

site search by freefind 
Statistical data analysis  Christoph Scherber
Last updates: September 2021
 Workshops &
Courses  Introduction to Statistics
and R  R scripts
& Code  YouTube
Channel
April 2021
New statistics/R course "Experimental Design and Statistics with R" at University of Bonn (OEPA21 module in MSc course)
July 2019
Course on mixed effects models will be given at the GfÖ conference in Münster
October 2017
MSclevel statistics course in English language (Umweltstatistik II  Analysis of scientific experiments)
October 2014
PhD course "Linear statistical models with R", Göttingen; Room L318, Grisebachstrasse 6, 6th10th October
June 2014
Workshop with John Fox on structural equation modelling on 6th June 2014. John Fox is an eminent expert in linear statistical models and he´s written books such as An R Companion to Applied Regression.
April 2014
Workshop by Christoph Scherber "Structural equation models in the Soil Sciences", Deutsche Bodenkundliche Gesellschaft
February 2014
Workshop "Structural Equation models" organized by C. Scherber. Guest speakers and lecturers:
James B. Grace (USGS)
W. Daniel Kissling (Denmark & The Netherlands)
Niels J. Blunch (Denmark)
Interpreting statistical models
Using R to Interpret Interaction Effects in Statistical Models published in Software Developer´s Journal in January 2017
Statistical graphics
Using R in combination with Adobe Illustrator CS6 for professional graphics outputpublished in Software Developer´s Magazine 4/2012.
General introductions to R and to statistical data analysis
An Introduction to Statistical Data analysis
Linear models
An introduction to mixed effects models
Basic model formulae for mixedeffects models in R
Nonlinear mixedeffects models in R
An introduction to generalized linear models
Linear models in matrix notation
Logtransformation for data assuming negative values:
log.modulus=function(x,k)sign(x)*log(abs(x)+k)
# k is an arbitrary constant to avoid taking logs of zero
Christoph´s mixed R functions
This is a continuously updated file containing useful snippets of R code.
General collection of useful R functions, Version 20210908
Multinomial models
When fitting multinomial models with the nnet package (multinom() function), it is sometimes desirable to increase the number of weights (especially when there is a large number of response categories). This may happen for example in the analysis of nextgeneration sequencing data. The Anova() function from John Fox´s package "car" can not deal with the MaxNWts argument and hence cannot be used for multinomial models with userspecified maximum number of weights. Below, I provide a function called Anova.multinom2, which allows MaxNWts to be set to any desirded number.
Anova for models with userspecified weights, fitted with the multinom() function
Nonlinear regression
In nonlinear regression situations, one often wishes to use power law functions of the form y=a+b*x^c. The following code allows starting estimates for this function to be estimated automatically.
Selfstarting nonlinear power law function in R
Model selection
StepAICc function for linear, generalized linear and mixed models
selMod function for model selection in mixed models
Contrast matrices
Working with orthogonal contrasts in R
Test for orthogonality of a contrast matrix
Linear mixed models
Extract lme ANOVAs from multiple models
Extract lme summaries from multiple models
Generalized linear mixed models
Time series analysis
A short introduction to timeseries analysis in R
Graphics
Creating publicationquality R Graphics
Ecological diversity
Calculate Shannon´s diversity index
Seed bank data analysis
Analyzing data from a seed bank study using R
Please contact me if you feel there are things that would need to be corrected. R is opensource and new libraries are published every other day, and so it is always a challenging task to keep up with all new developments.
Thanks to the R Core Development Team for making R possible, and also to Mick Crawley for introducing me to R. For downloading and installing R, please visit the R Project website.