+\begin{frame}{What habits would help with good data management?}
+  \centering
+  \includegraphics[width = 5cm]{../figures/QR Code for Methodenseminar SS 2024 - Session 1}
+  \url{https://app.sli.do/event/5nyLNFVV2bTHxGVUK1zFEX}
+\end{frame}
+
+\begin{frame}{The ``why''}
+  \centering
+  \includegraphics[width = .85\textwidth]{../figures/snafu}
+  \url{https://youtu.be/66oNv_DJuPc}
+\end{frame}
+
+\begin{frame}{The ``why''}
+  \begin{columns}
+    \begin{column}[c]{.6\textwidth}
+Reproducibility vs.\ replicability:
+      {\small
+  \renewcommand{\arraystretch}{2.5}
+  \begin{tabular}{llc|c|}
+    & & \multicolumn{2}{c}{\textbf{Data}} \\
+    
+    & & \cellcolor{gray}\textbf{\color{white}Same} & 
+    \cellcolor{gray}\textbf{\color{white}Different} \\
+    
+    \multirow{2}{*}{\textbf{Analysis}} &
+
+    \cellcolor{gray}\textbf{\color{white}Same}
+    & \only<2>{\bf \color{red}}Reproducible & Replicable    \\
+    \cline{2-4}
+    
+    & \cellcolor{gray}\textbf{\color{white}Different} & Robust & Generalizable \\
+    \cline{2-4}
+  \end{tabular}
+      }
+    \end{column}
+    \begin{column}[c]{.4\textwidth}
+      Ethical research standards:
+
+      \vspace{1cm}
+    \includegraphics[scale = .4]{../figures/2021-06-16_icon_intranet_fair2}
+    \end{column}
+  \end{columns}
+  \vfill
+  \flushright{\tiny \url{https://the-turing-way.netlify.app/reproducible-research}}
+\end{frame}
+
+\begin{frame}{What are possible barriers for good data management?}
+  \centering
+  \includegraphics[width = 5cm]{../figures/QR Code for Methodenseminar SS 2024 - Session 1}
+  \url{https://app.sli.do/event/5nyLNFVV2bTHxGVUK1zFEX}
+\end{frame}
+
+\begin{frame}[<+->]{Barriers}
+  \begin{itemize}
+    \item Skills for doing reproducible research are not taught in
+      a systematic way
+    \item Supervisors are often not doing it
+    \item Incentive system does not encourage to spend time on making
+      research reproducible (yet!)
+    \item Takes time
+    \item Takes time
+    \item Requires additional skills
+    \item Learning these skills is often full of frustrating experiences
+  \end{itemize}
+  \vfill
+\end{frame}
+
+\section[Example]{Personal example}
+
+\begin{frame}{}
+  \begin{center}
+    \includegraphics[scale = 0.55]{../figures/datenanfrage_phd_thesis}
+  \end{center}
+\end{frame}
+
+\begin{frame}[<+->]{The situation}
+  \begin{itemize}
+    \item I actually published the data of my first experiment in an R
+      package
+    \item BUT: He probably wants the data of my second experiment\dots
+      \includegraphics[scale = .03]{../figures/seenoevil_monkey}
+    \item First try:\\
+      \includegraphics[scale = .5]{../figures/phd_data1}
+
+      This does not look good\dots There's not even the actual folder with
+      the final data. WTF?
+    \item Remembering that I probably moved that to my ``postdoc folder''
+      -- but this is not on my work computer, since it is so big\dots OK, I
+      will check that at home tonight\dots
+  \end{itemize}
+\end{frame}
+
+\begin{frame}[allowframebreaks]{Getting closer}
+  \begin{itemize}
+    \item Puh, all the data are on my home computer (only copy,
+      though\dots)\\
+      \includegraphics[scale = .37]{../figures/phd_data2}
+    \item But not really organized\dots\\
+      \includegraphics[scale = .18]{../figures/phd_data3}
+    \item I check my analysis files and am pretty sure that the files
+      \texttt{vp0[1-4]\_finaldata.txt} are the ones I used in the analysis
+      in my diss
+    \item Checking the files again, I discover that the luminances of my
+      stimuli are not in these files -- only the stimulus names I used in
+      the experiment, something like \texttt{stim\_1\_7} (pretty
+      informative, huh?)
+    \item The stimulus files are also in the folder, the one for
+      \texttt{stim\_1\_7} looks like this\\
+      \includegraphics[scale = .1]{../figures/phd_data4}\\
+      (BTW, I investigated the perception of black and white colors in my
+      diss)
+  \end{itemize}
+\end{frame}
+
+\begin{frame}{I finally answered this}
+  \begin{center}
+      \includegraphics[scale = .55]{../figures/phd_data5}
+  \end{center}
+\end{frame}
+
+\begin{frame}{}
+  \begin{block}{Exercise}
+    \begin{itemize}
+      \item Go to \url{https://nextcloud.iwm-tuebingen.de/s/8KoefDc6tZSSMwy}
+        and download the data and additional material
+      \item Are you able to understand what needs to be done in order to
+        use this data based on the information provided?
+      \item Write down the steps that need to be taken in order to make
+        these data reusable
+      \item What kind of skills do we need in order to perform these steps?
+    \end{itemize}
+  \end{block}
+\end{frame}
+
+\begin{frame}[fragile]{What I wish I could have answered}
+  \begin{verbatim}
+  Hello,
+
+  All the data and analyses for my dissertation can be
+  found here: 
+  https://www.mathpsy.uni-tuebingen.de/colorlab/
+
+  Let me know if you need anything else.
+
+  Best wishes,
+  Nora
+  \end{verbatim}
+\end{frame}
+
+\begin{frame}[<+->]{What barriers stopped me from doing this?}
+  \begin{itemize}
+    \item Back then, I did not even consider to publish my data
+    \item (I only published the data for the first experiment so I had some
+      data in my R package)
+    \item Back then, I only wrapped up stuff before switching research
+      topics for my postdoc phase
+    \item However, I took some time to clean up the files, which allowed me
+      to answer the request within one day
+    \item I had most of the skills I needed, but nobody who emphasized how
+      important it might be to make the data and analysis scripts available
+      and reproducible
+  \end{itemize}
+\end{frame}
+
+\section{Upcoming sessions}
+
+\begin{frame}{What topics would you like to cover this semester?}
+  \centering
+  \includegraphics[width = 5cm]{../figures/QR Code for Methodenseminar SS 2024 - Session 1}
+  \url{https://app.sli.do/event/5nyLNFVV2bTHxGVUK1zFEX}
+\end{frame}
+
+\begin{frame}{Next week: Workflows}
+  \begin{itemize}
+    \item Read \citet{Lowndes2017} -- it's eye opening and kinda funny (and
+      short!)
+    \item Read \citet{Kathawalla2021} -- at least the sections on project
+      workflow (p.~4) and sharing data (p.~6)
+    \item Consider your current research data management and think about
+      what your current workflow is:
+      \begin{itemize}
+        \item What is going well?
+        \item What could be improved?
+        \item What could be the benefits of an improved workflow in this
+          area?
+      \end{itemize}
+  \end{itemize}
+  \vfill
+\end{frame}
+
+
+\begin{frame}[<+->]{Habit building: Get started today}
+  \begin{itemize}
+    %\item Start your 30 Days of Data Management Habits:
+    %  https://nextcloud.iwm-tuebingen.de/s/A5HbJZmZ7W5sQjP
+    \item Are you ten finger typing, yet? (If not, this is definitely
+      something that will improve all of your workflows)
+    \item Clean out the folders in your current project; rename the
+      files
+    %\item Look up note taking and try out some software
+    \item Organize your literature folder
+    \item Think about smart usage of cloud storage (there are many
+      different options at the IWM, there should be one that suits you --
+      are you using the one that suits you best?)
+    \item Next time you want to e-mail a document, think about a better
+      way to share it
+    \item Use R Markdown to write your next preregistration
+    \item Start reading a book on R and data analysis
+    \item Use Git for your next data analysis
+  \end{itemize}
+\end{frame}
+
+\appendix
+%%\begin{frame}[allowframebreaks]{References}
+\begin{frame}{References}
+%\renewcommand{\bibfont}{\small}
+%\bibliographystyle{apacite}
+%\bibliography{../lit}
+  \printbibliography
+\vfill
+\end{frame}
+
+\end{document}
+

