MEDICAL EVALUATIONS WITH THE R SOFTWARE PACKAGE
In-person events in Wiesbaden or online seminar on 2 days: €1,090 per person (net)
For all professionals in clinical and medical research who want to become competent in the use of statistics using R and appropriate additional packages or who want to improve their knowledge.
Open training dates: September 19-20, 2024
LEARNING OBJECTIVES AND AGENDA
Goals:
R, RStudio® and relevant add-on packages, resources
Competent use of R® in the medical field
Different techniques for data preparation depending on the research question
Learn the basics of medical statistics and implement them in R. Interpretation of results
IN-HOUSE SEMINAR
Seminars held at the customer's location
€1,390.00
per day up to 4 participants plus statutory VAT
All content of the in-house seminars is individually tailored and taught to specific target groups .
Intensive follow-up support enables participants to implement their knowledge in the shortest possible time.
Recommended seminar duration: 2 days
Rental fees for training notebook (on request): 60,- Euro (per day, per training computer)
WORKSHOP
You tell us your topics!
Price on request
plus statutory VAT and travel expenses if applicable
All workshop content is individually tailored and taught to specific target groups .
We are happy to conduct the workshop at your location, in Wiesbaden or online.
Rental fees for training notebook (on request): 60,- Euro (per day, per training computer)
Day 1
Basics of R and RStudio®
Data import into R: text files, databases, other sources
Visualizations and descriptive analysis of the data
Data preparation in R
Hypothesis testing in R: Parametric and nonparametric tests
Contingency analyses and risk parameters, especially risk ratio and odds ratio
Day 2
Power analysis in R
Overview of Multivariate Statistics in R
In-depth: Notes on variance analysis
Medical Statistics/Survival Analysis in R
Correlation analysis
Logistic regression
Mortality tables
Kaplan-Meier estimators and charts
Cox regression
Optional: Meta-analyses in R
Course Content
The course is aimed at anyone interested in medical statistics. It provides techniques for analyzing medical data, estimation methods, and data visualization. All analyses are carried out together in R/RStudio through numerous exercises. The seminar offers plenty of opportunities for hands-on practice in R alongside the instructor.
The focus of this seminar is the practical implementation of common statistical methods in medical statistics using the R software environment. We also discuss the use of R in relation to regulatory requirements, particularly those of the FDA.
We begin with the basics of R and the RStudio IDE. The help system and the R ecosystem (R project page, CRAN, Bioconductor, etc.) are introduced, along with special task views for medical statistics. Relevant literature is also presented.
Since statistics almost always require data, the next section covers importing datasets into R. In addition to text files, importing from database tables is explained. Exporting datasets and results in structured formats is also demonstrated. Other common data sources (other statistical software, MS Excel, etc.) are also covered.
Once the data has been imported, visualizations and univariate analyses are necessary to better understand it: Are variable values plausible? Are there outliers? Are missing values present, and if so, how many? What is the distribution of the data? These are typical questions we will explore in this section with R. Alongside the basic plot() function, we will also use the ggplot2 package for visualization.
After diagnosing the data properties, the next step is data preparation: Skewed distributions can be transformed (depending on the intended statistical methods). Missing values can be imputed, including through multiple imputation methods. Implausible values can be deleted or replaced with suitable alternatives. Categorical variables, if used in variance analysis (ANOVA or GLM), can be transformed into dummy variables, and so on.
Once the data is prepared, hypothesis testing can be carried out (hypotheses, of course, should already be documented at the start of the analysis in a study protocol). These hypotheses are then tested using parametric methods such as the classical t-test, F-tests, etc., as well as nonparametric equivalents such as the Mann-Whitney U test. We discuss assumptions, how to prepare the data in R for testing, conduct the tests (e.g., using the t.test() function), and interpret the results.
Contingency analysis, particularly the analysis of two-dimensional cross tables, plays an important role in medicine. For example, the 2x2 table (rows: drug vs. placebo or two drugs compared; columns: outcome [treatment success vs. no success]) forms the basis for calculating key medical risk parameters: risk ratio and odds ratio. In addition to calculating these parameters (including log-transformed values), confidence intervals and p-values are also computed.
Day 2 begins with power analyses, which are essential in medical statistics for sample size estimation. Power analysis helps determine the required sample size for an experiment in relation to the alternative hypothesis, which is often (though not always) the focus of interest. We first learn the logic behind these calculations before applying them in R.
Multivariate statistics is now a very broad field with many methods and specialized variants. An overview is therefore necessary to classify the procedures and, if needed, identify suitable methods. What is available in the standard R installation? Which add-on packages are useful? What role do measurement levels of dependent and independent variables, error distributions, and link functions play?
In medical statistics, some methods consider both the time until an event occurs and the fact that the event may not occur before the study ends. These are collectively known as survival analysis. This includes life tables, Kaplan-Meier estimators and plots, as well as Cox regression, which allows the control of time-independent covariates. The hazard ratio is used here. Implementation is done in R, beginning with the packages available in the standard installation.
Additional course content and focus areas can also be freely selected upon request! You have complete flexibility regarding the material if you book an in-house seminar—then we tailor all content to your specific needs.