Statistics Training

Two-day statisticsintensivecourseI 2017

For the latest information on statistics training courses: see
www.uni-kassel.de/fb11agrar/de/fachgebiete-einrichtungen/umweltchemie/statistikschulungen.html

Statistical principles, experimental designs and introduction to R for soil scientists.

In the media and journals of different disciplines, erroneous research due to insufficient knowledge of statistics is pointed out again and again. For example, the Süddeutsche Zeitung of 05.02.2016 writes: "You might as well roll the dice - Biomedical studies deliver questionable results". Ainsworth (2007, Nature 448, 849) formulates even more clearly: "The abysmal standard of statistical analysis in much of genetic epidemiology is little short of scandalous". It is possible that similar problems exist to some extent in soil science.

Typical problem areas in soil science could be, for example, (i) hypothesis-free research, (ii) inappropriate experimental designs, (iii) a lack of understanding of pseudoreplication, (iv) inappropriate handling of outliers, (v) lack of verification of conditions for hypothesis tests, and (vi) inadequate description of statistical analyses in publications so that studies are not reproducible ("When necessary data were transformed" is, for example, a text block rather than helpful information).

The intensive course will cover the statistical basics for soil scientists including an introduction to R, so that the above problem areas will be less common in soil science in the future.

Date: 09 March 2017 10:00 am to 10 March 2017 6:30 pm.

Location: University of Kassel, 37213 Witzenhausen, Nordbahnhofstr. 1a.

Cost: on request.

Number of participants: The number of participants is limited to 25.

Laptops: Please bring your own laptops with R and RStudio. If necessary, laptops can be borrowed in some cases by prior arrangement.

Materials: Course script, exercises and sample solutions will be provided.

Recommended reading: e.g. Crawley (2012). The R Book. 2nd Ed., Wiley.

Speaker: Prof. Dr. Bernard Ludwig

Schedule of the intensive course:

Thu., 09.03.2017

10:00 - 12:00 Welcome, introduction to descriptive statistics and important distributions.

12:00 - 13:00 Lunch break

13:00 - 14:00 Introduction to experimental designs, replication, pseudoreplication & hypothesis testing

14:00 - 16:30 Tests for normal distribution, variance homogeneity, parametric (various t-tests) and non-parametric tests (Wilcoxon rank sum tests), Spearman and Pearson correlations and chi-square tests

16:30 - 17:00 Coffee break

17:00 - 18:30 Introduction to R (data types)

Fri, 10.03.2017

10:00 - 12:00 Introduction to R (vectors & data frames, reading data)

12:00 - 13:00 Lunch break

13:00 - 16:30 Exercises in R with practical examples: parametric and non-parametric tests.

16:30 - 17:00 Coffee break

17:00 - 18:30 Exercises in R with practical examples: Correlations

Please address registrations and queries by 15.02.2017 to: Prof. Bernard Ludwig, University of Kassel, bludwig@uni-kassel.de

Please understand that the intensive course may also be cancelled if there are not enough registrations. In this case or in case of cancellation due to illness of the speaker or other events beyond our control, there are no further claims.