Workshops & Seminars

The following courses are designed for researchers to establish a firm understanding of the appropriate statistical methods in order to glean insights from their own data in their respective field of work. This provides a sound foundation for good statistical practice and evidence generation through research.

Basic Principles of Biostatistics

This course establishes a fundamental understanding of statistics for young researchers in life sciences.

  • Descriptive statistics & graphics
  • Principles of statistical testing
  • Statistical tests & interpretation
  • Evaluation of fold change data
  • Correlation and regression
  • Study design and common pitfalls
See Details

Good Statistical Practice

Helping researchers understand common pitfalls and misconceptions in conducting statistical analyses and communicating results.

  • Identifying uninformative or misleading plots
  • Hierarchical data structures
  • P-values and their limitations
  • Statistical significance vs. biological relevance
  • Multiple testing adjustments
See Details

Advanced Topics in Biostatistics

This course addresses advanced biostatistical questions including some theoretical background and real-life applications.

  • Analysis of variance & group tests
  • Regression models
  • Supervised learning (classification & prediction)
  • Unsupervised learning (clustering, PCA, …)
See Details

Intro to Statistical Programming with R

A gentle introduction to the use of R and Rstudio for data analysis.

  • Objects, functions & help
  • Data import
  • Descriptive statistics
  • First graphics for data
  • Variable transformations
  • Writing own functions
  • First statistical analyses
See Details

Identifying Subgroups in Omics Data

An overview of unsupervised methods for identification of subgroups in Omics data using Bioconductor and the R programming language.

  • Unsupervised learning
  • Clustering techniques
  • Dimension reduction
  • Visualization & interpretation
  • Validity & stability
See Details

Icons licensed under CC BY 4.0.  © Laura Reen

Addressing exactly what your participants need…

The range of covered topics, content and workshop duration can be modified to focus exactly on your participants’ particular needs. Get in touch and let me know what topics are most relevant to your group.

Get in touch

What Participants say

Super satisfied by the course! Topics that I thought would be very hard were very well explained.

Enthusiastic speaker! It was always fun to listen and I learned a lot.

Thanks to the energy of the presenter, the most interesting statistics course so far!

Great course, perfect lecturer, easy to understand. Now I know what the p-value is.

Frequently Asked Questions

Course sizes differ depending on format and course content.

For statistics courses with a classroom setup, such as Basic Principles of Biostatistics and Good Scientific practice, anywhere between 10 to 50 participants is recommended. This interval has proven helpful for encouraging participants to interact with each other and to engage in discussions.

For seminars involving hands-on programming sessions, (e.g. Intro to R, Analysis of Omics data, and Subgroup Identification), group sizes of 8 to 20 are preferable. This ensures that individual programming questions can be addressed and resolved quickly.

The statistics courses, such as Basic Principles of Biostatistics and Good statistical practice, are intended for young life-science researchers and do not require any particular statistical knowledge. High school level mathematics suffices, as these seminars intend to establish an understanding of basic statistical aspects that researchers are confronted with during their own work and in scientific publications.

Similarly, the Introduction to R workshop is intended for absolute beginners and does not require any prior knowledge of programming. Participants should bring their own laptop for the practical session.

The seminars involving programming sessions with Bioconductor (e.g. Analysis of Omics data, and Subgroup Identification) require a basic understanding of statistical concepts and some prior experience with R programming. These courses are not useful for participants with no knowledge of R. Participants should bring their own laptop for the practical session.

In all my course types I strive to deliver engaging and rewarding learning experiences. I encourage students to  discuss and interact by using polling software, which has been enthusiastically embraced by previous participants. I also find it important to maintain a welcoming atmosphere and to plan enough time for interaction and questions.

Seeing a full seminar room, I am very aware that each participant has taken time out of  his/her packed schedule to attend this course. Therefore, it is my goal to turn the seminar into a fruitful experience by addressing their particular needs and making sure that they obtain the proper statistical tools needed to become successful researchers.

Rates vary depending on course content, format and length. Get in touch to discuss your specific case and I’ll happily provide an estimate.

Yes, all courses can be conducted in either German or in English, depending on the participants’ preferences.

I can be somewhat flexible and plan around your own calendar openings. Let’s have a short talk about what dates you have in mind and I’ll see what I can do.

Seminars generally take place at your institute/facilities, both to ease the logistics and to save on costs – though I am open to other options you may find more suitable.

I am based near Heidelberg and can conduct classes anywhere in Germany and the European Union overall. Locations such as Frankfurt, Darmstadt, Mainz, Wiesbaden, and Mannheim can easily be reached within an hour, thus eliminating my need for a hotel stay in these and similar locations.

Any broader traveling can be considered but will require adequate prior notice and assistance with logistics on your end.

A regular conference room setup is perfectly sufficient: a projector, good acoustics, WiFi.

For seminars involving hands-on programming sessions (e.g. Intro to R, Analysis of Omics data, and Subgroup Identification) sufficient electricity sockets are required.

Let's Discuss Your Next Seminar or Workshop

    Which courses are you interested in?
    Basic Principles of BiostatisticsIntro to Statistical Programming with RAnalysis of Omics Data using Bioconductor and RIdentifying Subgroups in Omics DataGood Statistical PracticeSomething else

    Small quiz to show you're not a robot:

    Close Menu

    Basic Principles of Biostatistics​

    This course establishes a fundamental understanding of statistics for young researchers in life sciences. It clarifies basic concepts of statistics that are commonly encountered in scientific publications. The goal is to give participants a firm understanding of basic statistical concepts as well as to sensitize them to common errors and pitfalls.

    Prerequisites: High school level mathematics, no particular statistical knowledge required.

