Predictive Modelling (ODL) STATS5076
- Academic Session: 2019-20
- School: School of Mathematics and Statistics
- Credits: 10
- Level: Level 5 (SCQF level 11)
- Typically Offered: Semester 2
- Available to Visiting Students: No
- Available to Erasmus Students: No
- Taught Wholly by Distance Learning: Yes
This course introduces students to predictive models for regression and classification.
The course mostly consists of asynchronous teaching material.
Requirements of Entry
The course is only available to online-distance learning students on the PGCert/PGDip/MSc in Data Analytics and Data Analytics for Government.
Linear Models 3
Statistics 3L: Linear Models
Regression Models (Level M)
30% Continuous Assessment
70% Final exam (can be taken at test centres)
The continuous assessment will typically be made up of three homework exercises, including online quizzes (15%) and a project assessed by a report (15%). Full details are provided in the programme handbook.
Main Assessment In: April/May
The aims of this course are:
■ to introduce students to predictive modelling using multiple linear regression as a showcase;
■ to present some of the distributional theory underpinning the normal linear models and the associated methods for testing and interval estimation;
■ to explain how the design matrix of a linear model can be constructed to accommodate categorical covariates or, through basis expansions, non-linear effects;
■ to expose students to the problem of missing data
■ to describe and contrast several common methods for model assessment as well as variable and model selection;
■ to show students how to implement these statistical methods using the R computer package.
Intended Learning Outcomes of Course
By the end of this course students will be able to:
■ formulate normal linear models in vector-matrix notation and apply general results to derive ordinary least squares estimators in particular contexts;
■ construct a design matrix incorporating categorical covariates or covariates with a nonlinear effect;
■ derive, evaluate and interpret point and interval estimates of model parameters;
■ conduct and interpret hypothesis tests in the context of the Normal Linear Model;
■ derive, evaluate and interpret confidence and prediction intervals for the response at particular values of the explanatory variables;
■ assess the assumptions of a normal linear model using residual plots and diagnostics;
■ make use of and critique different methods for assessing the performance of a predictive model such R2 or AIC/BIC and use these for model or variable selection;
■ distinguish between different processes leading to missing data and apply suitable strategies for dealing with missing data
■ identify scenarios where data may be considered to be smooth functions and apply suitable data analysis techniques;
■ implement these statistical methods using the R computer package;
■ frame statistical conclusions clearly.
Minimum Requirement for Award of Credits
Students must submit at least 75% by weight of the components (including examinations) of the course's summative assessment.