Statistical Practice in Epidemiology using R.
Course from Thursday 1 to Tuesday 6 June 2017
Tartu, Estonia
Organized by the
Estonian Genome center
and the
Institute of Mathematics and Statistics,
University of Tartu
The course starts early morning Thursday, so arrival in Tartu must be on
Wednesday 31 May. The course ends at 14:00, so departure will be
possible on Tuesday 6 (flights from Tallinn later than 18:00 can be
reached).
Similar courses were given every year since 2000 with the exception of
2003 and 2008.
Audience
The course is intended for epidemiologists and statisticians who wish
to use R for
statistical modelling and analysis of epidemiological data.
The aim of the course is to give young statisticians (or not so young
epidemiologists) who wish to enter or who has recently entered
biostatistics or epidemiology access to a set of tools in current use
by statisticians in epidemiology.
The course requires basic knowledge of epidemiological concepts and
study types. These will only be briefly reviewed, whereas the more
advanced epidemiological and statistical concepts will be treated in
depth.
Contents
- History of R. Language. Objects. Functions.
- Interface to other dataformats. Dataframes.
- Tabulation of data.
- Logistic regression for case-control-studies.
- Poisson regression for follow-up studies.
- Causal inference.
- Parametrization of models.
- Graphics in R.
- Graphical reporting of results.
- Time-splitting & SMR.
- Nested and matched case-control studies.
- Case-cohort studies.
- Survival analysis in continuous time.
- Competing risk models and relative survival.
- Multistate models.
All methods will be thoroughly illustrated using R in practical
exercises.
The Epi package
which is developed for epidemiological analysis in R will be introduced.
Particular attention will be given to the reporting of the results; in
particular the use of graphics.
Faculty:
- Krista Fischer,
Senior researcher,
Estonian Genome Center, University of Tartu,
Estonia.
- Esa Läärä,
Professor of Biometry,
Department of Mathematical Sciences, University of Oulu,
Finland.
- Janne Pitkäniemi,
Chief Statistician,
Finnish Cancer Registry, Helsinki, Finland &
Department of Public Health, University of Helsinki, Helsinki, Finland .
- Bendix Carstensen,
Senior Statistician,
Steno Diabetes Center, Gentofte &
Department of Biostatistics, University of Copenhagen,
Denmark. Maintainer of the Epi package.
- Martyn Plummer,
Senior Statistician,
International Agency for Research on Cancer, Lyon, France.
Member of the R core team.
Assistants:
Kristi Läll, Silva Kasela
Venue
Institute of Mathematics and Statistics,
J
Liivi 2.
Course fee:
700 EUR (academic); 950 EUR (non-academic)
Includes course, course material, lunch, coffee breaks and social events.
Excludes transport, accomodation and dinner.
The course is a self-supporting entity, and there are NO grants
or stipends available for travel or participation.
Course program and instructions:
- Program with time table
here
- Practicals here
- Slides here, and as
3-ups or
8-ups.
- Maps of the venue: detailed
and larger scale.
- Download the latest version of R 3.4.0
(here, for
example), and install it.
- Install the
R-package
Epi
,
version 2.15 (soon to come in windows version) from
here
or by starting R and then typing:
> install.packages("Epi")
at the command prompt in R. If you have an older version of
Epi
, then
update to 2.15. This requires that your computer is connected to the net.
The latest version 2.15 is not yet in the windows version
on CRAN, but you can get it from
here
and install it.
- Install the R-packages
mgcv
,
data.table
,
popEpi
and
epitools
by starting R and then typing:
> install.packages("mgcv")
> install.packages("data.table")
> install.packages("popEpi")
> install.packages("epitools")
at the command prompt in R. This requires that your
computer is connected to the net.
It may also be of interest to install the package
eha
too.
- If you are not very familiar with R,
here is a draft version of a
short introduction to R, aimed at an uninitiated audience.
-
Concepts in survival and demography
is a brief account of basic concepts and their
relationships.
- Spline
demonstration written by Paul Lambert, University of Leicester.
Transport and getting around in Tartu
Tartu
is situated 185 km south-east of the Estonian captal
Tallinn. Transportation is by air (or sea from Helsinki) to Tallinn
and from there approximately 2.5 hrs. by
bus or
train. The bus calls at Tallinn
airport, the train can be boarded at Ülemiste station, close to the
airport.
There is also an airport in Tartu,
though thinly serviced.
For more information on transport to and around
Tartu, look here.
Last updated 30 May 2017, BxC