Second Course in Statistics-E2
| Numbering Code | U-LAS11 20002 LE55 | Year/Term | 2022 ・ First semester | |
|---|---|---|---|---|
| Number of Credits | 2 | Course Type | Lecture | |
| Target Year | Mainly 2nd year students | Target Student | For all majors | |
| Language | English | Day/Period | Thu.2 | |
| Instructor name | Croydon, David Alexander (Research Institute for Mathematical Sciences Associate Professor) | |||
| Outline and Purpose of the Course | This second course in statistics provides an in-depth introduction to regression, which is the area of statistics in which a dependent variable is modelled as a linear function of one or more predictor variables, together with a random error. Regression has applications across scientific research, engineering, and various other fields, and it will be an additional goal of the course to explore some of these. Whilst some knowledge of introductory statistical theory might be helpful, the course is intended to be self-contained. | |||
| Course Goals |
- To gain a mathematical foundation in regression analysis - To understand how to interpret and evaluate a linear model - To be able to apply simple linear regression, multiple linear regression, and generalized linear models in examples |
|||
| Schedule and Contents |
The following indicates possible topics that will be covered and approximate schedule, though the precise details may vary depending on the student's proficiency level and background. Moreover, in addition to the mathematical content, applications will be considered throughout the course. (1) Simple linear regression [7 weeks] Definition of the model, parameter estimation, model interpretation and evaluation (2) Multiple linear regression [4 weeks] Estimators for such models, tests for significance of regression, tests on individual regression coefficients and subsets of coefficients, confidence intervals on regression coefficients, polynomial regression (3) Generalized linear models [3 weeks] Link functions and linear predictors, parameter estimation, model analysis, specific examples of generalized linear models including logistic regression and Poisson regression Total: 14 classes and 1 week for feedback |
|||
| Evaluation Methods and Policy | There will be regular (approximately fortnightly) exercise sheets throughout the course, for which students will be expected to return work and present some of their answers in class. This will account for 70% of the final mark. The remaining 30% will be based on a final exam. | |||
| Course Requirements |
Whilst not essential, it will benefit students if they have previously taken an introductory statistics course. |
|||
| Study outside of Class (preparation and review) | The lecturer will present the basic concepts in class, upon which assignments will be set. The time for these might vary from assignment to assignment, and student to student, but the lecturer estimates these to take 2-3 hours each. | |||
| Textbooks | Textbooks/References |
There will be no set textbook for the course, as the lectures will contain all the material needed for the homework and exam. However, students might find the following useful as additional reading: Introduction to the Practice of Statistics, Moore and McCabe Regression: Linear Models in Statistics, Bingham and Fry, Springer, 2010 Introduction to Linear Regression Analysis, Montgomery, Peck, and Vining, Wiley, 2012 |
||
