MT2508 Statistical Inference
Academic year
2024 to 2025 Semester 2
Curricular information may be subject to change
Further information on which modules are specific to your programme.
Key module information
SCOTCAT credits
15
SCQF level
SCQF level 8
Planned timetable
12.00 noon Mon (even weeks), Tue and Thu
Module Staff
Prof Andy Lynch
Module description
This module provides an introduction to the mathematical models of randomness. These models are used to perform statistical analysis, where the aim is to evaluate our uncertainty on a certain quantity after observing data. Important topics in statistics are described including maximum likelihood estimation, confidence intervals and hypothesis testing, permutation tests, and linear regression. It forms a prerequisite for the statistics modules in the Honours programme. It is recommended that students in the Faculties of Arts and Divinity take an even number of the 15-credit 2000-level MT modules.
Relationship to other modules
Pre-requisites
BEFORE TAKING THIS MODULE YOU MUST PASS MT2504
Anti-requisites
YOU CANNOT TAKE THIS MODULE IF YOU TAKE EC2203
Assessment pattern
2-hour Written Examination = 70%, Coursework = 30%
Re-assessment
2-hour Written Examination = 100%
Learning and teaching methods and delivery
Weekly contact
2.5 hours of lectures (x 10 weeks), 1-hour tutorial (x 5 weeks), 1-hour examples class (x 5 weeks)
Scheduled learning hours
35
Guided independent study hours
115
Intended learning outcomes
- Define estimators and determine whether they are unbiased and/or consistent. Understand and estimate the variability of estimators. Calculate point estimates from data and quantify uncertainty through confidence intervals
- Identify, perform and interpret relevant hypothesis tests using both parametric and nonparametric methods
- Construct likelihoods and apply the method of maximum likelihood to basic examples including the mean and variance of the normal distribution
- Fit, interpret, compare and assess linear models including simple, multiple and polynomial regression with continuous covariates
- Appreciate the importance of testing assumptions and limitations of statistical methods. Appreciate and practice the conveying of statistics to a non-technical audience
- Develop basic skills in computational statistics using R including working with common distributions, reading in data, basic simulation methods, programming computational randomisation tests, fitting linear models and interpreting model output
Additional information from school
For guidance on module choice at 2000-level in Mathematics and Statistics please consult the School Handbook, at https://www.st-andrews.ac.uk/mathematics-statistics/students/ug/module-choices-2000/