- This event has passed.
ONLINE COURSE – Statistics For Biodiversity And Conservation (SFBC01) This course will be delivered live
30th May 2022 - 3rd June 2022
£425.00
Monday, May 30th 2022
Course Format
This is a ‘LIVE COURSE’ – the instructor will be delivering lectures and coaching attendees through the accompanying computer practical’s via video link, a good internet connection is essential.
Course Program
TIME ZONE – GMT+1 – however all sessions will be recorded and made available allowing attendees from different time zones to follow.
Please email oliverhooker@prstatistics.com for full details or to discuss how we can accommodate you.
About This Course
The way statistics are used in biology, and especially ecology, is changing, with a shift from statistical tests of significance to fitting statistical models to data to explain causation and draw inferences to wider situations. And a new enlightened Bayesian world of statistical inference is also emerging.
An understanding of statistical modelling is no longer a luxury, and it is an expectation that postgraduates and post-doctoral researchers, as well as ecological practitioners possess an understanding of this approach. This change has been unleashed by an explosion in computing power and the advent of powerful and flexible software, such as R, that permits users to wrangle, analyse and visualise their data in novel ways.
This course is aimed at introducing researchers to analysing ecological and environmental data with GLMs using R. Study design will be discussed, as well as data analysis and statistical interpretation. Sessions will be a blend of interactive demonstrations and lectures, where learners will have the opportunity to ask questions throughout. Prior to the course, you will receive R script and datasets and a list of R packages to install.
By the end of the course, participants should be able to:
- Apply data exploration techniques and avoid the common pitfalls in tackling a data analysis
- Recognise common problems associated with analysis of ecological data and how to address them
- Understand and apply alternative approaches to model selection
- Apply statistical modelling methods to ecological data using GLMs
- Recognise the distinction between frequentist and Bayesian approaches to model fitting
Intended Audiences
Post graduate or post-doctoral level researchers who wish to learn how to manipulate and analyse ecological data using R
Applied researchers and analysts in the environmental/ecological sector with a role in handling and analysing data
Venue
Course Details
Availability – 30 places
Duration – 5 days
Contact hours – Approx. 35 hours
ECT’s – Equal to 3 ECT’s
Language – English
Teaching Format
Ideally, participants will be able to use a computer screen that is sufficiently large to enable them to view my shared RStudio and their own RStudio simultaneously.
Assumed quantitative knowledge
Assumed computer background
Equipment and software requirements
A full list of required packages will be made available to participants prior to the course.
Ideally, participants will be able to use a computer screen that is sufficiently large to enable them to view my shared RStudio and their own RStudio simultaneously
Cancellations are accepted up to 28 days before the course start date subject to a 25% cancellation fee. Cancellations later than this may be considered, contact oliverhooker@prstatistics.com. Failure to attend will result in the full cost of the course being charged. In the unfortunate event that a course is cancelled due to unforeseen circumstances a full refund of the course fees will be credited.
If you are unsure about course suitability, please get in touch by email to find out more oliverhooker@prstatistics.com
COURSE PROGRAMME
Monday 30th
Classes from 09:00 to 17:00
Introduction to R and RStudio
- Getting started with R and RStudio
- Basic points
- Navigating RStudio
- Basic settings in RStudio
- Basic principles in R
- Setting the working directory
- Importing data
- Functions and packages in R
Data exploration
- Six-step data exploration protocol
- Outliers
- Normality and homogeneity of the dependent variable
- Lots of zeros in the response variable
- Multicollinearity among covariates
- Relationships among dependent and independent variables
- Independence of response variable
- Results of data exploration
Testing differences between two groups
- European hedgehogs
- Outliers
- Normality and homogeneity of the dependent variable
- Zeros in the response variable
- Multicollinearity among covariates
- Relationships among dependent and independent variables
- Independence of response variable
- Results of data exploration
- Comparing two groups of normal unpaired data: unpaired t-test
- Comparing two groups of normal paired data: the paired t-test
- Comparing two groups of non-normal unpaired data: the Mann-Whitney test
- Comparing two groups of non-normal paired data: the Wilcoxon test
- Presenting results
Testing association between two continuous variables: correlation
- Barn owls
- Outliers
- Normality of the variables
- An excess of zeros
- Multicollinearity among covariates
- Relationships between variables
- Independence of variables
- Results of data exploration
- Testing association between two continuous normal variables: Pearson’s correlation
- Testing association between two continuous non-normal variables: Spearmann’s rank correlation
- Testing association between two continuous non-normal variables with small sample size and ties: Kendall’s Tau correlation
- Presenting the results
Tuesday 31st
Classes from 09:00 to 17:00
