After successful completion of the course, students are able to  (1) design experiments and analyze the resulting data; (2) carry out supervised and unsupervised statistical analysis of categorical data (survival function estimation, Cox proportional hazard regression) using the R programming language.  

COURSE OUTLINE

      I. Design of Experiments

• Components of an experiment, terms and concepts
• Completely randomized designs: Models, parameter estimation, contrasts, checking assumptions
• Multiple comparisons
• Power and sample size
• Fixed, random and mixed models, nesting
• Variance reduction designs: complete block design, latin square

1. Categorical Data Analysis
• Categorical data: nominal vs ordinal
• Two-way contingency tables
• Three-way contingency tables
• Logistic regression
2. Survival Analysis
• Time to event data and censoring
• The survival and the hazard functions
• Survival function estimation
• Cox proportional-hazards regression model

The course wants to be taught using lecture slides in conjunction with derivations on board. Course information and materials, including notes and details about course assignments and exams will be posted in TUWEL.

Three reference books are used:

• DOE: Design and Analysis of Experiments, 10th Edition by Montgomery (available at TU Library)

• Categorical Data: An Introduction to Categorical Data Analysis, Second Edition by Agresti (available online at the TU Library)

• Survival Analysis: Applied Survival Analysis, Second Edition by Hosmer, Lemeshow and May (available online at the TU Library)

The statistical software we want to use is R. It can be downloaded from the R home page . RStudio offers a GUI R platform.

Continuous assessment via oral examination and regular homework tasks throughout the semester.

Probability and statistics at the level of Applied Mathematical Statistics; Calculus and Linear Algebra.