SIB2001-2425 : Research Skills 2 - Assessment Task One Group Data Analysis | University of Huddersfield

Assessment Information

For this assignment, you will be divided into groups of five to six students each and work together on the analysis of a complex dataset, using R statistical programming language (note: you must use R for your analysis – not Excel, for example). The marks for this assignment are for your submitted R code documenting the fully reproducible analysis of your team’s data.

These marks are made up of the following components: 

Group data analysis itself makes up 90% of the main component mark

Five low-stakes homework exercises that you will be asked to do during the term. The marks from the best four of your submissions will make up 10% of the main component mark. There are no possibilities of extensions or ECs for these exercises.
Feedback will be provided to each group via annotations on the submitted R code.

Assessment Criteria

R code formatting - 10%
The data analysis must be presented as a single file in an R Notebook or Quarto format, with clearly marked sections of R code and explanatory text where necessary. Calls for required packages and custom functions must be included.

Functional R code - 20%
The R code in the file must enable replication of group’s analysis. The tutors must be able to open the file and execute the R code, including reproduction of all the graphs, tables and statistical analyses.

Reuse of someone else’s code must be clearly acknowledged and linked to the original source.
Failure to provide R code of the analysis will result with a mark of zero for this entire component.    

Data analysis - 70%
The data analysis must include and demonstrate the application and use of at least the following elements and approaches:

Structure elements: data importing, cleaning up, reformatting etc.

Visualisations: the analysis must include several visualisations to describe the data and/or present some results of the analyses
Statistical analyses: descriptive statistics of the data as well as appropriate tests for significance should be included

The presented analysis must be biologically sound, i.e. you should use your knowledge and skills from other modules and/or literature to inform the analyses. Technically correct R code analysing a biologically nonsensical question will result in reduced marks for this component. The analysis should attempt to frame and answer a reasonably plausible biological problem or phenomenon.