01_intro/exercise/README.md

@@ -0,0 +1,7 @@
+Here are the information, that I provided in my e-mail:
+
+The data for the second experiment are not integrated, yet, and the
+luminances of the stimuli need to be added. I attached the files with the
+raw data for each subject: `vp0[1-4]_finaldata.txt`. The luminances for the
+12 infield/surround configurations can be taken from the attached PDF-file.
+

README.md

@@ -0,0 +1,23 @@
+# Overview of dates
+
+| Date       | Topic                                   |
+| ---------- | --------------------------------------- |
+| 13.05.2024 | Introduction to data management         |
+| 27.05.2024 | Workflows                               |
+| 10.06.2024 |                                         |
+| 24.06.2024 |                                         |
+| 08.07.2024 |                                         |
+| 22.07.2024 |                                         |
+| ---------- | --------------------------------------- |
+
+# Literature
+
+Kathawalla, U.-K., Silverstein, P., & Syed, M. (2021).Easing into open
+science: A guide for graduate students and their advisors. Collabra:
+Psychology, 7(1). https://doi.org/10.1525/collabra.18684
+
+Lowndes, J. S. S., Best, B. D., Scarborough, C., Afflerbach, J. C.,
+Frazier, M. R., O’Hara, C. C., Jiang, N., & Halpern, B. S. (2017).Our path
+to better science in less time using open data science tools. Nature
+Ecology & Evolution, 1(6), 1–7. https://doi.org/10.1038/s41559-017-0160
+

literature/lit.bib

@@ -0,0 +1,32 @@
+@article{Kathawalla2021,
+  title     = {Easing into open science: {A} guide for graduate students and their advisors},
+  author    = {Kathawalla, Ummul-Kiram and Silverstein, Priya and Syed, Moin},
+  journal   = {Collabra: Psychology},
+  volume    = {7},
+  number    = {1},
+  year      = {2021},
+  doi       = {10.1525/collabra.18684}
+}
+
+@article{Lowndes2017,
+  title     = {Our path to better science in less time using open data science tools},
+  author    = {Lowndes, Julia S Stewart and Best, Benjamin D and Scarborough, Courtney and Afflerbach, Jamie C and Frazier, Melanie R and O'Hara, Casey C and Jiang, Ning and Halpern, Benjamin S},
+  journal   = {Nature Ecology \& Evolution},
+  volume    = {1},
+  number    = {6},
+  pages     = {1--7},
+  year      = {2017},
+  doi       = {10.1038/s41559-017-0160}
+}
+
+@article{Meyer2018,
+  title     = {Practical tips for ethical data sharing},
+  author    = {Meyer, Michelle N},
+  journal   = {Advances in methods and practices in psychological science},
+  volume    = {1},
+  number    = {1},
+  pages     = {131--144},
+  year      = {2018},
+  doi       = {10.1177/2515245917747656}
+}
+