Compare commits
5 Commits
f1f7f35988
...
master
| Author | SHA1 | Date | |
|---|---|---|---|
 Nora Wickelmaier
|
2a2df1d6f4 | ||
|
Nora Wickelmaier
|
7a2327aba3 | ||
|
Nora Wickelmaier
|
66c9711d45 | ||
|
Nora Wickelmaier
|
5cdb5fdb8f | ||
|
Nora Wickelmaier
|
e723230ca5 |
@@ -3,8 +3,11 @@
|
||||
## Responsible person
|
||||
|
||||
Nora Wickelmaier
|
||||
|
||||
Referentin Forschungsmethoden und Forschungsdatenmanagement
|
||||
|
||||
Leibniz-Institut für Wissensmedien (IWM)
|
||||
|
||||
n.wickelmaier@iwm-tuebingen.de
|
||||
|
||||
## Folder structure and naming conventions
|
||||
@@ -25,7 +28,7 @@ numbered, indicating the order they should be executed in.
|
||||
The `data` folder contains all folders associated with data and its
|
||||
documentation.
|
||||
|
||||
The `code` folder with contains different codebook options and R scripts that
|
||||
The `codebook` folder contains different codebook options and R scripts that
|
||||
create these codebooks. If the codebook is created by an R script, the script
|
||||
and the codebook are named identically, e.g., `codebook_01.R` and
|
||||
`codebook_01.xslx`.
|
||||
@@ -40,7 +43,7 @@ RDM_MS_SS2024_download_<YYYY-MM-DD>.<fileending>
|
||||
No other files than the downloads from qualtrics should go into this folder!
|
||||
|
||||
The `results` folder contains processed data. The scripts in `/code/` process
|
||||
the data from `/rawdata/` and saves the files containing the processed data to
|
||||
the data from `/rawdata/` and save the files containing the processed data to
|
||||
`/results/`. Data can be exported as CSV files or RData files. If different file
|
||||
formats contain the same data, they should be named identically, e.g.,
|
||||
`data_rdm-ms-ss2024_cleaned.csv` and `data_rdm-ms-ss2024_cleaned.RData`.
|
||||
|
||||
Binary file not shown.
@@ -0,0 +1,515 @@
|
||||
\documentclass[aspectratio=169]{beamer}
|
||||
|
||||
\usepackage{listings}
|
||||
%\usepackage[utf8]{inputenc}
|
||||
\usepackage[style = apa, backend = biber, natbib = true]{biblatex}
|
||||
\addbibresource{../literature/lit.bib}
|
||||
|
||||
\usepackage{fancyvrb}
|
||||
\usepackage{fontawesome5} % get icons
|
||||
\usepackage{multirow}
|
||||
\usepackage{color, colortbl}
|
||||
|
||||
\usepackage{tikz}
|
||||
\usetikzlibrary{fit}
|
||||
\usepackage[edges]{forest}
|
||||
|
||||
\lstset{language=R,%
|
||||
backgroundcolor=\color{iwmgray!15!white},
|
||||
basicstyle=\ttfamily\color{iwmgray},
|
||||
frame=none,
|
||||
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}}
|
||||
|
||||
\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}
|
||||
|
||||
\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{Data sharing}
|
||||
\author{Nora Wickelmaier}
|
||||
\date{June 24, 2024}
|
||||
|
||||
\begin{document}
|
||||
|
||||
\begin{frame}{}
|
||||
\thispagestyle{empty}
|
||||
\titlepage
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{What are the benefits of sharing your data?}
|
||||
% slido
|
||||
\centering
|
||||
\includegraphics[width = 5cm]{../figures/QR Code for Methodenseminar SS 2024 - Session 4}
|
||||
|
||||
\url{https://app.sli.do/event/m5FEcBYkqtVAsjkdTsKsmd}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[<+->]{Benefits of sharing data}
|
||||
Sharing data
|
||||
\begin{itemize}
|
||||
\item[\dots] ensures that data are not ultimately lost (save data for posterity)
|
||||
\item[\dots] is consistent with scientific norms of openness and rigor
|
||||
\item[\dots] increases citation scores of papers
|
||||
\item[\dots] encourages more research because it enables secondary analyses
|
||||
\item[\dots] facilitates subsequent reanalyses (correct errors, emphasize
|
||||
robustness of original results)
|
||||
\item[\dots] is demanded by most third party funding agencies
|
||||
\end{itemize}
|
||||
\vfill
|
||||
\hfill\tiny \citet{Wicherts2012}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{Agenda}
|
||||
\centering
|
||||
\begin{tabular}{ll}
|
||||
\hline
|
||||
Date & Topic \\
|
||||
\hline
|
||||
2024-05-13 & Introduction to data management \\
|
||||
2024-05-27 & Workflow \\
|
||||
2024-06-10 & Data organisation\\
|
||||
\only<1>{2024-06-24}\only<2>{\bf 2024-06-24} & \only<1>{Data sharing}\only<2>{\bf Data sharing} \\
|
||||
2024-07-08 & Clean coding \\
|
||||
2024-07-22 & Version control \\
|
||||
\hline
|
||||
\end{tabular}
|
||||
\end{frame}
|
||||
|
||||
% uploading under a license (CC-BY....)
|
||||
% loading data on an archive, repository etc...
|
||||
% Doing the archive
|
||||
% mportant things before the open-access data
|
||||
% Where to store data for long-term accessibility (conventions?)
|
||||
% Tools, where I should upload my final data
|
||||
% Upload data before or after publishing a paper? Time mangement
|
||||
|
||||
\section{Data organisation}
|
||||
|
||||
\begin{frame}[<+->]{What we covered so far}
|
||||
\begin{itemize}
|
||||
\item What habits do we need for effective research data management?
|
||||
\item What is a workflow and why do we need one?
|
||||
\item What needs to be considered when naming files of a research project?
|
||||
\item How to organize folders for a research project?
|
||||
\item What metadata should be added to my research project?
|
||||
\item What are good ways to document a data set?
