Gwybodaeth Modiwlau
Module Identifier
MX37210
Module Title
Regression and Anova
Academic Year
2015/2016
Co-ordinator
Semester
Semester 2
Mutually Exclusive
Pre-Requisite
Other Staff
Course Delivery
Delivery Type | Delivery length / details |
---|---|
Practical | 11 x 2 Hour Practicals |
Lecture | 33 x 1 Hour Lectures |
Assessment
Assessment Type | Assessment length / details | Proportion |
---|---|---|
Semester Assessment | Course work | 30% |
Semester Exam | 2 Hours (written examination) | 70% |
Supplementary Exam | 2 Hours (written examination) | 100% |
Learning Outcomes
On completion of this module, a student should be able to:
1. explain the rationale behind, and the underlying theory of, the analysis of variance;
2. explain the issues that arise in extending regression from one predictor variable to two;
3. carry out appropriate analyses and draw conclusions.
Brief description
This module covers the theory of some of the most commonly used statistical techniques - regression and the analysis of variance. It also includes practical application of these important techniques.
Aims
This module will provide a thorough grounding in the basic theory associated with some important statistical models.
Content
1. Regression: The regression model, Ordinary least squares and the Normal equations. Detailed analysis of the two regressor model. Residuals and the residual sum of squares. Sequential sum of squares. Standardised residuals. Decomposition of the sum of squares.
2. One way classification: the one way ANOVA model. Decomposition of the sum of squares. The ANOVA table and expected mean squares. Distribution of mean squares. The F-test. The treatment effects model. Random effects model. Unbalance design. The idea of blocking. Contrasts.
3. Higher order classification: The two way (balanced) model with replication. Decomposition. Interaction. Further contrasts and multiple comparisons. Expansion to higher order models.
2. One way classification: the one way ANOVA model. Decomposition of the sum of squares. The ANOVA table and expected mean squares. Distribution of mean squares. The F-test. The treatment effects model. Random effects model. Unbalance design. The idea of blocking. Contrasts.
3. Higher order classification: The two way (balanced) model with replication. Decomposition. Interaction. Further contrasts and multiple comparisons. Expansion to higher order models.
Notes
This module is at CQFW Level 6