    Content:

    • Descriptive statistics: plots, measures of location and variation
    • Fundamentals: Quantiles, the normal distribution, binomial distribution
    • Confidence intervals
    • How to plot data
    • The principle of statistical testing
    • Statistical tests for quantitative data: t-test
    • Statistical tests for quantitative data, more than 2 groups: ANOVA
    • Statistical tests for qualitative data: chisquare-test
    • Interpretation of p-values
    • Evaluation of fold change data
    • Correlation and regression
    • Study design

    Duration:  2.5 - 3 days

    Class Size: 10 - 24 participants

    Expected Outcome:
    After the course the participants will have a solid understanding of basic statistical concepts used in scientific practice. They will know how to interpret and evaluate published results with a critical eye for common pitfalls and limitations.

    Get in Touch to Book

    This class addresses common misconceptions and issues that many researchers face in their daily work. We discuss real-life applications of these hurdles in all phases: from planning an experiment, gathering data, statistical analysis and communication of results. The main goal is to sensitize researchers to problems such as misinterpretation, bias, lack of reproducibility while showing constructive ways of circumventing these common pitfalls which lead to better scientific practice and more reliable results.

    Prerequisites: No particular statistical knowledge required.

    Content:

    Duration: 1 day

    Class Size: 10 - 24 participants

    Expected Outcome: After the course the participants are equipped with tools to better plan and execute their own scientific experiments as well as to be aware and critical of published work that they encounter in their daily research.

    Get in Touch to Book

    Advanced Topics in Biostatistics

    This seminar addresses advanced biostatistical questions that researchers may face in various settings. We discuss the theoretical background of statistical methods and look into real-life applications thereof. In particular, we take a close look at parametric and non-parametric methods for group comparisons, as well as regression methods that incorporate covariates into the model. We discuss supervised learning for classification and prediction, and unsupervised approaches for the identification of subgroups. Many examples are discussed in the context of biological experiments.

    Prerequisites: Introductory workshop “Basic Principles of Biostatistics” or basic statistical knowledge from another previous introductory class.

    Content:

    • Analysis of variance and group tests
      • Variance decomposition & anova testing procedure
      • Simple and multifactorial analysis of variance
      • Interaction effects: types and interpretations
      • Post-hoc tests
      • Non-parametric alternatives to t-test and anova
    • Regression models and supervised methods
      • Correlation analyses
      • Linear regression (simple & multiple regression) for continuous endpoints
      • Logistic regression for binary endpoints
    • Supervised learning for classification and prediction
      • Intro to common methods (linear models, regularisation, trees, ...)
      • Dimensionality and signal-to-noise ratio
      • Overfitting & Model Validation
    • Screening methods for differential expression
      • Search for differentially expressed biomarkers between groups
      • Multiple testing procedures and p-value adjustment
    • Unsupervised learning for identification of subgroups by means of clustering• Principal components analysis
      • Hierarchical clustering & K-means procedures
      • Constructing heat maps for visualisation of results
      • Cluster validation

    Duration: 4 sessions of each 4 hours ( = 2 days)

    Class Size: 8 - 24 participants

    Expected Outcome: After the course, the participants are equipped with tools to better plan and execute their own scientific experiments and data analysis steps. In particular, participants will be familiar with common approaches for group testing, regression modelling, differential expression analysis, interpretation and visualisation of results. They will also have a basic understanding of common clustering approaches and how to apply these to their own data to identify possible subgroups.

    Get in Touch to Book

    Intro to Statistical Programming with R​

    This course offers an intuitive and engaging approach to the statistical programming language R. It is meant for users with no prior programming experience and allows them to get acquainted with the basics of this software in order to take their first steps towards analysing their own data. The workshop includes a 1-day exercise session where participants can put the newly learned concepts to practical use.

    Prerequisites: High school level mathematics, no particular statistical knowledge required. Participants should bring their own laptop for the practical session.

    Content:
    - software installation and GUI (R, Rstudio)
    - objects (assignments, environment, nomenclature)
    - functions & help
    - data import (excel, csv, txt, …)
    - scripts and workspaces (.R, .Rdata)
    - common object types (vectors, matrices, data frames, lists, …)
    - descriptive statistics (mean, SD, …)
    - first graphics for data (hist, bar plot, box plot, scatter plot, heat map …)
    - variables transformations
    - if/else, loops, apply
    - writing own functions
    - first statistical analyses (correlation, linear model, clustering, group comparisons, …)
    - Packages (CRAN, BioC)

    Duration: 3 days (including 1 day hands-on exercise session)

    Class Size: 8 - 24 participants

    Expected Outcome:
    After the course the participants will have and understanding of the basic tools for using R and finding help. They will have had initial experience with the software during the exercise session and be familiar with the general concepts of this programming language. This course lays the groundwork for progressing towards more sophisticated statistical analysis of any type of data.

    Get in Touch to Book

    Identifying Subgroups in Omics Data​

    This course gives an introduction to unsupervised methods for identification of subgroups in Omics data using Bioconductor and the R programming language. The main focus is on the statistical challenges of clustering algorithms and interpretation of results.

    This course does not address bioinformatics issues such as preprocessing, annotation, alignment, imputation, alternative splicing, etc.

    Prerequisites: Basic understanding of statistical concepts and some prior experience with R. Please note, that this course is not useful for participants with no knowledge of R programming.
    Participants should bring their own laptop for the practical session.

    Contents:

    Duration: 1 day (consists of half-day lecture and a half-day exercise session)

    Class Size: 8 - 24 participants

    Expected Outcome:
    Participant will be familiar approaches for unsupervised learning applied to omics data. They will have a basic understanding of common clustering approaches and how to apply these to their own data to identify possible subgroups.

    Get in Touch to Book