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{Examples for documenting data sets}
|
||||
\begin{enumerate}
|
||||
\item A recent paper with published data by \citet{Ngo2023} investigating
|
||||
what cues are considered by Twitter users to identify social bots
|
||||
\item A multi-cohort, longitudinal study by the Hector Research Institute of
|
||||
Education Sciences and Psychology at the university of Tübingen:
|
||||
Transformation of the secondary school system and academic careers
|
||||
\citep[TOSCA,][]{Koeller2004}
|
||||
\item Editorial on why to publish your data with an accompanying data set
|
||||
by \citet{Wicherts2012}
|
||||
\end{enumerate}
|
||||
\vfill
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{\citet{Ngo2023}}
|
||||
They provide
|
||||
\begin{itemize}
|
||||
\item A data set with 221 observations and 633 variables
|
||||
\item A PDF with all measures and the scenario used for collecting the data
|
||||
\end{itemize}
|
||||
\vspace{.3cm}
|
||||
\begin{block}{Exercise}
|
||||
\begin{itemize}
|
||||
\item Go to \url{https://osf.io/6y3nk/} and download the files
|
||||
\texttt{data.csv} and
|
||||
\texttt{Experimental-Study-Measures and scenario.pdf}
|
||||
\item Read the data into R using \texttt{read.csv()}
|
||||
\item Find out which variables in the data correspond to measure
|
||||
``(9)~Demographics''
|
||||
\end{itemize}
|
||||
\end{block}
|
||||
\vspace{.3cm}
|
||||
\pause
|
||||
(BTW: Sharing the data in this form is better than \emph{not} sharing them,
|
||||
in my opinion)
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{What additional information do we need to use these data?}
|
||||
% slido
|
||||
\centering
|
||||
\includegraphics[width = 5cm]{../figures/QR Code for Methodenseminar SS 2024 - Session 4}
|
||||
|
||||
\url{https://app.sli.do/event/m5FEcBYkqtVAsjkdTsKsmd}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{TOSCA}
|
||||
\begin{itemize}
|
||||
\item Multi-cohort study that includes longitudinal data for several cohorts
|
||||
\item Broad spectrum of achievement test data and psycho-social variables
|
||||
\item Large number of publications on different topics using these data
|
||||
\item This is not the original data set, but a prepared version for teaching
|
||||
statistics (hence, proportions in the data and the codebook are not
|
||||
identical)
|
||||
\end{itemize}
|
||||
\begin{block}{Exercise}
|
||||
\begin{itemize}
|
||||
\item Read the data set \texttt{TOSCAtoTeach\_W123.sav} into R using
|
||||
\texttt{foreign::read.spss()} or \texttt{haven::read\_spss()}
|
||||
\item Create contingency tables for the variables \texttt{sform} and
|
||||
\texttt{szweig1} and compare the results to the codebook
|
||||
\texttt{Skalenhandbuch\_TOSCAtoTeachW123.pdf}
|
||||
\end{itemize}
|
||||
\end{block}
|
||||
\hfill{\tiny \url{https://uni-tuebingen.de/en/faculties/faculty-of-economics-and-social-sciences/subjects/department-of-social-sciences/education-sciences-and-psychology/research/current-studies/tosca}}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{\citet{Wicherts2012}}
|
||||
They provide
|
||||
\begin{itemize}
|
||||
\item A data set with 537 observations and 79 variables
|
||||
(\texttt{1-s2.0-S0160289612000050-mmc2.xls})
|
||||
\item A codebook with variable names and some descriptive statistics for
|
||||
the scales (\texttt{1-s2.0-S0160289612000050-mmc1.doc})
|
||||
\item ``Publish (your data) or (let the data) perish! Why not publish your
|
||||
data too?''
|
||||
\item Data come from freshman-testing program called ``Testweek''
|
||||
\item (Try \texttt{readxl::read\_excel()} to read the data into R)
|
||||
\end{itemize}
|
||||
\vfill
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{What is the single one thing that would make sharing these data
|
||||
indefinitely better?}
|
||||
% slido
|
||||
\centering
|
||||
\includegraphics[width = 5cm]{../figures/QR Code for Methodenseminar SS 2024 - Session 4}
|
||||
|
||||
\url{https://app.sli.do/event/m5FEcBYkqtVAsjkdTsKsmd}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[<+->]{Non-anonymous data}
|
||||
\begin{itemize}
|
||||
\item Before putting data into any cloud, you should always take a moment to
|
||||
reflect if your data are anonymous
|
||||
\item No (third-party) cloud storage, even if it is not publicly accessible
|
||||
\item If your data contains personal data, it should always be stored
|
||||
locally, ideally on an encrypted device
|
||||
\item You should have a plan --- bofore ever collecting the data --- how,
|
||||
when, and by whom the data will be anonymized
|
||||
\item All data should eventually be anonymized! (Yes, even audio and video
|
||||
data)
|
||||
\item IWM servers can be considered local
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\section[Collaborative use]{Sharing data for collaborative use}
|
||||
|
||||
\begin{frame}[<+->]{Working together with the same data}
|
||||
\begin{itemize}
|
||||
\item Part of data organisation is to think about who needs access to
|
||||
your data
|
||||
\item Often these are colleagues from the same lab and there is
|
||||
infrastructure to share files and scripts easily
|
||||
\item The IWM offers several solutions for sharing your data (internally and
|
||||
externally)
|
||||
\item When the end goal is to make the data public, it might be a good idea
|
||||
to work together at a place where the data can go public at a certain
|
||||
point in time
|
||||
\item We will look at two possiblities: OSF and Github
|
||||
\end{itemize}
|
||||
\vfill
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{IWM solutions}
|
||||
IWM servers
|
||||
\begin{itemize}
|
||||
\item Nextcloud: \url{https://nextcloud.iwm-tuebingen.de/}
|
||||
\item Gitea: \url{https://gitea.iwm-tuebingen.de/}
|
||||
\item Shared drive: \texttt{Y:/}
|
||||
\end{itemize}
|
||||
\vspace{.4cm}
|
||||
Microsoft servers
|
||||
\begin{itemize}
|
||||
\item OneDrive
|
||||
\item Teams
|
||||
\end{itemize}
|
||||
\vfill
|
||||
\pause
|
||||
(Maybe check out the three tips of the week on this topic:
|
||||
{\tiny
|
||||
\url{https://iwmonline.sharepoint.com/sites/intranet/SitePages/direktorat/en/Interne-Kommunikation.aspx\#tip-of-the-week-tutorial-series}})
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{Open Science Framework}
|
||||
{\url{https://osf.io/}}
|
||||
\begin{columns}
|
||||
\begin{column}{.4\textwidth}
|
||||
\begin{itemize}
|
||||
\item ``OSF is a free and open source project management tool that supports
|
||||
researchers throughout their entire project lifecycle.''
|
||||
\item Founded in 2012 and constantly developed: \url{https://www.cos.io/timeline}
|
||||
\item Meant to integrate all research steps
|
||||
\end{itemize}
|
||||
\end{column}
|
||||
\begin{column}{.7\textwidth}
|
||||
\includegraphics[scale = .2]{../figures/osf_workflow.png}
|
||||
\end{column}
|
||||
\end{columns}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Let's try it out}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 5.1cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node (ex) at (0, 0) {\faIcon{folder} \verb+toyexample+};
|
||||
\node (n1) at (5, 0) {\faIcon{folder} \verb+code+};
|
||||
