Details of Award
NERC Reference : NE/M006360/1
Introduction to Multivariate Ecological Statistics: exploring tools for ecologists
Training Grant Award
- Lead Supervisor:
- Dr JMR Hughes, University of Oxford, Continuing Education
- Grant held at:
- University of Oxford, Continuing Education
- Science Area:
- Atmospheric
- Earth
- Freshwater
- Marine
- Terrestrial
- Overall Classification:
- Atmospheric
- ENRIs:
- Biodiversity
- Environmental Risks and Hazards
- Global Change
- Natural Resource Management
- Pollution and Waste
- Science Topics:
- Statistics & Appl. Probability
- Abstract:
- The proposed 4 day postgraduate and professional skills training course in Multivariate Statistics (theory and practice) provides an integrated programme of statistical approaches for research in ecology, field biology, environmental science and management. Students will be introduced to skills in experimental design, sampling strategies and data analysis that are essential to the setting up and evaluation of field experiments, landscape scale studies, research into ecosystem services and processes, and assessing the impacts of environmental change or management on biodiversity. Tuition will be via a series of short presentations, each followed by several practical sessions in which students will analyse real data sets from research in a diversity of biomes (e.g. terrestrial, aquatic, experimental, monitoring). Software used during the course is predominantly open source R although students will have the opportunity to explore other tools for specific analyses as appropriate e.g. biodiversity indices, food webs. Students will be asked to bring their own data sets and there will be daily opportunities to relate student data to the topic being taught. Uniqueness The course introduces students to multivariate statistics and their applications. The core team of three tutors will provide a supportive but rigorous forum in which students can improve their analytical skills as well as address specific questions related to their own research. As well as providing teaching excellence in data analysis, the tutors will use some well-known data sets in the practical sessions e.g. long term monitoring data sets from Wytham Woods, Oxfordshire. The course will revise inferential statistics while learning the statistical programming language R, the use of RStudio, how to import, visualise and analyse data. The core emphasis is on statistical applications rather than the use of R, but Day 1 provides the opportunity for students to become familiar with the software. The remaining three days summarise the role of experimental design and sampling, from small scale factorial to landscape scale correlative studies and introduce more complex analytical approaches used in the exploration, analysis and interpretation of a wide range of experimental designs, data types and spatial/temporal scales. As well as focusing on multivariate statistical approaches, the course introduces more specific analytical methods used in the interpretation of complex community ecology data. Impact The course fills a widening gap in skills provision in ecological statistics and data analysis. The ability to analyse and interpret data underpins all ecological research and decision making: core skills valued by academics, NGOs, consultants and industrial employers. This proposal is an adaptation of the programme that was successfully run in February 2014. Both student and tutor feedback werre extremely positive, and the programme had a high application rate (52 applications for 15 places) and an extensive waiting list which demonstrated the need for further programming in this area. The vast majority of the students agreed with the statements that the course: was interesting and enjoyable; was at an appropriate level of difficulty; provided them with concepts/techniques that will be useful in the future; had an excellent standard of teaching with approachable and effective tutors. They appreciated being able to take their own data to the programme, the small class sizes and excellent tuition. In the light of student feedback, we have adapted the 2015 proposed course to provide more tuition on the use of mixed effect models, power analysis, more detailed instruction on R using the more user-friendly RStudio interface, and more on the use of GLMs as well as providing additional tutor support and more integrated opportunities for students to discuss their own data throughout the course.
- NERC Reference:
- NE/M006360/1
- Grant Stage:
- Completed
- Scheme:
- Doctoral Training
- Grant Status:
- Closed
- Programme:
- Advanced Training
This training grant award has a total value of £25,342
FDAB - Financial Details (Award breakdown by headings)
| Total - Other Costs |
|---|
| £25,342 |
If you need further help, please read the user guide.