MAS2904 : Statistical Inference & Stochastic Modelling
- Offered for Year: 2020/21
- Module Leader(s): Professor Robin Henderson
- Lecturer: Dr Daniel Henderson
- Owning School: Mathematics, Statistics and Physics
- Teaching Location: Newcastle City Campus
Semesters
Semester 1 Credit Value: | 10 |
Semester 2 Credit Value: | 10 |
ECTS Credits: | 10.0 |
Aims
To lay the foundations of statistical inference. The students will learn about the distinction between a population and a sample. They will know about the use of estimators calculated from random samples as a means of learning about properties of the population. They will be able to describe the role of likelihood methods in the derivation of estimators and their properties.
This module will also provide an introduction to ways of mathematically describing processes that exhibit variability. Students will learn about the use of linear models to build statistical descriptions of data and about the use of simple probability distributions to provide useful models for many applications. Students will be able to use regression analysis in some simple cases; they will be able to apply Poisson Processes to model relevant random processes
Module summary
Statistics aims to learn about populations on the basis of samples drawn from them. Population parameters, such as means, can be estimated by suitable sample statistics, but they will be in error because of sample to sample variation. Statistical inference is concerned both with estimating parameters and also with quantifying the associated sampling variation.
This module introduces fundamental notions of a standard error, confidence interval and hypothesis tests, in the context of both discrete and continuous variables. The likelihood is probably the most important concept in statistical methodology, and its introduction in the case of a scalar parameter is one of the main features of the module.
The module will also introduce students to two distinct areas of stochastic modelling. One part will broaden the students' knowledge of statistical inference by introducing the linear model. This will start with a simple regression for a scalar covariate, moving to an introductory treatment of a matrix-based approach for a model with more covariates. The other part will be to use the Poisson process as an example of a model for a process of events occurring randomly in time. The main properties of the homogenous Poisson process will be derived, and necessary tools, such as probability and moment generating functions, will be studied.
Outline Of Syllabus
Notion of an estimator: examples using means and proportions.
Properties of sampling distributions, including standard errors and confidence intervals.
Simulation of a sampling distribution.
Central Limit Theorem via simulation, no proof.
Likelihood, maximum likelihood estimators (scalar case) and their properties, including the illustration of these using simulation. Likelihood ratio test. Sufficiency.
Introduction to hypothesis tests: rejection regions, type I and type II errors, power and significance level. Most powerful tests via the Neyman-Pearson Lemma. Illustrations using one- and two-sample hypothesis tests for means and for proportions.
Simple linear regression, i.e. E(Y) = ?0 + ?1 x for scalar x with Normal errors with unknown variance. Equivalence of least squares and maximum likelihood. Properties of estimator of ? = (?0 ?1). Introduction of the general linear model using matrix formulation; demonstration of formula for the estimator of ?; use of formula for the variance of the estimator of ? but no proof. Examples using regression with two or three continuous covariates.
Introduction to PGFs and MGFs. Formal definition of the homogenous Poisson Process. Distribution of number of events in an interval. Distribution of inter-arrival times and time to nth event. Reinforcement of results using simulation.
Teaching Methods
Please note that module leaders are reviewing the module teaching and assessment methods for Semester 2 modules, in light of the Covid-19 restrictions. There may also be a few further changes to Semester 1 modules. Final information will be available by the end of August 2020 in for Semester 1 modules and the end of October 2020 for Semester 2 modules.
Teaching Activities
Category | Activity | Number | Length | Student Hours | Comment |
---|---|---|---|---|---|
Guided Independent Study | Assessment preparation and completion | 30 | 1:00 | 30:00 | N/A |
Scheduled Learning And Teaching Activities | Lecture | 9 | 1:00 | 9:00 | Present in Person |
Scheduled Learning And Teaching Activities | Lecture | 9 | 1:00 | 9:00 | Synchronous On-Line Material |
Structured Guided Learning | Lecture materials | 36 | 1:00 | 36:00 | Non-Synchronous Activities |
Structured Guided Learning | Structured non-synchronous discussion | 18 | 1:00 | 18:00 | N/A |
Scheduled Learning And Teaching Activities | Drop-in/surgery | 4 | 1:00 | 4:00 | Office Hour or Discussion Board Activity |
Guided Independent Study | Independent study | 94 | 1:00 | 94:00 | N/A |
Total | 200:00 |
Jointly Taught With
Code | Title |
---|---|
MAS2901 | Introduction to Statistical Inference |
MAS2902 | Introduction to Regression and Stochastic Modelling |
Teaching Rationale And Relationship
Non-synchronous online materials are used for the delivery of theory and explanation of methods, illustrated with examples, and for giving general feedback on assessed work. Present-in-person and synchronous online sessions are used to help develop the students’ abilities at applying the theory to solving problems and to identify and resolve specific queries raised by students, and to allow students to receive individual feedback on marked work. Students who cannot attend a present-in-person session will be provided with an alternative activity allowing them to access the learning outcomes of that session. In addition, office hours/discussion board activity will provide an opportunity for more direct contact between individual students and the lecturer: a typical student might spend a total of one or two hours over the course of the module, either individually or as part of a group.
Alternatives will be offered to students unable to be present-in-person due to the prevailing C-19 circumstances.
Student’s should consult their individual timetable for up-to-date delivery information.
Assessment Methods
Please note that module leaders are reviewing the module teaching and assessment methods for Semester 2 modules, in light of the Covid-19 restrictions. There may also be a few further changes to Semester 1 modules. Final information will be available by the end of August 2020 in for Semester 1 modules and the end of October 2020 for Semester 2 modules.
The format of resits will be determined by the Board of Examiners
Exams
Description | Length | Semester | When Set | Percentage | Comment |
---|---|---|---|---|---|
Written Examination | 120 | 2 | A | 80 | Alternative assessment - in class test |
Exam Pairings
Module Code | Module Title | Semester | Comment |
---|---|---|---|
MAS2901 | Introduction to Statistical Inference | 2 | N/A |
MAS2902 | Introduction to Regression and Stochastic Modelling | 2 | N/A |
Other Assessment
Description | Semester | When Set | Percentage | Comment |
---|---|---|---|---|
Written exercise | 1 | M | 10 | written exercises |
Written exercise | 2 | M | 10 | written exercises |
Assessment Rationale And Relationship
A substantial formal examination is appropriate for the assessment of the material in this module. The course assessments will allow the students to develop their problem solving techniques, to practise the methods learnt in the module, to assess their progress and to receive feedback; these assessments have a secondary formative purpose as well as their primary summative purpose.
Reading Lists
Timetable
- Timetable Website: www.ncl.ac.uk/timetable/
- MAS2904's Timetable