\node (n2) at (5, -1.4) {\faIcon{folder} \verb+data+};
|
||||
\node (n3) at (5, -2.8) {\faIcon[regular]{file} \verb+README.md+};
|
||||
\path (ex.center) -- (n1.west);
|
||||
\path (ex.center) -- (n2.west);
|
||||
\path (ex.center) -- (n3.west);
|
||||
|
||||
\node (o1a) at (10, 0) {\faIcon[regular]{file} \verb+01_preprocessing.R+};
|
||||
\node (o1b) at (10, -0.7) {\faIcon[regular]{file} \verb+02_descriptives.R+};
|
||||
\node (o2) at (10, -1.4) {\faIcon{folder} \verb+processed+};
|
||||
\node (o3) at (10, -2.1) {\faIcon{folder} \verb+rawdata+};
|
||||
\node (o4) at (10, -2.8) {\faIcon[regular]{file} \verb+codebook.pdf+};
|
||||
\path (n1.center) -- (o1a.west);
|
||||
\path (n1.center) -- (o1b.west);
|
||||
\path (n2.center) -- (o2.west);
|
||||
\path (n2.center) -- (o3.west);
|
||||
\path (n2.center) -- (o4.west);
|
||||
\end{tikzpicture}
|
||||
Steps
|
||||
\begin{enumerate}
|
||||
\item You need an OSF account -- just sign up with an e-mail address or use ORCID
|
||||
\item Sign in
|
||||
\item Create a project
|
||||
\item Upload (or link) your files
|
||||
\item Invite contributors
|
||||
\end{enumerate}
|
||||
\end{frame}
|
||||
|
||||
% TODO:
|
||||
|
||||
% Show different cases on OSF:
|
||||
% 1. OSF with handmade codebook, all in one folder
|
||||
% 2. OSF with different components (show that they can all have different
|
||||
% licenses)
|
||||
% 3. OSF with Github integrated
|
||||
|
||||
% Show selection of servers (GDPR)
|
||||
|
||||
\begin{frame}{Licenses}
|
||||
\begin{columns}
|
||||
\begin{column}{.3\textwidth}
|
||||
\includegraphics[scale = .4]{../figures/licenses_osf.png}
|
||||
\end{column}
|
||||
\begin{column}{.7\textwidth}
|
||||
\begin{itemize}
|
||||
\item OSF offers you several options for licenses
|
||||
\item For data the Creative Common (CC) licenses are usually a good option
|
||||
\item For software, other options might be better suited
|
||||
\item For code (e.\,g., analysis scripts) CC licenses are also a good
|
||||
choice
|
||||
\end{itemize}
|
||||
\vspace{1cm}
|
||||
|
||||
\hfill{\footnotesize \url{https://creativecommons.org/}}\\
|
||||
\hfill{\footnotesize \url{https://help.osf.io/article/288-license-your-project}}\\
|
||||
\hfill{\footnotesize \url{https://choosealicense.com/}}
|
||||
\end{column}
|
||||
\end{columns}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{Github}
|
||||
{\url{https://github.com/}}
|
||||
\begin{columns}
|
||||
\begin{column}{.8\textwidth}
|
||||
\begin{itemize}
|
||||
\item Developer platform that allows developers to create, store, manage and
|
||||
share code
|
||||
\item Based on Git software providing version control
|
||||
\begin{itemize}
|
||||
\item[+] access control
|
||||
\item[+] bug tracking
|
||||
\item[+] software feature requests
|
||||
\item[+] task management
|
||||
\item[+] continuous integration
|
||||
\item[+] wikis
|
||||
\end{itemize}
|
||||
\item Commonly used to host open source software development projects
|
||||
\item Bought by Microsoft in 2018
|
||||
\end{itemize}
|
||||
\end{column}
|
||||
\begin{column}{.3\textwidth}
|
||||
\includegraphics[scale = .2]{../figures/github.png}
|
||||
\end{column}
|
||||
\end{columns}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{Github workflow}
|
||||
\begin{center}
|
||||
\includegraphics[scale = .3]{../figures/workflow_git-github.png}
|
||||
\end{center}
|
||||
\hfill{\tiny \url{https://carpentries-incubator.github.io/open-science-with-r/09-collaborating}}
|
||||
\end{frame}
|
||||
|
||||
% TODO:
|
||||
|
||||
% READMEs:
|
||||
% https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-readmes
|
||||
|
||||
\section[Repositories]{Sharing data in repositories}
|
||||
|
||||
\begin{frame}[allowframebreaks]{Data publication}
|
||||
Which data should I share?
|
||||
\begin{itemize}
|
||||
\item In general, all data that are used in publications
|
||||
\item Data for your dissertation
|
||||
\item Data that you collected but know that you will never come around to
|
||||
analyzing
|
||||
\end{itemize}
|
||||
\vspace{.3cm}
|
||||
What are the reasons to share data?
|
||||
\begin{itemize}
|
||||
\item Transparency
|
||||
\item Data safety
|
||||
\item Cumulative research process
|
||||
\item Visibility
|
||||
\end{itemize}
|
||||
\framebreak
|
||||
For whom are you sharing data?
|
||||
\begin{itemize}
|
||||
\item Yourself
|
||||
\item Reviewers
|
||||
\item People who read your papers
|
||||
\item Other scientists
|
||||
\item Colleagues and collaboraters
|
||||
\end{itemize}
|
||||
\vspace{.3cm}
|
||||
How should you share your data?
|
||||
\begin{itemize}
|
||||
\item On a public platform (or website), i.\,e., no account needed if
|
||||
possible
|
||||
\item Together with a codebook or at least an informative README
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{Data repositories (suggested in our Research Data Policy)}
|
||||
National
|
||||
\begin{itemize}
|
||||
\item \url{https://www.psycharchives.org/}
|
||||
\item \url{https://www.forschungsdaten-bildung.de/}
|
||||
\item \url{https://datorium.gesis.org/}
|
||||
\item \url{https://www.iqb.hu-berlin.de/fdz}
|
||||
\end{itemize}
|
||||
\vspace{.4cm}
|
||||
International
|
||||
\begin{itemize}
|
||||
\item \url{https://datadryad.org/}
|
||||
\item \url{https://osf.io/}
|
||||
\item \url{https://zenodo.org/}
|
||||
\end{itemize}
|
||||
\vfill
|
||||
|
||||
\hfill{\footnotesize \url{https://datamanagement.hms.harvard.edu/share-publish/data-repositories}}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[<+->]{Zenodo}{https://zenodo.org/}
|
||||
\begin{itemize}
|
||||
\item General-purpose open repository launched in 2015
|
||||
\item Financed by the EU (European OpenAIRE program)
|
||||
\item Operated by CERN
|
||||
\item All disciplines
|
||||
\item Suitable for
|
||||
\begin{itemize}
|
||||
\item Data sets
|
||||
\item Papers / Preprints
|
||||
\item Research software
|
||||
\item Reports
|
||||
\item Any other digital research objects
|
||||
\end{itemize}
|
||||
\item Upload up to 50 GB possible
|
||||
\item Easily citable since all objects get DOI
|
||||
\item Open source code is available on Github
|
||||
\item IWM example: \url{https://doi.org/10.5281/zenodo.2532411}
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[<+->]{PsychArchives}{https://psycharchives.org/}
|
||||
\begin{itemize}
|
||||
\item Disciplinary repository for psychological science (and neighboring
|
||||
disciplines)
|
||||
\item Developed and operated by ZPID (Leibniz-Institut für Psycholgie)
|
||||
\item Accommodating 20 different digital research object (DRO) types
|
||||
\begin{itemize}
|
||||
\item Articles
|
||||
\item Preprints
|
||||
\item Research data
|
||||
\item Code
|
||||
\item Supplements
|
||||
\item Preregistrations
|
||||
\item \dots
|
||||
\end{itemize}
|
||||
\item Searchable by ``IWM'': \url{https://psycharchives.org/en/browse/?q=iwm}
|
||||
\item Easily citable since all objects get DOI
|
||||
\item Different objects can be linked together (e.\,g., data und code)
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\appendix
|
||||
%%\begin{frame}[allowframebreaks]{References}
|
||||
\begin{frame}{References}
|
||||
%\renewcommand{\bibfont}{\small}
|
||||
\printbibliography
