Review of Linear Regression Using Stata

Registration deadline: 19 November 2017

This course is only open to social science PhD students from the Bristol, Bath, Exeter, Plymouth or UWE arms of the South West Doctoral Training Partnership (SWDTP).

To apply for a place, please email fssl-aqmcourses@bristol.ac.uk and give your name, department and institution. Please only apply for a place if you satisfy the course prerequisites and if you can attend both days.

Course leader: Dr George Leckie

Dates: November 30 - December 1 2017

Time: 10:00-17:00

Location: Small Computer Room 1.4n, Geographical Sciences, University Road, Clifton, Bristol BS8 1SS.

Description: This course provides a review of linear regression using the Stata statistical software. We first discuss how two-sample t-tests, analysis of variance (ANOVA), and analysis of covariance (ANCOVA) can all be viewed as special cases of linear regression. We then proceed to discuss simple regression and multiple regression. We pay special attention to specifying and interpreting dummy variables and interactions in linear regression models. We illustrate linear regression through social science examples. We show in detail how Stata can be used to conduct linear regression.

Outline:

DAY 1

10:00 - 12:00 Session 1 - Introduction; The faculty data; Two-sample t-test; One-way analysis of variance (ANOVA)
12:00 - 12:45 Lunch
12:45 - 14:45 Session 2 - Simple linear regression, Centring and rescaling variables
14:45 - 15:00 Break
15:00 - 17:00 Session 3 - Dummy variables, Multiple linear regression

DAY 2

10:00 - 12:00 Session 4 - Interactions; Dummy variables for more than two groups
12:00 - 12:45 Lunch
12:45 - 14:45 Session 5 - Other types of interactions; Nonlinear effects
14:45 - 15:00 Break
15:00 - 17:00 Session 6 - Residual diagnostics; Robust inference; Summary and further reading

The course consists of a 2:1 mix of lectures and practicals using Stata. Stata will be used solely through the command syntax and syntax files.

On completion of this course, participants should be able to conduct linear regression on their own data using Stata.

Prerequisites: This course is a refresher to linear regression rather than a first introduction. Students should therefore be familiar with both introductory inferential statistics (e.g., two-sample t-tests; ANOVA) and the basic notions of linear regression (e.g., simple regression; multiple regression). Prior experience of Stata would be advantageous, but is not essential.

Other details: Participants are expected to attend both days of the course. Please bring a memory stick so that you can take the course electronic materials away with you. While there is no dedicated time to analysing your own data, you are encouraged to apply what you learn on the course to your own data during the breaks should you wish to do so. I will be around for some of this time and am happy to discuss your research with you and in particular to answer questions relating to carrying out linear regression in your own research.

Refreshments: As this is a free course, lunch and coffee are not provided. However, there are various cafes close to the computer lab where you can purchase refreshments.

Contacts: Please email George Leckie (g.leckie@bristol.ac.uk) if you have any queries about the course.

Edit this page