Department of Statistics

Bayesian and Penalised Regression Methods for Epidemiological Analysis


Bayesian and Penalised Regression Methods for Epidemiological Analysis: Presented by Professor Sander Greenland

Thurs & Fri, 8 and 9 September 2016 

Background: Bayesian methods continue to become more popular in statistical modelling, but are not covered in most basic teaching. This lag may in part be due to common misconceptions (encouraged by most expositions) that Bayesian methods are conceptually distinct from frequentist methods and require special software. In fact, Bayesian methods are examples of penalized ("shrinkage") estimation and thus are perfectly acceptable frequentist methods; conversely, common frequentist methods are special types of Bayesian methods in which prior distributions are noninformative (so penalties are either zero or infinite). This short course will cover philosophy of statistics for epidemiology, illustrate the relationship between Bayesian and frequentist perspectives with real examples, and will show how penalization allows one to deal with a number of common problems that render ordinary statistical methods misleading for epidemiological research.

Topics covered (as of 21/4/2016)

Thursday 8 September

On day 1, Bayesian and penalized regression methods will be introduced, as an alternative to standard frequentist approaches, for analysing data from observational studies in health and social sciences. How to include prior information or suitable shrinkage, without requiring specialist software (such as WinBUGs), will be demonstrated, with SAS and Stata coding provided in the computer labs.

Friday 9 September
On day 2, the methods will be extended for more general regression modelling, including hierarchical (multilevel) and bias modelling. These methods provide an alternative to the parsimony-oriented approaches of standard regression analyses. In particular, they replace arbitrary variable-selection criteria by penalized estimation, which has many desirable frequentist properties and which facilitates realistic use of vague but important prior information. The methods facilitate handling problems of sparse data, multiple comparisons, and sensitivity analysis with multiple bias sources.


Target Audience

The course was designed for researchers with previous formal training in epidemiology and multivariable regression methods. During computing sessions the participants will be provided with examples of computer code.

Prerequisite and requirements

Attendees are requested toBring your own laptop with Stata or SAS installed. R code will also be available.





Professor Sander Greenland is one of the most prolific and influential authors on epidemiological methods of the past 2-3 decades. He is a co-author (with K Rothman) of the key reference textbook ‘Modern Epidemiology’ and an author of more than 390 articles in epidemiology and biostatistics journals





Regular (NZD)

Late (NZD)

    Available until 12pm 15th July 2016 NZT Available until 12pm 1st September 2016 NZT

UoA (internal)  

  • You must currently be employed by, or a student of, the University of Auckland and already have approval for your department or faculty to pay for your registration (excluding UniServices).
    • You must have the cost centre code, account code/(PReSS account code), approver/manager name & email before you fill the registration form. Generally these details are available with the GSC or the accountant for the department.
  • (If you are a UoA staff member or student who cannot pay via Journal Transfer please contact to organise credit card payment for availing internal price.)



Others / External/Non-UoA

  • Online Payments using Master or Visa Card. 



Fee depends on registration type.

* including GST (15%). GST is not applicable where the fee is paid from an account within The University of Auckland utilising the internal journal transfer mode (excluding uniservices).

# UoA - University of Auckland


Registration & Payment

Closing date:

  • Regular registration close at 12pm on 15th July 2016 NZT;
  • Late registration close at 12pm 1st September 2016 NZT.

The fine print:

  • Attendees must bring their own laptops, with SAS or STATA installed. R code will also be available
  • Registration payments by non-UoA staff and students can only be made by credit/debit card via our online payment system. Please check with your bank on conversion rates and banking fees if you are not using an NZD account card.
  • Our cancellation policy, due to the administrative and banking charges incurred by each registration, is to refund 95% of the registration fee for cancellations made prior to 5pm, Monday, 8 August 2016, and 50% for cancellations made up to 48 hours prior to the workshop.  No refund is given for cancellations made less than 48 hours prior to the workshop.
  • Any refunds processed will be in NZD. Please check with your bank on conversion rates and banking fees if you are not using an NZD account credit card.
  • Please provide your reference number “Ref:” which appears on your confirmation email in any communications you have with us in regard to your registration.  This will help in avoiding any ambiguities.


Registration Form:


  • University of Auckland Staff and Student Participants/Internal Journal Transfer (excluding UniServices)
    • If your University of Auckland faculty or department (excluding UniServices) will be paying for your registration by Internal Journal, please click here to register.
    • If you are a UoA staff member or student who cannot pay via Journal Transfer please contact to organise credit card payment.


  • Others/ External Payments/ Non-UoA 





  • City Campus, The University of Auckland, Auckland CBD, Auckland, New Zealand.