Statistical Modelling (Part II, Michaelmas 2024)
General information
-
This course consists of 16 lectures and 8 practical sessions. It complements the Part II Principles of Statistics, but takes a more applied perspective.
-
Time: 12-1 M/W/F
-
Location: MR4.
-
Instructors: Qingyuan Zhao (lecturer) and Louis Christie (practical instructor).
-
Prerequisites: Part IB Statistics.
-
Please email me or leave a comment below if you find any mistakes or have any questions.
-
Lectures will be recorded and the recordings can be found on Moodle.
Lectures notes
- Lecture Notes (updated ).
- Demonstration in lectures .
- See below for practical sheets.
Example sheets
- Example sheet 1 (with corrections )
- Example sheet 2 (with corrections )
- Example sheet 3 .
Provisional schedule
| Date | Number | Topic |
|---|---|---|
| L1 | Introduction; review of OLS | |
| P1 | Basic R ( sheet; R code) | |
| L2 | Nested projection; Exact inference | |
| P2 | Computing linear models ( sheet; R code) | |
| L3 | Misspecified linear model | |
| L4 | Model diagnostics; Bias-variance trade-off | |
| P3 | Data frame; Diagnostics; Quartets ( sheet; R code) | |
| L5 | Model selection | |
| L6 | Box-Cox transformation; regularization | |
| P4 | Model selection ( sheet; R code) | |
| L7 | Exponential family; Basic properties | |
| L8 | Asymptotic inference; Bayes perspective | |
| L9 | Hypothesis testing; Deviance; | |
| P5 | Exponential family ( sheet; R code) | |
| L10 | Canonical GLMs; analysis of deviance | |
| L11 | Dispersion parameter; linkage; MLE | |
| L12 | Asymptotic inference; iterative algorithms | |
| L13 | GLM diagnostics and selection; Binomial GLMs | |
| P6 | Binomial GLMs ( sheet; solution) | |
| L14 | Poisson GLM | |
| L15 | Contingency tables | |
| P7 | Binomial and Poisson GLMs ( sheet; solution) | |
| P8 | Contingency tables; regularization ( sheet; solution) | |
| L16 | Review and look forward |
Further readings
-
Prof Richard Weber’s notes for IB Statistics.
-
A. Agresti. Foundations of Linear and Generalized Linear Models. Wiley 2015. [Introduction to the classical theory of LM and GLM.]
-
G. James, D. Witten, T. Hastie, R. Tibshirani. An Introduction to Statistical Learning (with Applications in R). Springer 2013. [Modern, more algorithmic perspective on statistical modelling, with R labs.]
-
B. Efron. Exponential Families in Theory and Practice. CUP 2022. [More advanced theory for exponential families.]
-
D. Freedman. Statistical Models: Theory and Practice. CUP 2012. [Less technical but excellent book to reflect on how statistical models should be used for real-world scientific problems.]
-
W. N. Venables, D. M. Smith and the R Core Team. An Introduction to R.
-
H. Wickham. Advanced. [For anyone who wants to use R as a programming language.]