Principles of Biostatistics

Module 1: Introduction to Statistics

• Data collection and sampling methods
• Data classification and presentation
• Measure of central tendency and variability

Module 2: Statistical Inference

• Tests/confidence intervals for one group
• Tests/confidence intervals for two group comparisons
• Test for multiple group comparisons (ANOVA) and post-hoc tests
• Chi-square tests

Module 3: Introduction to Statistical Modelling with R

• Simple linear regression

Module 4: Applied Statistical Modeling with R

• Multiple Linear Regression Model Building (First order model/Model with interaction/Higher order model) for quantitative and qualitative independent variables
• Estimation and Interpretation of the model parameters
• Significance Testing (Full model test /Partial test)
• Model Selections (Stepwise/Backward/Forward Procedure)
• Model Diagnostics (Linearity/Independence/Normality/Homoscedasticity/Outliers)
• Model Transformation (Box Cox Transformation) 
• Model Prediction

At the end of this section, participants will be able to: 

• Apply the basic principles of biostatistics to summarize and draw conclusions from data.

• Formulate testable research questions, evaluate the suitability of different research designs, plan a well-designed experiment or clinical trial, choose an appropriate statistical test and present results in a scientific and comprehensible manner.

• Implement R-software and analyze statistical results for biomedical and veterinary data.

At the end of this section, participants will be able to: 

• Model the multiple linear relationship between a response variable (Y) and all explanatory variables (both categorical and numerical variables) with interaction terms.  Interpret model parameter estimates, construct confidence intervals for regression coefficients, evaluate model fits, visualize correlations between a response variable (Y) and all explanatory variables (X) by graphs (scatter plot, residual plot) to assess model validity.
• Predict the response variable at a certain level of the explanatory variables, once the fit model exists.
• Implement R-software and analyze statistical results for biomedical and veterinary data.

Assignments will be posted on Slack (our communication tool with students). 

Students must attend 70% of the sessions in order to receive the certificate and are encouraged to work on the assignments progressively throughout the course as the relevant material is covered.

Assignments will be posted on Slack (our communication tool with students). 

Students must attend 70% of the sessions in order to receive the certificate and are encouraged to work on the assignments progressively throughout the course as the relevant material is covered.