![enter image description here][1] # **Independent Learning Resources Section** In this section we will collect a number of different resources which you can use in your own time. Hopefully this will help you to leran some new skills that can be applied in your research to take it to the next level. *The section will be developed and improved with time so make sure to check it out every once in a while to see what's new.* ### **Contents:** 1. Discussions and News 2. Open and Reproducible Science - First Steps 3. Data Management and Research Planning 4. Transparent lab books and notes 5. Registered Reports 6. Statistical thinking and skills development 7. Programming Skills 8. Data analysis in R 9. Researcher Profiles and Portfolios ---------- ## 1. Discussions and News Recorded talks and discussions: - **RIOT Science Club** [YouTube Page][2] Podcasts: - **Everything Hertz** (general research themes but run by psychologists) - **The Road to Open Science** by the Open Scinece Community Utrecht, multidisciplinary focus - **ReproducibiliTea** (general research themes but run by psychologists) - **The Black Goat** (mainly psychology themes but widely applicable) ## 2. Open and Reproducible Research - First Steps **Guides and tools** A preprint with [guidelines for graduate students][3] on easing into open science. Co-authored by one of our members Priya Silverstein. A very useful [useful paper][4] with tips for early career researchers on the implementation of open research. Includes a great description of the expected challenges and benefits. **The most comprehensive open and reproducible research guide** [The Turing Way Book (online)][5] **Introductory Online Courses** [Open Science MOOC (Massive Open Online Course)][6] This course includes many independent learning modules starting with open science principles, through collaborations, software, data, public engagement and more. Good for beginners in all disciplines. [Transparent and Open Social Science Research][7] This is a Future Learn platform course which may not always be available, but it's good to subscribe and be alerted when the course becomes active. ## 3. Data Management and Research Planning **PUBLICATION STRATEGY** Consider how you may want to go ahead with sharing your research from pre-registrations, through preprints towards a publication. **General guide on writing research reports** [PLOS resources and a writing toolbox][8] **Publication strategy guide** [PLOS information page][9] ---------- **PREREGISTRATIONS** You should take into consideration pre-registering your study before you start data collection. There are many benefits to this and it will help you to make your research more reproducible and transparent. **Preregistrations** are time-stamped versions of your project including your aims and hypotheses to protect you from introducing bias later on after you analyse your data. These can be public or private. Preregistration process and benefits: [Pre-registration info][10] Preregistrations guide: [Preregistration step-by-step][11] Preregistration types & templates: [Types][12] [Templates][13] ---------- **DATA MANAGEMENT PLANS** It would be very beneficial to create a thorough data management plan for each of your studies. Many funders now also expect this from you when you submit your bids for grants. These links will take you through the data management plan steps: [Data management plans guide by the OSF][14] [Data management plans guide by PLOS][15] The website below contains some templates: [DMP Templates][16] **Workshops** University of Surrey Researcher Development Programme also offer a few courses on research and data management plans. If you are a PGR student here, you can use SITS and sign up for: - Dealing with data - Data Management Plans - Research Data Management [Here][17] you can also find the slides from a workshop that was run by Alice Motes during one of the society meetings. ## 4. Transparent lab books and notes [R Markdown Guide][18] Make notes as you go through your data analysis - keep a transparent lab book. Any notes or text you write, the images, tables and figures as well as the code and the results can be organised within one document! It also allows you to create presentations and event write your publications in a template for a given journal --> [Templates][19] [Jupyter Notebooks Guide][20] If you use Python, Jupyter notebooks offer a very savvy way of keeping your notes and creating documents. Similarl to R Markdown, any notes or text you write, the images, tables and figures as well as the code and the results can be organised within one document! Have a look at this [paper][21] which also gives additional advice on using Jupyter. [Binder Guide][22] Binder is a great resource that allows you to organise the code that is stored in your Git repositories into cohesive projects. It also works well with Jupyter notebooks. Check out the introduction [Slides][23] by Andrew Stewart, University of Manchester. ## 5. Registered Reports Read this [article][24] to learn about the rise of registered reports. The main hub for information on *registered reports* is the Centre for Open Science [RR Section][25]. You should also take a look at this [table][26] to consider different expectations from journals accepting registered reports. You can also listen to a podcast [ReproducibiliTea episode 18][27] welcoming a researcher who completed a registered report during their PhD. They discuss their experience reflecting on the challenges and the benefits. ## 