Lecturer(s): Dr Panayiota Constantinou and Dr Simon Spencer
Prerequisite(s): Either ST115 Introduction to Probability or ST111/ST112 Probability A & B (taken concurrently).
Leads to: ST221 Linear Statistical Modelling
Commitment: This module runs in Term 2 and 3 and is weighted at 12 CATS.
Term 2: 3 lectures each in weeks 6-10 and 1 lab each in weeks 7-10,
Term 3: 3 lectures each in weeks 1-2, 4 lectures each in weeks 3-4 and 1 lab each in weeks 1-4.
- Introduction to R
- Exploratory data analysis: methods of visualisation and summary statistics
- Sampling from standard discrete and continuous distributions (Bernoulli, Geometric, Poisson, Gaussian, Gamma)
- Generic methods for sampling from univariate distributions
- The use of R to illustrate probabilistic notions such as conditioning, convolutions and the law of large numbers
- Examples of modelling real data (but without formal statistical inference) and the use of visualisations to assess fit
Aims: To introduce students to the R software package, making use of it for exploratory data analysis and simple simulations. This should deepen and reinforce the understanding of probabilistic notions being learnt in ST115 and ST111/2.
- A familiarity with the R software package, making use of it for exploratory data analysis.
- An understanding of elementary simulation techniques applied to probability.
- The ability to propose appropriate probabilistic models for simple data sets.
Assessment: 30% assessed work and 70% open-book examination.
Term 2: Thursday of Week 10: Lab report 1 (15%)
Term 3: Thursday of Week 3: Lab report 2 (15%)
Feedback: Feedback to students will be given within 20 working days after the submission deadline.
Resources for Current ST104 Students (restricted access)