SINGS activities spring 2014

"Methods for dealing with biases in register-based studies” (1.5 hp), March 31 – April 2

Workshop on Advanced Methods Professor Miguel Hernán Harvard School of Public Health and Prof Sander Greenland UCLA, April 2 – 4

Workshop: “Writing and presenting successful grant applications and communicating science” (2.5 hp), May 14-16

For additional information about the activities, please see below.

“Methods for dealing with biases in register-based studies” (1.5 hp), March 3 – April 2
Description: The course include methods, such as imputation of missing data and sensitivity analysis, for biases in studies based on register-based data. Focus will also be on practical application to register-based studies.

Teachers:
Nicola Orsini, Ph.D., Associate Professor of Medical Statistics, Karolinska Institutet (course director)
Kirk Scott, Ph.D., Associate Professor of Economic History, Lund University
Juho Härkönen, Ph.D., Associate Professor of Sociology, Stockholm University
Matteo Bottai, Ph.D., Professor of Biostatistics, Karolinska Institutet
Maria Feychting, Ph.D., Professor of Epidemiology, Karolinska Institutet
Rickard Ljung, Ph.D., Associate Professor of Epidemiology, Karolinska Institutet
Andrea Discacciati, Doctoral Student, Karolinska Institutet

Workshop on Advanced Methods, Professor Miguel Hernán Harvard School of Public Health and Prof Sander Greenland UCLA, April 2-4
The workshop constitutes two parts and is given by international leading scientists. The content is focused on advanced epidemiological and statistical methods and concepts that can be applied in the analysis and interpretation of any kind of data.

Course 1: “Causal Inference with time-varying exposures and confounders”

Instructor: Miguel A. Hernán, Professor of Epidemiology, Harvard School of Public Health, Boston, MA, USA. Website: http://www.hsph.harvard.edu/miguel-hernan/  

Content: This course presents a framework for causal inference from observational data.  The emphasis is on complex longitudinal data with time-varying treatments and time-varying confounders that are affected by prior treatment. The methods described include g-estimation of structural nested models and inverse probability weighting of marginal structural models.

Course 2: “Sensitivity and Bayesian analysis for biases”

Instructor: Sander Greenland, Professor of Epidemiology, UCLA School of Public Health, and Professor of Statistics, UCLA College of Letters and Science, Los Angeles, CA, USA. Website: http://www.ph.ucla.edu/epi/faculty/greenland/

Content: In the analysis of observational studies different types of biases or errors (selection, participation, measurement, confounding) arise from the fact that is often not possible or feasible to observe exactly what one would like to observe. Few papers, however, investigate scientifically the role of bias in the observed findings. Bias analysis is about estimating the magnitude of potential biases and quantifying the uncertainty that should be associated with results. 

Workshop “Writing and presenting successful grant applications and communicating science” (2.5 hp), May 14-16
Description: The first part focuses on formulating an abstract and the second part focuses on a full proposal (maximum 5 pages). The workshops include features of a successful grant application as well as common problems to avoid. The workshop also focuses on how to effectively communicate not only research results, but also planned research both to peers within academia as well as to a wider audience. You will also receive constructive feedback on your work.

Teachers:
Kirk Scott, Ph.D., Associate Professor of Economic History, Lund University
Mårten Lundberg, Senior Advisor Hero Kommunikation
Anita Berglund, Ph.D, Lecturer in Epidemiology, Karolinska Institutet
Several other senior researchers working with register-based research in social and medical sciences