|
||||
\vfill
|
||||
\end{frame}
|
||||
|
||||
\end{document}
|
||||
|
||||
@@ -0,0 +1,503 @@
|
||||
\documentclass[aspectratio=169]{beamer}
|
||||
|
||||
\usepackage{listings}
|
||||
%\usepackage[utf8]{inputenc}
|
||||
\usepackage[style = apa, backend = biber, natbib = true]{biblatex}
|
||||
\addbibresource{../literature/lit.bib}
|
||||
|
||||
\usepackage{fancyvrb}
|
||||
\usepackage{fontawesome5} % get icons
|
||||
\usepackage{multirow}
|
||||
\usepackage{color, colortbl}
|
||||
|
||||
\usepackage{tikz}
|
||||
\usetikzlibrary{fit}
|
||||
\usepackage[edges]{forest}
|
||||
|
||||
\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}}
|
||||
|
||||
\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}
|
||||
|
||||
\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{Clean coding}
|
||||
\author{Nora Wickelmaier}
|
||||
\date{July 8, 2024}
|
||||
|
||||
\begin{document}
|
||||
|
||||
\begin{frame}{}
|
||||
\thispagestyle{empty}
|
||||
\titlepage
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{What is needed to make code reproducible?}
|
||||
% slido
|
||||
\centering
|
||||
\includegraphics[width = 5cm]{../figures/QR Code for Methodenseminar SS 2024 - Session 5}
|
||||
|
||||
\url{https://app.sli.do/event/uEz8fJWkLBNm1sthQovXNH}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Programming resources}
|
||||
\footnotesize
|
||||
\begin{tabular}{ll}
|
||||
Learning statistics with R & {\url{https://learningstatisticswithr.com/book/}} \\
|
||||
&\\
|
||||
R for Data Science & {\url{https://r4ds.hadley.nz/}} \\
|
||||
&\\
|
||||
Advanced R & {\url{https://adv-r.hadley.nz/}} \\
|
||||
&\\
|
||||
Happy Git and GitHub for the useR & {\url{https://happygitwithr.com/}} \\
|
||||
&\\
|
||||
R Programming for Research & {\url{https://geanders.github.io/RProgrammingForResearch/}} \\
|
||||
&\\
|
||||
Building reproducible analytical pipelines with R & {\url{https://raps-with-r.dev/}} \\
|
||||
&\\
|
||||
Data Skills for Reproducible Science & {\url{https://psyteachr.github.io/msc-data-skills/}} \\
|
||||
\end{tabular}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{Agenda}
|
||||
\centering
|
||||
\begin{tabular}{ll}
|
||||
\hline
|
||||
Date & Topic \\
|
||||
\hline
|
||||
2024-05-13 & Introduction to data management \\
|
||||
2024-05-27 & Workflow \\
|
||||
2024-06-10 & Data organisation\\
|
||||
2024-06-24 & Data sharing \\
|
||||
\only<1>{2024-07-08}\only<2>{\bf 2024-07-08} &
|
||||
\only<1>{Clean coding}\only<2>{\bf Clean coding} \\
|
||||
2024-07-22 & Version control \\
|
||||
\hline
|
||||
\end{tabular}
|
||||
\end{frame}
|
||||
|
||||
% Understandable coding
|
||||
% Cleaning up R code for readability
|
||||
% Documentation of a final R script
|
||||
% Reproducible code
|
||||
|
||||
\section{Style guidelines}
|
||||
|
||||
\begin{frame}[<+->]{Style guidelines in R}
|
||||
\begin{itemize}
|
||||
\item R has no mandatory or commonly accepted style guide
|
||||
\item However, Hadley Wickham and Google developed style guides which are
|
||||
now widely accepted
|
||||
\begin{itemize}
|
||||
\item \url{https://google.github.io/styleguide/Rguide.html}
|
||||
\item \url{https://style.tidyverse.org/}
|
||||
\end{itemize}
|
||||
\item It is always a good idea to follow a style guide and not ``create''
|
||||
your own rules (if you deviate, be consistent!)
|
||||
\item A style guide helps with
|
||||
\begin{itemize}
|
||||
\item Keeping code clean which is easier to read and interpret
|
||||
\item Making it easier to catch and fix mistakes
|
||||
\item Making it easier for others to follow and adapt your code
|
||||
\item Preventing possible problems, e.\,g., avoiding dots in function
|
||||
names
|
||||
\end{itemize}
|
||||
\end{itemize}
|
||||
\nocite{Wickham_styleguide, Anderson2023}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile, allowframebreaks]{File names}
|
||||
\begin{itemize}
|
||||
\item File names should be meaningful and end in .R
|
||||
\item Avoid using special characters in file names
|
||||
\item Stick with numbers, letters, \verb+-+, and \verb+_+
|
||||
\begin{lstlisting}[identifierstyle = \bfseries\color{iwmgray}]
|
||||
# Good
|
||||
fit_models.R
|
||||
utility_functions.R
|
||||
|
||||
# Bad
|
||||
fit models.R
|
||||
foo.r
|
||||
stuff.r
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item If files should be run in a particular order, prefix them with numbers
|
||||
\item If it seems likely you’ll have more than 10 files, left pad with zero
|
||||
\begin{lstlisting}[identifierstyle = \bfseries\color{iwmgray}]
|
||||
00_download.R
|
||||
01_explore.R
|
||||
...
|
||||
09_model.R
|
||||
10_visualize.R
|
||||
\end{lstlisting}
|
||||
\item If you later realize that you missed some steps, it’s tempting to use
|
||||
02a, 02b, etc.
|
||||
\item However, it is generally better to bite the bullet and rename all
|
||||
files
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile, allowframebreaks]{Object names}
|
||||
\begin{itemize}
|
||||
\item Variable and function names should use only lowercase letters,
|
||||
numbers, and \verb+_+
|
||||
\item Use underscores (\verb+_+) (so called snake case) to separate words
|
||||
within a name
|
||||
\begin{lstlisting}[identifierstyle = \bfseries\color{iwmgray}]
|
||||
# Good
|
||||
day_one
|
||||
day_1
|
||||
|
||||
# Bad
|
||||
DayOne
|
||||
dayone
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item Generally, variable names should be nouns and function names should be
|
||||
verbs
|
||||
\item Strive for names that are concise and meaningful
|
||||
\begin{lstlisting}[identifierstyle = \bfseries\color{iwmgray}]
|
||||
# Good
|
||||
day_one
|
||||
|
||||
# Bad
|
||||
first_day_of_the_month
|
||||
djm1
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item Avoid re-using names of common functions and variables
|
||||
\begin{lstlisting}
|
||||
# Bad
|
||||
T <- FALSE
|
||||
c <- 10
|
||||
mean <- function(x) sum(x)
|
||||
\end{lstlisting}
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile, allowframebreaks]{Spacing}
|
||||
\begin{itemize}
|
||||
\item Always put a space after a comma, never before
|
||||
\begin{lstlisting}
|
||||
# Good
|
||||
x[, 1]
|
||||
|
||||
# Bad
|
||||
x[,1]
|
||||
x[ ,1]
|
||||
x[ , 1]
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item Do not put spaces inside or outside parentheses for regular function
|
||||
calls
|
||||
\begin{lstlisting}
|
||||
# Good
|
||||
mean(x, na.rm = TRUE)
|
||||
|
||||
# Bad
|
||||
mean (x, na.rm = TRUE)
|
||||
mean( x, na.rm = TRUE )
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item Place a space before and after \texttt{()} when used with \texttt{if},
|
||||
\texttt{for}, or \texttt{while}
|
||||
\begin{lstlisting}
|
||||
# Good
|
||||
if (debug) {
|
||||
show(x)
|
||||
}
|
||||
|
||||
# Bad
|
||||
if(debug){
|
||||
show(x)
|
||||
}
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item Place a space after \texttt{()} used for function arguments
|
||||
\begin{lstlisting}
|
||||
# Good
|
||||
function(x) {}
|
||||
|
||||
# Bad
|
||||
function (x) {}
|
||||
function(x){}
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item Most infix operators (\verb+==+, \verb|+|, \verb+-+, \verb+<-+, etc.)
