Date: 12 December 2018
Time: 10:00 - 16:00
Location: Copenhagen University Library Frederiksberg, Dyrlægevej 10, 1870 Frederiksberg
Fee: Free

This intensive one-day course is aimed at Library and Research Services colleagues who work with bibliometrics regularly but have little or no background in statistics. The course introduces a set of statistical approaches that can be incorporated into common bibliometric analyses to aid with the responsible interpretation of results, e.g. for visualisations. Hands on training is a key element of the course, and attendees will work with the open source statistical environment ‘R’. No prior experience with R is necessary.

While including an overview of basic statistical concepts, this course is not intended as a traditional introduction to statistics. Instead, the focus is on using statistics specifically in bibliometrics, a context that does not lend itself well to many of the standard approaches normally taught in introductory statistics courses. We will cover topics such as statistical distributions in bibliometrics, calculation of normalised metrics and how these differ, quantifying uncertainty around bibliometric indicators, and key issues to consider when inferring difference. We will also consider options for visualising uncertainty in bibliometric data. The aim is to bring all of these concepts together to help promote responsible metrics.

Please note that this course assumes that attendees are familiar with a range of bibliometric indicators commonly used in research evaluation. Ideally, attendees will have worked with the more advanced, normalised indicators found in tools such as Dimensions, InCites, or SciVal. However, subscription access to these tools is not a pre-requisite, and we will not use any of them during the course.

Course presenter: Dr Abigail McBirnie is a UK-based information specialist. As a bibliometrician and analyst, she has worked in higher education and research. A current LIS-Bibliometrics committee member, she is interested in the use of statistics in bibliometrics and the implications of this for responsible metrics.

Program

10:00 – 10:10 Welcome / Marianne Gauffriau
10:10 – 11:00 Statistical starting points; bibliometric distributions; first steps with R / Abigail McBirnie
11:00 – 11:15 Break
11:15 – 12:15 Continuing with R; overview of bibliometric indicator calculation methods; preparing bibliometric data for statistical analysis / Abigail McBirnie
12:15 – 13:00 Lunch
13:00 – 14:00 Quantifying uncertainty for bibliometric indicators; calculating confidence intervals in R / Abigail McBirnie
14:00 – 14:10 Break
14:10 – 15:00 Visualising uncertainty in bibliometric data; issues around inferring difference in bibliometrics / Abigail McBirnie
15:00 – 15:15 Break
15:15 – 15:45 Course round up: using statistics to promote responsible metrics / Abigail McBirnie
15:45 – 16:00 Evaluation / Marianne Gauffriau

There are computers available for the participants to use during the workshop. If you wish to use our own laptop, please make sure that R and RStudio Desktop (https://www.rstudio.com/products/rstudio/download/#download), Notepad++ (https://notepad-plus-plus.org/download/v7.6.html) and Excel are installed on your computer before the workshop.

See blog about the course in UK: https://thebibliomagician.wordpress.com/2018/06/28/course-summary-statistics-for-responsible-bibliometrics/