30 and 31 October 2014, Sydney
Presented by the University of Technology, Sydney
with Thomas Lumley,
targeted at Statisticians, epidemiologists interested in both methods and applications.
About the presenter:
Thomas Lumley was a Professor in the Department of Biostatistics at University of Washington Seattle until 2010 when he returned to take a position as Professor of Biostatistics at the University of Auckland. He has received a number of awards, including most recently election as a Fellow of the American Statistical Association. He is an expert on statistical methods for survey sampling and has published extensively on the topic, including a recently book, Complex Surveys: a guide to analysis using R, published by Wiley. He is the developer of the R survey package and has worked extensively in both cardiovascular epidemiology and design-based inference.
For more details, please click here.
About the course:
This course is about design and analysis for epidemiologic research based on random subsampling from an existing population, cohort or case-control sample. Professor Lumley has published extensively on this topic, often in collaboration with Professor Norman Breslow from University of Washington. A good sense of the material to be covered in the course can be obtained by looking over the following articles:
- Breslow, Lumley et al (2009 ). Using the Whole Cohort in the Analysis of Case-Cohort Data. American Journal of Epidemiology. (http://aje.oxfordjournals.org/content/early/2009/04/08/aje.kwp055.full)
- Lumley, Shaw and Dai (2011). Connections between Survey Calibration Estimators and Semiparametric Models for Incomplete Data. International Statistical Review, Volume 79: 200–220. (http://onlinelibrary.wiley.com/doi/10.1111/j.1751-5823.2011.00138.x/abstract)
The course will cover much of the material presented in Professor Lumley’s book (http://au.wiley.com/WileyCDA/WileyTitle/productCd-0470284307.html). The course will include some practical sessions using the R Survey package, which can be downloaded from http://cran.r-project.org/web/packages/survey/index.html
The first day will cover more general topics, while the second will focus on the more specialized topic of two-phase sampling.
- Complex survey sampling: stratification, clustering, weighting, multistage/multiphase sampling
- Regression models for survey data, including AIC, BIC, and likelihood ratio tests
- Practical session: bring your own laptop
- Unmatched, matched, and countermatched case-control designs
- Two-phase case-control sampling, case-cohort sampling
- Calibration of weights to use the whole cohort
- Practical session: bring your own laptop
- New research: calibration of weights in counter-matched designs, efficiency in nearly-true models
Course starts at 9:30 and finishes by 5pm both days, with registrations opening at 8:30am on the first day. Morning and afternoon tea will be provided at approximately 11am and 3:00pm, respectively.
There will be a lunch break from 12:30 to 1:30
NOTE: Participants are required to bring their own laptops and install R prior to attending the workshop. Installation instructions will be supplied.
- Understand general concepts related to survey sampling for epidemiological research
- Understand the theory of two-stage sampling as developed by Breslow, Lumley and others.
- Learn to apply these methods in R
- Gain an appreciation for latest research in the area
Early Bird Registrations (registration and payment before 15 October 2014)
General public: $675
SSAI Members: $450.00
Regular registrations (registrations and payment from 15 October 2014)
General public: $725.00
SSAI Members: $500.00
SSAI Membership is available for $20.00 p/a (student membership) or $225.00 p/a (full membership)
Registrations close strictly on 23 October 2014.
Cancellations received prior to 27 October 2014 will be refunded in full. Cancellations need to be accompanied by a valid credit card number, expiry date and CVV number which will be used to put the refund through. After this time no part of the registration fee will be refunded. However, registrations are transferable within the same organisation. Please advise any changes to firstname.lastname@example.org.
Occasionally workshops have to be cancelled due to a lack of subscription. Early registration ensures that this will not happen. However, please contact the SSAI Office before making any travel arrangements to confirm that the workshop will go ahead, because the SSAI will not be held responsible for any travel or accommodation expenses incurred due to a workshop cancellation.
|When:||30/10/2014 - 31/10/2014|
|Time:||9:30 am - 5:00 pm|
|Location:||University of Technology,Building 6, Room 3.52,
702-730 Harris Street,