6. Statistical thinking and skills development Books: **The Art of Statistics: Learning from Data** **David Spiegelhalter** This is an essential book that will help you to become more open-minded about statistics and data. It is an absolute **must read** for anyone doing any work on data from undergraduate level onwards. If you ever get a chance to attend a talk by David make sure not to miss it! He is based at the University of Cambrudge and he is a great speaker! **The Design and Statistical Analysis of Animal Experiments** **Simon T. Bate & Robin A. Clark** This book is specifically directed at researchers who work with animals. Novel statistical approaches are discussed to help with the improvement of research projects from study design to analysis. **Learning Statistics with R** **Danielle Navarro** This is a comprehensive book introducing statistics for social sociences using R. It covers all common frequentist and as well as some Bayesian approaches. This is an [online book][28]. **Causal Inference in Statistics: A Primer** **Judea Pearl, Madelyn Glymour, and Nicholas P. Jewell** The book provides guidance to through understanding of causal inferences. Ideal for beginners in statistics. Fundamental knowledge that is often overlooked in common statistical training for non-statisticians. ---------- Online Courses: **Improving your statistical inferences** **Daniel Lakens**, Eindhoven University of Technology [Course Era Link][29] This is a great course that uses R for illustrations of flaws and challenges in statistical inferences. It covers frequentist and Bayesian approaches as well as important issues regarding open science and reproducibility. I strongly suggest you should follow Daniel on Twitter as he is a very active user and you can learn a lot from his tweets [@lakens][30]. **Improving you Statistical Questions** **Daniel Lakens** Eindhoven University of Technology [Course Era Link][31] Covers key statistical considerations to be made when designing new studies to improve the quality of conducted research. **Causal Inference Course** **Brady Neal** Mila - Quebec AI Institute [Online Course Details][32] An online course on causality and causal inference aimed at researchers in varied disciplines including epidemiology, economics, social science, machine learning etc. **Bayesian Statistics: Techniques and Models** **Matthew Heiner** University of California Santa Cruz [\[Course Era Link\]][33] Bayesian statistics are commonly used in many fields of research mainly related to computational modeling. They are also becoming more and more popular in basic experimental research. It is not commonly taught within the standard statistical curriculum for non-statisticians but it is extremely helpful! ---------- Online Resources: **PsyTeachR** **University of Glasgow** [PsyTeachR Link][34] The name of this platform is rather misleading as most of its components are not tightly linked to psychology alone. It can be applied across disciplines. The platform contains a large amount of resources for workshops, tutorials and lectures oriented around data reproducibility as well as the development of programming skills. ## 7. Programming Skills You may use a statistics softare for you analyses and you may be considering using programming such as R, Matlab or Python instead. Some of the above resources already include guides on using programming for stats. You may also use programming for other purposes such as data management, creating software, websites and experiments. Top support the use of good practice in programming and making your code reproducible and usable for other researchers, you should get familiar with the principles of programming first. We suggest the first two chapters of the open source book: **Think Python** **Allen B. Downey** [https://greenteapress.com/wp/think-python-2e/][35] For data management and analysis in R see the section below. ## 8. Data analysis in R University Workshops: **University of Surrey, School of Psychology Resources** **Peter Hilpert and Marta Topor** [OSF Link][36] Have a look through the worksheets used during the introductory sessions on data management in R Studio. Data files are also provided. ---------- Online Courses: **Introduction to R for Data Science** **Mark Daniel Ward**, Purdue University [Future Learn link][37] This is a great introductory course with videos and step by step instructions for big data handling in R. If you have no experience in R, this course would be ideal to start learning. The course is not always available but you can add it to your wishlist and you will be notified when you can start learning. **Introduction to R** [DataCamp Link][38] This is a very basic course in R which helps to understand the different types of data used in programming languages and specifically in R. If you have no experience of programming, this will be a good place to start. The course is always available. However, it uses R in an in-built console and there is no introduction to using R Studio. ---------- Online Resources: **R Studio Quick Guides (cheat sheets)** [R Studio Link][39] These quick guides provide a lot of information in poster formats. They are a good resource to check what you can do in R and how to go about doing it. They are also great to keep handy to help you refresh your knowledge once you learn something once. Unfortunately, if you don't use R regularly, it is easy to forget how to do different things. Therefore, you should make sure to keep the notes you have been learning