STATS 762 Statistical Modelling

Below description edited in year: 2017

Points: 15

Prereqs: STATS 210 or 225; 15 points from STATS 201, 207, 208 or B+ in BIOSCI 209

Restrictions: STATS 330

Credit: Final exam 60%, tests 20%, assignments 20%

For Advice: Thomas Lumley (Email: t.lumley@auckland.ac.nz | extn: 83785)

Taught: First Semester City

Website: STATS 762 website

This course includes the material in STATS 330. It is intended for postgraduate students who have not already passed STATS 330.

STATS 762 is an extended version of STATS 330. The main emphasis of this course is on analysing data using extensions of the regression methods seen in STATS 201/7/8. These extensions permit, for example, the building of models for response variables which are not continuous. The main statistical computer package used is R. Regression modelling is fundamental to statistics and data science. This course should be very useful for almost all subjects in Business and Economics, for Operations Research, for any experimental or social science.

Topics studied include: Application of the generalised linear model to fit data arising from a wide range of sources, including multiple linear regression models, Poisson regression, and logistic regression models. The graphical exploration of data. Model building for prediction and for causal inference. Other regression models such as quantile regression.

* The course uses a mixture of lecture and lab exercises. Students should bring their own laptop where possible.

* This course was revised substantially in 2016; information from earlier years may be out of date.

Disclaimer:
Although every reasonable effort is made to ensure accuracy, this information for the course year (2017), is provided as a general guide only for students and is subject to alteration. All students enrolling at the University of Auckland must consult its official document, the University of Auckland Calendar, to ensure that they are aware of and comply with all regulations, requirements and policies.