|
||||
should always be surrounded by spaces
|
||||
\begin{lstlisting}
|
||||
# Good
|
||||
height <- (feet * 12) + inches
|
||||
mean(x, na.rm = TRUE)
|
||||
|
||||
# Bad
|
||||
height<-feet*12+inches
|
||||
mean(x, na.rm=TRUE)
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item There are a few exceptions, which should never be surrounded by
|
||||
spaces: \verb+::+, \verb+:::+, \verb+$+, \verb+@+, \verb+[+, \verb+[[+,
|
||||
\verb+?+, \verb+^+, and \verb+:+
|
||||
{\small
|
||||
\begin{lstlisting}
|
||||
# Good
|
||||
sqrt(x^2 + y^2)
|
||||
df$z
|
||||
x <- 1:10
|
||||
package?stats
|
||||
?mean
|
||||
|
||||
# Bad
|
||||
sqrt(x ^ 2 + y ^ 2)
|
||||
df $ z
|
||||
x <- 1 : 10
|
||||
package ? stats
|
||||
? mean
|
||||
\end{lstlisting}
|
||||
}
|
||||
\item Adding extra spaces is ok if it improves alignment of \verb+=+ or
|
||||
\verb+<-+
|
||||
\begin{lstlisting}
|
||||
# Good
|
||||
list(
|
||||
total = a + b + c,
|
||||
mean = (a + b + c) / n
|
||||
)
|
||||
|
||||
# Also fine
|
||||
list(
|
||||
total = a + b + c,
|
||||
mean = (a + b + c) / n
|
||||
)
|
||||
\end{lstlisting}
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
% CITE:
|
||||
% https://style.tidyverse.org/index.html
|
||||
% R Programming for Reserach: https://geanders.github.io/RProgrammingForResearch/
|
||||
% Building reproducible analytical pipelines with R: https://raps-with-r.dev/
|
||||
|
||||
\section{Script organisation}
|
||||
|
||||
\begin{frame}[fragile]{Script header}
|
||||
\begin{itemize}
|
||||
\item It can be very helpful to have some general information right at the
|
||||
top when opening a script
|
||||
\begin{lstlisting}
|
||||
# 01_preprocessing.R
|
||||
#
|
||||
# Cleaning up toy data set (Methods Seminar SS2024)
|
||||
#
|
||||
# Input: rawdata/RDM_MS_SS2024_download_2024-06-07.csv
|
||||
# Output: processed/data_rdm-ms-ss2024_cleaned.csv
|
||||
# processed/data_rdm-ms-ss2024_cleaned.RData
|
||||
#
|
||||
# Created: 2024-06-03, NW
|
||||
\end{lstlisting}
|
||||
\item These metadata help you remember faster what you did
|
||||
\item Might not be necessary when using consistent version control (but does
|
||||
not hurt either)
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Line length}
|
||||
{}
|
||||
\begin{center}
|
||||
{\Large\bf Keep lines to 80 characters or less!}
|
||||
\end{center}
|
||||
\begin{lstlisting}
|
||||
# Good
|
||||
my_df <- data.frame(n = 1:3,
|
||||
letter = c("a", "b", "c"),
|
||||
cap_letter = c("A", "B", "C"))
|
||||
|
||||
# Bad
|
||||
my_df <- data.frame(n = 1:3, letter = c("a", "b", "c"), cap_letter = c("A", "B", "C"))
|
||||
\end{lstlisting}
|
||||
\begin{itemize}
|
||||
\item Ensures that your code is formatted in a way that you can see all of
|
||||
the code without scrolling horizontally
|
||||
\item To set your script pane to be limited to 80 characters, go to\\
|
||||
\verb+RStudio -> Preferences -> Code -> Display+\\
|
||||
and set ``Margin Column'' to 80
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile, allowframebreaks]{File organisation}
|
||||
\begin{itemize}
|
||||
\item Try to write scripts that are concerned with one (major) task
|
||||
\item If you can find a name, that captures the content, it is usually a
|
||||
good way to start
|
||||
\item Some (random) examples
|
||||
\begin{lstlisting}[identifierstyle = \bfseries\color{iwmgray}]
|
||||
download-data.R
|
||||
data-cleaning.R
|
||||
cluster_analysis_exp1.R
|
||||
visualization_logistic-model.R
|
||||
anova_h1.R
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item Export data sets for new scripts (do not make yourself run all scripts
|
||||
up to script 5 each time, just because you need the data in a certain
|
||||
format)
|
||||
\begin{lstlisting}
|
||||
# Interoperable
|
||||
write.table(dat,
|
||||
file = "data_exp1_cleaned.csv",
|
||||
sep = ";",
|
||||
quote = FALSE,
|
||||
row.names = FALSE)
|
||||
|
||||
# Preserve order of factor levels, date formats, etc.
|
||||
save(dat, file = "data_exp1_cleaned.RData")
|
||||
\end{lstlisting}
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile, allowframebreaks]{Internal structure}
|
||||
\begin{itemize}
|
||||
\item Use commented lines with \texttt{-} or \texttt{=} to break your file
|
||||
up into chunks
|
||||
\item Load additional packages at the beginning of the script
|
||||
\begin{lstlisting}
|
||||
library(lme4)
|
||||
library(sjPlot)
|
||||
|
||||
# Load data ---------------------------
|
||||
|
||||
# Plot data ---------------------------
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item If you load several packages, be aware that the order of loading
|
||||
matters!
|
||||
\item If you use only one or two functions from a package, get the function
|
||||
with \verb+::+ instead of loading the whole package
|
||||
\begin{lstlisting}
|
||||
library(lme4)
|
||||
...
|
||||
|
||||
# Fit mixed-effects model to test Hypothesis 1
|
||||
lme1 <- lmer(Reaction ~ Days + (Days | Subject), sleepstudy)
|
||||
summary(lme1)
|
||||
sjPlot::tab_model(lme1)
|
||||
\end{lstlisting}
|
||||
\framebreak
|
||||
|
||||
\item Group related pieces of code together
|
||||
\item Separate blocks of code by empty spaces
|
||||
\begin{lstlisting}
|
||||
# Load data
|
||||
library(faraway)
|
||||
data(nepali)
|
||||
|
||||
# Relabel sex variable
|
||||
nepali$sex <- factor(nepali$sex,
|
||||
levels = c(1, 2),
|
||||
labels = c("Male", "Female"))
|
||||
\end{lstlisting}
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
|
||||
\begin{frame}{How can I test if my code is reproducible?}
|
||||
% slido
|
||||
\centering
|
||||
\includegraphics[width = 5cm]{../figures/QR Code for Methodenseminar SS 2024 - Session 5}
|
||||
|
||||
\url{https://app.sli.do/event/uEz8fJWkLBNm1sthQovXNH}
|
||||
\end{frame}
|
||||
|
||||
\section{Code reviews}
|
||||
|
||||
\begin{frame}[<+->]{Use your peers}
|
||||
\begin{itemize}
|
||||
\item Do not overthink it!
|
||||
\item Just give your data and code to a colleague and ask them to reproduce
|
||||
what you did (this sounds easy, but it is actually not!)
|
||||
\item This will give you tons of insights about your workflow
|
||||
\begin{itemize}
|
||||
\item Can this person (in general) understand what you did?
|
||||
\item Is this person able to easily put your data on their machine and
|
||||
run the code right away?
|
||||
\item Anything this person would have done differently?
|
||||
\item Discuss why and which things you do differently
|
||||
\end{itemize}
|
||||
\item Reading other peoples's code is the best way to learn about how things
|
||||
can be done differently than you do them
|
||||
\item You can review code by printing it out and adding comments by hand\\
|
||||
(I highly recommend this!)