Modelling two continuous variables with linear regression
- Northern pike length-fecundity relationship
- Outliers
- Normality and homogeneity of the variables
- An excess of zeros
- Multicollinearity among covariates
- Relationship between variables
- Independence of variables
- Results of data exploration
- Bivariate linear regression
- Model validation
- Homogeneity of variance of the residuals
- Normality of residuals
- Plot of the linear regression model
- Absence of influential observations
- Conclusions from model validation
- Data transformation
- Refit linear regression with transformed data
- Model re-validation
- Homogeneity of variance of the residuals
- Normality of residuals
- Plot of the linear regression model
- Absence of influential observations
- Model presentation and interpretation
Gaussian General Linear Model (GLM)
- Diet of weatherfish in different seasons
- Data exploration
- Outliers
- Normality and homogeneity of the variables
- Lots of zeros in the response variable
- Multicollinearity among covariates
- Relationships among dependent and independent variables
- Independence of response variable
- Model fitting
- Model validation
- Homogeneity of residual variance
- Model misfit
- Normality of residuals
- Absence of influential observations
- Model presentation
Wednesday 1st
Classes from 09:00 to 17:00
Modelling two continuous variables with linear regression
- Northern pike length-fecundity relationship
- Outliers
- Normality and homogeneity of the variables
- An excess of zeros
- Multicollinearity among covariates
- Relationship between variables
- Independence of variables
- Results of data exploration
- Bivariate linear regression
- Model validation
- Homogeneity of variance of the residuals
- Normality of residuals
- Plot of the linear regression model
- Absence of influential observations
- Conclusions from model validation
- Data transformation
- Refit linear regression with transformed data
- Model re-validation
- Homogeneity of variance of the residuals
- Normality of residuals
- Plot of the linear regression model
- Absence of influential observations
- Model presentation and interpretation
Gaussian General Linear Model (GLM)
- Diet of weatherfish in different seasons
- Data exploration
- Outliers
- Normality and homogeneity of the variables
- Lots of zeros in the response variable
- Multicollinearity among covariates
- Relationships among dependent and independent variables
- Independence of response variable
- Model fitting
- Model validation
- Homogeneity of residual variance
- Model misfit
- Normality of residuals
- Absence of influential observations
- Model presentation
Thursday 2nd
Classes from 09:00 to 17:00
Poisson Generalised Linear Model (GLM)
- Abundance of freshwater mussels
- Data exploration
- Outliers
- Lots of zeros in the response variable
- Multicollinearity among covariates
- Relationships among dependent and independent variables
- Independence of response variable
- Model fitting
- Model validation
- Overdispersion
- Model misfit
- Simulating from the model
- Model presentation
Negative binomial Generalised Linear Model (GLM)
- Species diversity of chironomids
- Data exploration
- Outliers
- Lots of zeros in the response variable
- Multicollinearity among covariates
- Relationships among dependent and independent variables
- Model fitting
- Model validation
- Overdispersion
- Model presentation
Friday 3rd
Classes from 09:00 to 17:00
Gaussian Generalised Linear Mixed Model (GLMM)
- Body condition of European tree frogs
- Data exploration
- Outliers
- Normality and homogeneity of the dependent variable
- Lots of zeros in the response variable
- Multicollinearity among covariates
- Relationships among dependent and independent variables
- Independence of response variable
- Results of data exploration
- Model fitting
- Model validation
- Homogeneity of residual variance
- Model misfit
- Normality of residuals
- Absence of influential observations
- Refit model
- Model validation
- Homogeneity of residual variance
- Model misfit
- Normality of residuals
- Absence of influential observations
- Refit model with random term
- Model validation
- Homogeneity of residual variance
- Model misfit
- Normality of residuals
- Model presentation
Bayesian inference
- Introduction to Bayesian inference
- European bitterling territoriality
- Data exploration
- Outliers
- Normality and homogeneity of the dependent variable
- Lots of zeros in the response variable
- Independence of response variable
- Model fitting
- INLA
- Posterior (marginal) distributions
- Comparison with frequentist Gaussian GLM
- Model validation
- Homogeneity of residual variance
- Model misfit
- Normality of residuals
- Model presentation
Course Instructor
Dr. Carl Smith
Senior Lecturer, Psychology Department, Nottingham Trent University
Teaches:
- Statistics for biodiversity and conservation (SFBC01)
- Bayesian GLMs for Ecologists (BGFE01)
Mark Andrews is a Senior Lecturer in the Psychology Department at Nottingham Trent University in Nottingham, England. Mark is a graduate of the National University of Ireland and obtained an MA and PhD from Cornell University in New York. Mark’s research focuses on developing and testing Bayesian models of human cognition, with particular focus on human language processing and human memory. Mark’s research also focuses on general Bayesian data analysis, particularly as applied to data from the social and behavioural sciences. Since 2015, he and his colleague Professor Thom Baguley have been funded by the UK’s ESRC funding body to provide intensive workshops on Bayesian data analysis for researchers in the social sciences.