from. You will probably need them again! **R for Social Scientists** [Data Carpentry Link][40] Not just for social scientists! This repository has a very well structured and accessible introduction to R. It is not like a usual online course, but completing all the steps and exercises will feel like completing a full introductory course in R. It explains how to use R studio as well as useful instructions for managing and visualising data. **Programming with R** [Software Carpentry Link][41] This is a very comprehensive repository with guides for a range of things that can be done in R. It is suitable for relative beginners, but also those who want to explore cool new things they can do with R. It has sections which are more technical and relate to the development of programming skills but also applied sections for instance on patient data. **More R!** Check out the [wiki page][42] of the Brain and Behaviour group within the school of psychology here at the University of Surrey. They have a very comprehensive list of different R resources. **Stats in R** Don't forget about the [Stats Book][43] by Danielle Navaro. It will guide you through all most commonly used statistical analyses in R. ## 9. Researcher Profiles and Portfolios We highly recommend keeping track of your open and reproducible research skills and outputs. These can be then linked to your CV and your future employers will have direct access to these resources. This will allow you to showcase your research achievements beyond published papers. **Get an ORCID iD!** You should get an [ORCID iD][44] which will keep track of your published work based on the DOIs. It will collect your published work automatically across your career even when changing your place of work. For a demonstration of ORCID benefits, see [this video][45]. Make sure to link it to University of Surrey profile when you get an ID. You can do it using the link below: [https://magic.surrey.ac.uk/orcid/servlet/Orcid][46] **Make a webiste/profile/portfolio!** If you already have ideas about how you want to keep track of your work and activities to make it easy to share with future employers or funders please let us know! We are constantly looking for inspirations and ideas. So far we can recommend using: - [GitHub pages][47] to create a website/page about yourself and your work. - Use the OSF to bring all of your projects together in one place - we are currently working on a template for this and will let you know when ready to be used! [1]: https://files.osf.io/v1/resources/4ahfw/providers/osfstorage/5f86be6b37b6bb00ed30b040?mode=render [2]: https://www.youtube.com/channel/UCqAkVUPSOg0bC5dB9tPRAVw [3]: https://psyarxiv.com/vzjdp/ [4]: https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3000246 [5]: https://the-turing-way.netlify.app/welcome [6]: https://opensciencemooc.eu/ [7]: https://www.futurelearn.com/courses/open-social-science-research [8]: https://plos.org/resources/writing-center/?utm_medium=email&utm_source=internal&utm_campaign=ae2020&utm_content=ntds [9]: https://plos.org/resource/how-to-share-your-research/ [10]: https://help.osf.io/hc/en-us/articles/360021390833-Preregistration [11]: https://help.osf.io/hc/en-us/articles/360019738834-create-a-preregistration [12]: https://osf.io/zab38/wiki/home/ [13]: https://osf.io/zab38/ [14]: https://help.osf.io/hc/en-us/articles/360019931133-Creating-a-data-management-plan-DMP-document [15]: https://plos.org/resource/how-to-store-and-manage-your-data/ [16]: https://dmptool.org/ [17]: https://osf.io/cwbq3/ [18]: https://rmarkdown.rstudio.com/ [19]: https://github.com/rstudio/rticles [20]: https://www.dataquest.io/blog/jupyter-notebook-tutorial/ [21]: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1007007 [22]: https://mybinder.readthedocs.io/en/latest/ [23]: https://bit.ly/2XwFsoL [24]: https://rss.onlinelibrary.wiley.com/doi/10.1111/j.1740-9713.2019.01299.x [25]: https://cos.io/rr/ [26]: https://docs.google.com/spreadsheets/d/1D4_k-8C_UENTRtbPzXfhjEyu3BfLxdOsn9j-otrO870/edit#gid=0 [27]: https://soundcloud.com/reproducibilitea/episode-18-hannah-hobson [28]: https://learningstatisticswithr.com/ [29]: https://www.coursera.org/learn/statistical-inferences/home/welcome [30]: https://twitter.com/lakens?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Eauthor [31]: https://www.coursera.org/learn/improving-statistical-questions [32]: https://www.bradyneal.com/causal-inference-course [33]: https://www.coursera.org/learn/mcmc-bayesian-statistics [34]: https://psyteachr.github.io/ [35]: https://greenteapress.com/wp/think-python-2e/ [36]: https://osf.io/pkjsu/ [37]: https://www.futurelearn.com/courses/data-science [38]: https://www.datacamp.com/courses/free-introduction-to-r?utm_source=adwords_ppc&utm_campaignid=805200711&utm_adgroupid=42045039256&utm_device=c&utm_keyword=%2bdatacamp%20%2br&utm_matchtype=b&utm_network=g&utm_adpostion=1t1&utm_creative=255792658557&utm_targetid=aud-334851567295:kwd-424141783896&utm_loc_interest_ms=&utm_loc_physical_ms=9045837&gclid=CjwKCAjw9dboBRBUEiwA7VrrzcxWlRRjhkgfzLqAre4gPeeY_bDF-ALdbNzwy-pyooLwkpNLCGq4ARoCVmkQAvD_BwE [39]: https://www.rstudio.com/resources/cheatsheets/ [40]: https://datacarpentry.org/r-socialsci/ [41]: https://swcarpentry.github.io/r-novice-inflammation/ [42]: https://osf.io/mydnq/wiki/5F:%20Methods%20-%20Statistics/ [43]: https://learningstatisticswithr.com/ [44]: https://orcid.org/ [45]: https://www.youtube.com/watch?v=a1Rijk_TMHA [46]: https://magic.surrey.ac.uk/orcid/servlet/Orcid [47]: https://pages.github.com/