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\appendix
|
||||
%\begin{frame}[allowframebreaks]{References}
|
||||
\begin{frame}{References}
|
||||
%\renewcommand{\bibfont}{\small}
|
||||
\printbibliography
|
||||
\vfill
|
||||
\end{frame}
|
||||
|
||||
\end{document}
|
||||
|
||||
@@ -0,0 +1,23 @@
|
||||
# Last session: Wrap-up
|
||||
|
||||
How to apply all we learned this semester to archiving our research data at the
|
||||
IWM:
|
||||
|
||||
|
||||
* Show how to fill in the input mask
|
||||
|
||||
* Details on how to prepare data and folders
|
||||
|
||||
Show slide set "How to know what to archive"
|
||||
|
||||
* How to upload research data
|
||||
|
||||
* How to create new version of research data
|
||||
|
||||
* How to update meta data
|
||||
|
||||
* Explain the "Status" mechanism
|
||||
|
||||
* Show that only one person per data set has access to the meta data entry
|
||||
|
||||
|
||||
@@ -0,0 +1,408 @@
|
||||
\documentclass[aspectratio=169]{beamer}
|
||||
|
||||
\usepackage{tikz}
|
||||
\usetikzlibrary{fit}
|
||||
|
||||
\usepackage{listings}
|
||||
\usepackage[utf8,latin1]{inputenc}
|
||||
\usepackage{multirow}
|
||||
\usepackage{color, colortbl}
|
||||
\usepackage{fontawesome5} % get icons
|
||||
|
||||
\makeatletter \def\newblock{\beamer@newblock} \makeatother
|
||||
|
||||
\beamertemplatenavigationsymbolsempty
|
||||
\setbeamertemplate{itemize items}[circle]
|
||||
\setbeamertemplate{section in toc}[circle]
|
||||
\mode<beamer>{\setbeamercolor{math text displayed}{fg=iwmgrau}}
|
||||
\setbeamercolor{block body}{bg=iwmorange!50!white}
|
||||
\setbeamercolor{block title}{fg=white, bg=iwmorange}
|
||||
|
||||
\definecolor{iwmorange}{RGB}{255,105,0}
|
||||
\definecolor{iwmgray}{RGB}{67,79,79}
|
||||
\definecolor{iwmblue}{RGB}{60,180,220}
|
||||
\definecolor{iwmpurple}{RGB}{120,0,75}
|
||||
|
||||
\definecolor{iwmorange}{RGB}{255,105,0}
|
||||
\definecolor{iwmgrau}{RGB}{67,79,79}
|
||||
\setbeamercolor{title}{fg=iwmorange}
|
||||
\setbeamercolor{frametitle}{fg=iwmorange}
|
||||
\setbeamercolor{structure}{fg=iwmorange}
|
||||
\setbeamercolor{normal text}{fg=iwmgrau}
|
||||
\setbeamercolor{author}{fg=iwmgrau}
|
||||
\setbeamercolor{date}{fg=iwmgrau}
|
||||
|
||||
\lstset{language=bash,%
|
||||
literate={Ü}{{\"U}}1
|
||||
{ü}{{\"u}}1,
|
||||
backgroundcolor=\color{iwmgrau!15!white},
|
||||
basicstyle=\ttfamily\color{iwmgrau},
|
||||
frame=none,
|
||||
basicstyle=\ttfamily\color{iwmgrau},
|
||||
commentstyle=\slshape\color{iwmgrau},
|
||||
keywordstyle=\bfseries\color{iwmgrau},
|
||||
identifierstyle=\color{iwmgrau},
|
||||
stringstyle=\color{iwmgrau},
|
||||
numbers=none,%left,numberstyle=\tiny,
|
||||
basewidth={.5em, .4em},
|
||||
showstringspaces=false,
|
||||
emphstyle=\color{red!50!white}}
|
||||
|
||||
\pgfmathdeclarefunction{gauss}{2}{%
|
||||
\pgfmathparse{1/(#2*sqrt(2*pi))*exp(-((x-#1)^2)/(2*#2^2))}%
|
||||
}
|
||||
|
||||
\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{How to know what to archive}
|
||||
\author{Nora Wickelmaier}
|
||||
\date{\today}
|
||||
|
||||
\begin{document}
|
||||
|
||||
\begin{frame}{}
|
||||
\thispagestyle{empty}
|
||||
\titlepage
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}{The basics}
|
||||
Data
|
||||
\begin{itemize}
|
||||
\item Keep your raw data in a separate folder
|
||||
\item If your raw data \emph{do not contain any personal data} submit them
|
||||
with your analysis-ready data files
|
||||
\item Submit the analysis script that got your raw data to
|
||||
``analysis-ready`` (or at least a description of the process)\pause\hfill
|
||||
{\bf\color{iwmpurple} Check out our Research Data Policy!}
|
||||
\end{itemize}
|
||||
\pause
|
||||
Material
|
||||
\begin{itemize}
|
||||
\item Submit all materials that have been used to create these data
|
||||
\begin{itemize}
|
||||
\item Questionnaires
|
||||
\item Program code for experiments
|
||||
\item Stimuli presented, e.\,g., pictures or similar
|
||||
\item \dots
|
||||
\end{itemize}
|
||||
\end{itemize}
|
||||
\pause
|
||||
Documentation
|
||||
\begin{itemize}
|
||||
\item Add a description of your data and experiment
|
||||
\item In its simplest form this can just be a README file, ideally as text
|
||||
or PDF file
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Previous folder structure on \texttt{Y:/}}
|
||||
\begin{columns}
|
||||
\begin{column}{.4\textwidth}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 3.6cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node[text width = 2cm] (top) at (0, 0) {\faIcon{folder} \verb+study+};
|
||||
% first level
|
||||
\node (n1) at (4, 0) {\faIcon{folder} \verb+data+};
|
||||
\node (n2) at (4, -0.7) {\faIcon{folder} \verb+ethik+};
|
||||
\node (n3) at (4, -1.4) {\faIcon{folder} \verb+material+};
|
||||
\node (n4) at (4, -2.1) {\faIcon{folder} \verb+pub+};
|
||||
\node (n5) at (4, -2.8) {\faIcon{folder} \verb+scans+};
|
||||
\path (top.east) -- (n1.west);
|
||||
\path (top.east) -- (n2.west);
|
||||
\path (top.east) -- (n3.west);
|
||||
\path (top.east) -- (n4.west);
|
||||
\path (top.east) -- (n5.west);
|
||||
\end{tikzpicture}
|
||||
\end{column}
|
||||
\begin{column}{.6\textwidth}
|
||||
\begin{itemize}[<+->]
|
||||
\item Very basic (and good) folder structure for a research project
|
||||
\item Submitting the approval document of our \emph{local} ethics
|
||||
committee is now optional, since the connection will be possible via
|
||||
your meta data\\
|
||||
% $\to$ If the project was evaluated by an external ethics committee it
|
||||
% might still be a good idea to submit the approval document
|
||||
\item Data and material are the most important folders to help other
|
||||
people make sense of your data
|
||||
\end{itemize}
|
||||
\end{column}
|
||||
\end{columns}
|
||||
\vfill
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Some additional suggestions}
|
||||
\vspace{.2cm}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 3.6cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node[text width = 2cm] (top) at (0, 0) {\faIcon{folder} \verb+study+};
|
