Data Management and Reproducibility Workshop
The CPD invites you to participate in the following workshop "Data Management and Reproducibility Workshop". As reproducibility of social science research is becoming an increasing concern, data management is becoming even more important. This one-day workshop is designed to leave you with a solid foundation for creating and sharing reproducible quantitative social science projects.
Please note that space is limited so make sure to sign up as soon as possible with the link below. Priority will be given to CPD students and McGill Sociology students until March 15th.
REGISTER HERE
Abstract
This one-day workshop should give you a solid foundation for creating and sharing a reproducible quantitative social science projects. You will learn about version control, data citations and deposits, and curating a reproducible repository. You will practice using the actual tools through exercises meant to walk you through the basics of the concepts introduced.
Outline: We will go through all the necessary steps for creating a reproducible research product. We will discuss the following topics:
1. Finding, describing, accessing and sharing datasets to enhance reproducibility
2. Data management plans/planning
3. Reproducible work and code
Each topic has a number of sub-topics and we will work through exercises using tools consistent with best practices in each topic.
Location
This is an in-person event held in Education Building, 3700 McTavish Street, Room 624.
Instructor
Dr. Grant Gibson received his Ph.D. in economics in 2018 from McMaster university. Since then he has been working in research management at the Canadian Research Data Centre Network (CRDCN for short). He has published in journals such as Health Economics, Social Science & Medicine, and Data Science (pending, but I think it'll be there by the summer). He is involved in a number of Pan-Canadian initiatives around data management and is a member of the RDM (Research Data Management) network of experts. His research work generally involves unwieldy datasets from multiple sources.