Introduction to Panel Data Analysis

HILDA training

Crawford School of Public Policy Australian National University

More Information

Nicole Watson

n.watson@unimelb.edu.au

T: +61 3 8344 2088

A 4-day hands-on introductory course on panel data analysis will be held on 17 - 20 February 2020 at the Australian National University. There are two 3-day options possible for this course as described below.

Course information

This course is designed for people familiar with panel data, including how to clean data and set it up for analysis, but now want to understand various statistical and econometric techniques that take full advantage of the panel nature of the data. The topics covered in the course include:

DAY 1

  • Longitudinal descriptive statistics, such as
    • cross-wave correlations
    • conditional means
    • transition probabilities

DAYS 2 & 3

  • Regression analysis, including using pooled data, or cross-sectional techniques using lagged data
  • Panel data regression techniques:
    • Difference-in-differences
    • Fixed effects
    • Random effects
    • First-differences
    • Second- (and longer) differences

DAY 4

  • Instrumental variables in panel data
  • Panel data regression techniques:
    • Binary response models
    • Categorical response models

Data from the Household, Income and Labour Dynamics in Australia (HILDA) Survey will be used during the course and participants will be required to apply for, and be approved to use, the General Release 18 datasets prior to the course. The course will take several published papers using the HILDA Survey data with a view to re-producing some of the estimates presented by the authors. The course will be taught in Stata.

Course instructor

The course will be presented by Professor Robert Breunig, who is a researcher at the Crawford School of Public Policy at the Australian National University. His primary applied research interests are in analysing individual and firm behaviour, evaluating government tax and transfer programs and analysing large data sets.

Pre-requisites

You will have completed the “Getting Started: Analysing HILDA with Stata” course (or you will some have experience using longitudinal data and have some experience programming in Stata). You will be familiar with regression theory. You will need to apply for, and be approved to use, HILDA General Release 18 (available in December 2019). If you have any questions about these pre-requisites or wish to discuss them further, please contact Nicole Watson

Registrations

Places are limited. Registrations close 5pm 7 February 2020 unless all of the places are taken earlier. Please register for this course here.

If you would like to receive notifications of other training courses, please subscribe to the HILDA mailing list.

Location: Crawford School of Public Policy, Australian National University (lab to be advised)

Date/Time: Monday 17 February to Thursday 20 February 2020, 9.15am – 4.00pm

Catering: Morning tea, lunch and afternoon tea provided

Fees (incl. GST): 4-day course is $1,200 ($800 PhD and Masters students intending to use longitudinal data in their thesis).

3-day course is $900 ($600 PhD and Masters students intending to use longitudinal data in their thesis) for Days 1-3 OR Days 2-4. The Day 2-4 option is only available for those attending the “Getting Started: Analysing HILDA with Stata” early February 2020.

Registration: Places are limited. Please register here