||||
% first level
|
||||
\node (n1) at (4, 0) {\faIcon{folder} \verb+code+};
|
||||
\node (n2) at (4, -0.7) {\faIcon{folder} \verb+data+};
|
||||
\node (n3) at (4, -1.4) {\faIcon{folder} \verb+material+};
|
||||
\node (n4) at (4, -2.1) {\faIcon{folder} \verb+preregistration+};
|
||||
\node (file) at (4, -2.8) {\faIcon[regular]{file} \verb+README.md+};
|
||||
\path (top.east) -- (n1.west);
|
||||
\path (top.east) -- (n2.west);
|
||||
\path (top.east) -- (n3.west);
|
||||
\path (top.east) -- (n4.west);
|
||||
\path (top.east) -- (file.west);
|
||||
\end{tikzpicture}
|
||||
\pause
|
||||
\vfill
|
||||
Separate your code from your data folder and add your preregistration for the
|
||||
project
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Some additional suggestions}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 3.6cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node[text width = 2cm] (top) at (0, 0) {\faIcon{folder} \verb+study+};
|
||||
% first level
|
||||
\node (n1) at (4, 0) {\faIcon{folder} \verb+code+};
|
||||
\node (n2) at (4, -0.7) {\faIcon{folder} \verb+data+};
|
||||
\node (n3) at (4, -1.4) {\faIcon{folder} \verb+material+};
|
||||
\node (n4) at (4, -2.1) {\faIcon{folder} \verb+preregistration+};
|
||||
\node (file) at (4, -2.8) {\faIcon[regular]{file} \verb+README.md+};
|
||||
\path (top.east) -- (n1.west);
|
||||
\path (top.east) -- (n2.west);
|
||||
\path (top.east) -- (n3.west);
|
||||
\path (top.east) -- (n4.west);
|
||||
\path (top.east) -- (file.west);
|
||||
% second level
|
||||
\node[text width = 5cm] (o1) at (10, 0) {\faIcon[regular]{file} \verb+01_preprocessing.R+};
|
||||
\node[text width = 5cm] (o2) at (10, -0.7) {\faIcon[regular]{file} \verb+02_descriptives.R+};
|
||||
\node[text width = 5cm] (o3) at (10, -1.4) {\faIcon[regular]{file} \verb+03_modeling.R+};
|
||||
\node[text width = 5cm] (o4) at (10, -2.1) {\faIcon[regular]{file} \verb+04_plots.R+};
|
||||
\path (n1.east) -- (o1.west);
|
||||
\path (n1.east) -- (o2.west);
|
||||
\path (n1.east) -- (o3.west);
|
||||
\path (n1.east) -- (o4.west);
|
||||
\end{tikzpicture}
|
||||
\vfill
|
||||
Separate your code from your data folder and add your preregistration for the
|
||||
project
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Some additional suggestions}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 3.6cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node[text width = 2cm] (top) at (0, 0) {\faIcon{folder} \verb+study+};
|
||||
% first level
|
||||
\node (n1) at (4, 0) {\faIcon{folder} \verb+code+};
|
||||
\node (n2) at (4, -0.7) {\faIcon{folder} \verb+data+};
|
||||
\node (n3) at (4, -1.4) {\faIcon{folder} \verb+material+};
|
||||
\node (n4) at (4, -2.1) {\faIcon{folder} \verb+preregistration+};
|
||||
\node (file) at (4, -2.8) {\faIcon[regular]{file} \verb+README.md+};
|
||||
\path (top.east) -- (n1.west);
|
||||
\path (top.east) -- (n2.west);
|
||||
\path (top.east) -- (n3.west);
|
||||
\path (top.east) -- (n4.west);
|
||||
\path (top.east) -- (file.west);
|
||||
% second level
|
||||
\node[text width = 6cm] (o1) at (10.5, -0.7) {\faIcon{folder} \verb+01_raw-data+};
|
||||
\node[text width = 6cm] (o2) at (10.5, -1.4) {\faIcon{folder} \verb+02_processed-data+};
|
||||
\node[text width = 6cm] (o3) at (10.5, -2.1) {\faIcon[regular]{file}
|
||||
\verb+codebook_processed-data.pdf+};
|
||||
\path (n2.east) -- (o1.west);
|
||||
\path (n2.east) -- (o2.west);
|
||||
\path (n2.east) -- (o3.west);
|
||||
\end{tikzpicture}
|
||||
\vfill
|
||||
Separate your code from your data folder and add your preregistration for the
|
||||
project
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Some additional suggestions}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 3.6cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node[text width = 2cm] (top) at (0, 0) {\faIcon{folder} \verb+study+};
|
||||
% first level
|
||||
\node (n1) at (4, 0) {\faIcon{folder} \verb+code+};
|
||||
\node (n2) at (4, -0.7) {\faIcon{folder} \verb+data+};
|
||||
\node (n3) at (4, -1.4) {\faIcon{folder} \verb+material+};
|
||||
\node (n4) at (4, -2.1) {\faIcon{folder} \verb+preregistration+};
|
||||
\node (file) at (4, -2.8) {\faIcon[regular]{file} \verb+README.md+};
|
||||
\path (top.east) -- (n1.west);
|
||||
\path (top.east) -- (n2.west);
|
||||
\path (top.east) -- (n3.west);
|
||||
\path (top.east) -- (n4.west);
|
||||
\path (top.east) -- (file.west);
|
||||
% second level
|
||||
\node[text width = 5cm] (o1) at (10, -1.4) {\faIcon{folder} \verb+stimuli+};
|
||||
\node[text width = 5cm] (o2) at (10, -2.1) {\faIcon[regular]{file} \verb+survey01.pdf+};
|
||||
\node[text width = 5cm] (o3) at (10, -2.8) {\faIcon[regular]{file} \verb+survey02.pdf+};
|
||||
\path (n3.east) -- (o1.west);
|
||||
\path (n3.east) -- (o2.west);
|
||||
\path (n3.east) -- (o3.west);
|
||||
\end{tikzpicture}
|
||||
\vfill
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Some additional suggestions}
|
||||
\vspace{.4cm}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 3.6cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node[text width = 2cm] (top) at (0, 0) {\faIcon{folder} \verb+study+};
|
||||
% first level
|
||||
\node (n1) at (4, 0) {\faIcon{folder} \verb+code+};
|
||||
\node (n2) at (4, -0.7) {\faIcon{folder} \verb+data+};
|
||||
\node (n3) at (4, -1.4) {\faIcon{folder} \verb+material+};
|
||||
\node (n4) at (4, -2.1) {\faIcon{folder} \verb+preregistration+};
|
||||
\node (file) at (4, -2.8) {\faIcon[regular]{file} \verb+README.md+};
|
||||
\path (top.east) -- (n1.west);
|
||||
\path (top.east) -- (n2.west);
|
||||
\path (top.east) -- (n3.west);
|
||||
\path (top.east) -- (n4.west);
|
||||
\path (top.east) -- (file.west);
|
||||
% second level
|
||||
\node[text width = 6cm] (o1) at (10.5, -2.1) {\faIcon[regular]{file} \verb+2024-06-11_prereg_study.pdf+};
|
||||
\path (n4.east) -- (o1.west);
|
||||
\end{tikzpicture}
|
||||
\pause
|
||||
\vfill
|
||||
A preregistration usually contains all important information like what
|
||||
variables have been collected, what were the hypotheses, etc.
