Small Area Estimation using R and Stat-JR

Description:

This one-day course is being run in collaboration with Professor Nikos Tzavidis from the University of Southampton and can be attended as a stand-alone course for those already familiar with multilevel modelling or as a continuation for the introductory course on multilevel modelling that immediately precedes it.
 

The workshop will provide an introduction to Small Area Estimation and in particular how multilevel models are used as part of this topic. It will use the R statistical software to illustrate how to fit classical small area estimation models using the emdi package. It will also use the Stat-JR software distributed along with MLwiN by the Centre for Multilevel Modelling, Bristol to illustrate work in a current ESRC funded project looking at MCMC methods for Small Area Estimation and we will demonstrate an eBook that has been developed as part of the project.
 

The workshop will consist of a mixture of explanatory talks and demonstrations together with ‘hands-on’ model fitting. 

Links

General information on Stat-JR: https://www.bristol.ac.uk/cmm/software/statjr/

Stat-JR manuals: https://www.bristol.ac.uk/cmm/software/statjr/manuals/

If you have not used Stat-JR before then it is suggested that you work through the quick start guide prior to attending the workshop to ensure that the software is set up correctly.

Topics covered:

1. Introduction to small area estimation including unit-level and area-level models
2. The emdi package in R along with a practical to illustrate small area estimation
3. Introduction to the StatJR package with particular focus on the eBook interface and the new small area estimation templates.
4. Practical testing out the SAE ebook on an example dataset

Pre-requisites:

This course assumes familiarity with multilevel modelling up to the level of module 5 of our LEMMA online course (https://www.bristol.ac.uk/cmm/learning/online-course/course-topics.html) or that you have attended the introduction to multilevel modelling course preceding it. If you are attending this course, you will need to bring your own Windows laptop. If you already have Stat-JR then we advise that you install and test this beforehand, otherwise we will provide a cut-down version on a USB stick for the duration of the workshop.

Instructors:

Professor Nikos Tzavidis, Professor William Browne, Mr Christopher Charlton

Timing:

The course starts with registration at 10.15 and finishes at 17:00. Participants are expected to attend the full course. 

Cost:

For UK-registered MSc and PhD students - £30.
For UK university academics, UK public sector staff, and staff at UK registered charity organisations - £30.
For all other participants - £30.

Combined cost with the Introduction to Multilevel Modelling Using MLwiN workshop:
For UK-registered MSc and PhD students - £210.
For UK university academics, UK public sector staff, and staff at UK registered charity organisations - £390.
For all other participants - £690.

Website and registration:

https://www.cmm.bris.ac.uk/clients/booking/

Region:

South West

Keywords:

Quantitative Data Handling and Data Analysis, Multilevel Modelling , Hierarchical models, Mixed models, Random effects, Longitudinal Data Analysis, Growth curve models

Related publications and presentations:

Quantitative Data Handling and Data Analysis
Multilevel Modelling
Hierarchical models
Mixed models
Random effects
Longitudinal Data Analysis
Growth curve models

Back to archive...