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Some additional suggestions}
|
||||
\begin{columns}
|
||||
\begin{column}{.45\textwidth}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 3.6cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node[text width = 2cm] (top) at (0, 0) {\faIcon{folder} \verb+study+};
|
||||
% first level
|
||||
\node (n1) at (4, 0) {\faIcon{folder} \verb+code+};
|
||||
\node (n2) at (4, -0.7) {\faIcon{folder} \verb+data+};
|
||||
\node (n3) at (4, -1.4) {\faIcon{folder} \verb+material+};
|
||||
\node (n4) at (4, -2.1) {\faIcon{folder} \verb+preregistration+};
|
||||
\node (file) at (4, -2.8) {\faIcon[regular]{file} \verb+README.md+};
|
||||
\path (top.east) -- (n1.west);
|
||||
\path (top.east) -- (n2.west);
|
||||
\path (top.east) -- (n3.west);
|
||||
\path (top.east) -- (n4.west);
|
||||
\path (top.east) -- (file.west);
|
||||
\end{tikzpicture}
|
||||
\end{column}
|
||||
\begin{column}{.55\textwidth}
|
||||
\vspace{-3cm}
|
||||
\begin{itemize}
|
||||
\item Add any additional folders that you need
|
||||
\end{itemize}
|
||||
\end{column}
|
||||
\end{columns}
|
||||
\end{frame}
|
||||
|
||||
|
||||
\begin{frame}[fragile]{Some additional suggestions}
|
||||
\vspace{1cm}
|
||||
\begin{columns}
|
||||
\begin{column}{.45\textwidth}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 3.6cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node[text width = 2cm] (top) at (0, 0) {\faIcon{folder} \verb+study+};
|
||||
% first level
|
||||
\node (n1) at (4, 0) {\faIcon{folder} \bf background};
|
||||
\node (n2) at (4, -0.7) {\faIcon{folder} \verb+code+};
|
||||
\node (n3) at (4, -1.4) {\faIcon{folder} \verb+data+};
|
||||
\node (n4) at (4, -2.1) {\faIcon{folder} \verb+material+};
|
||||
\node (n5) at (4, -2.8) {\faIcon{folder} \verb+preregistration+};
|
||||
\node (file) at (4, -3.5) {\faIcon[regular]{file} \verb+README.md+};
|
||||
\path (top.east) -- (n1.west);
|
||||
\path (top.east) -- (n2.west);
|
||||
\path (top.east) -- (n3.west);
|
||||
\path (top.east) -- (n4.west);
|
||||
\path (top.east) -- (n5.west);
|
||||
\path (top.east) -- (file.west);
|
||||
\end{tikzpicture}
|
||||
\end{column}
|
||||
\begin{column}{.55\textwidth}
|
||||
\vspace{-2.5cm}
|
||||
\begin{itemize}
|
||||
\item Add any additional folders that you need
|
||||
\item Maybe a folder \verb+background+ with a PhD expos{\'e} or a grant
|
||||
application (or both)
|
||||
\end{itemize}
|
||||
\end{column}
|
||||
\end{columns}
|
||||
\vfill
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}[fragile]{Some additional suggestions}
|
||||
\vspace{.5cm}
|
||||
\begin{columns}
|
||||
\begin{column}{.45\textwidth}
|
||||
\begin{tikzpicture}[
|
||||
every node/.style = {text width = 3.6cm, align = left},
|
||||
every path/.style = {thick, draw}
|
||||
]
|
||||
\node[text width = 2cm] (top) at (0, 0) {\faIcon{folder} \verb+study+};
|
||||
% first level
|
||||
\node (n1) at (4, 0) {\faIcon{folder} \verb+code+};
|
||||
\node (n2) at (4, -0.7) {\faIcon{folder} \verb+data+};
|
||||
\node (n3) at (4, -1.4) {\faIcon{folder} \verb+material+};
|
||||
\node (n4) at (4, -2.1) {\faIcon{folder} \verb+preregistration+};
|
||||
\node (n5) at (4, -2.8) {\faIcon{folder} \bf software};
|
||||
\node (file) at (4, -3.5) {\faIcon[regular]{file} \verb+README.md+};
|
||||
\path (top.east) -- (n1.west);
|
||||
\path (top.east) -- (n2.west);
|
||||
\path (top.east) -- (n3.west);
|
||||
\path (top.east) -- (n4.west);
|
||||
\path (top.east) -- (n5.west);
|
||||
\path (top.east) -- (file.west);
|
||||
\end{tikzpicture}
|
||||
\end{column}
|
||||
\begin{column}{.55\textwidth}
|
||||
\begin{itemize}
|
||||
\item Add any additional folders that you need
|
||||
\item Maybe a folder \verb+background+ with a PhD expos{\'e} or a grant
|
||||
application (or both)
|
||||
\item Or a folder \verb+software+ with Python or Matlab code that you
|
||||
wrote for your experiment
|
||||
\item \dots
|
||||
\end{itemize}
|
||||
\vfill
|
||||
\end{column}
|
||||
\end{columns}
|
||||
\end{frame}
|
||||
|
||||
|
||||
\begin{frame}{}
|
||||
{}
|
||||
\begin{center}
|
||||
{\Huge\color{iwmblue} Don't overthink it and use common sense.\\
|
||||
\vspace{1cm}\pause
|
||||
Then add everything that you think a colleague needs to understand what you
|
||||
did.}
|
||||
\end{center}
|
||||
|
||||
\end{frame}
|
||||
|
||||
\end{document}
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
| 2024-06-10 | Data organisation |
|
||||
| 2024-06-24 | Data sharing |
|
||||
| 2024-07-08 | Clean coding |
|
||||
| 2024-07-22 | Version control |
|
||||
| 2024-07-22 | Archiving data at the IWM |
|
||||
|
||||
# Literature
|
||||
|
||||
@@ -20,6 +20,10 @@ 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
|
||||
|
||||
Wicherts, J. M., & Bakker, M. (2012).Publish (your data) or (let the data)
|
||||
perish! Why not publish your data too? _Intelligence, 40_(2), 73–76.
|
||||
https://doi.org/10.1016/j.intell.2012.01.004
|
||||
|
||||
Wilbrandt, J. (2023). Research Data Management Intro Series: Coffee Lectures &
|
||||
Espresso Shots. https://doi.org/10.5281/zenodo.7573695
|
||||
|
||||
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 5.6 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 5.7 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 11 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 43 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 146 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 529 KiB |
@@ -1,3 +1,11 @@
|
||||
@book{Anderson2023,
|
||||
title = {R programming for research},
|
||||
author = {Brooke Anderson and Rachel Severson and Nicholas Good},
|
||||
year = {2023},
|
||||
publisher = {Colorado State University, ERHS 535},
|
||||
url = {https://geanders.github.io/RProgrammingForResearch/}
|
||||
}
|
||||
|
||||
@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},
|
||||
@@ -8,6 +16,14 @@
|
||||
doi = {10.1525/collabra.18684}
|
||||
}
|
||||
|
||||
@book{Koeller2004,
|
||||
title = {Wege zur {H}ochschulreife in {B}aden-{W}{\"u}rttemberg: {TOSCA} -- {E}ine {U}ntersuchung an allgemein bildenden und beruflichen {G}ymnasien},
|
||||
author = {K{\"o}ller, Olaf and Watermann, Ralf and Trautwein, Ulrich and L{\"u}dtke, Oliver},
|
||||
year = {2004},
|
||||
publisher = {Springer},
|
||||
doi = {10.1007/978-3-322-80906-3}
|
||||
}
|
||||
|
||||
@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},
|
||||
@@ -30,6 +46,35 @@
|
||||
doi = {10.1177/2515245917747656}
|
||||
}
|
||||
|
||||
@article{Ngo2023,
|
||||
title = {Spot the bot: Investigating user's detection cues for social bots and their willingness to verify Twitter profiles},
|
||||
journal = {Computers in Human Behavior},
|
||||
volume = {146},
|
||||
pages = {107819},
|
||||
year = {2023},
|
||||
issn = {0747-5632},
|
||||
doi = {https://doi.org/10.1016/j.chb.2023.107819},
|
||||
url = {https://www.sciencedirect.com/science/article/pii/S074756322300170X},
|
||||
author = {Thao Ngo and Magdalena Wischnewski and Rebecca Bernemann and Martin Jansen and Nicole Kr{\"a}mer}
|
||||
}
|
||||
|
||||
@article{Wicherts2012,
|
||||
title = {Publish (your data) or (let the data) perish! {W}hy not publish your data too?},
|
||||
author = {Wicherts, Jelte M and Bakker, Marjan},
|
||||
journal = {Intelligence},
|
||||
volume = {40},
|
||||
number = {2},
|
||||
pages = {73--76},
|
||||
year = {2012},
|
||||
doi = {10.1016/j.intell.2012.01.004}
|
||||
}
|
||||
|
||||
@misc{Wickham_styleguide,
|
||||
author = {Hadley Wickham},
|
||||
title = {The tidyverse style guide},
|
||||
url = {https://style.tidyverse.org/}
|
||||
}
|
||||
|
||||
@misc{Wilbrandt2023,
|
||||
author = {Wilbrandt, Jeanne},
|
||||
title = {{Research Data Management Intro Series: Coffee Lectures \& Espresso Shots}},
|
||||
|
||||
Reference in New Issue
Block a user