Dear all,
I am happy to announce that our optimal experimental design software PopED has
been translated from MATLAB to R and is now available as a package on the
Comprehensive R Archive Network (CRAN). This means that installation is as
simple as typing at your R command prompt:
install.packages("PopED")
PopED is a tool to test and optimize experimental designs for both population
and individual studies based on nonlinear mixed-effect models. Often this is
based on a computation of the Fisher Information Matrix (FIM). Key
functionality includes:
* Flexible model description — structural, between subject variability and
residual unexplained variability models can be easily and flexibly described by
the user.
* Incorporation of uncertainty in design optimization — one can take into
account parameter and/or model uncertainty in computing optimal designs.
* Wide range of optimization criteria — numerous defined design criteria
including D-family, E-family and S-family designs, plus the ability to define
your own design criteria to optimize (e.g., cost or the power to detect a drug
effect).
* Optimization of virtually any design variable such as time, dose, number
of patients per study arm, number of samples per study arm, start and stop time
of treatment, treatment length, etc.
* Full range of model and FIM approximation methods.
For more information about the R release of PopED please see
https://github.com/andrewhooker/PopED.git, for general information about PopED
please see http://poped.sourceforge.net/.
Best regards
Andrew Hooker
Andrew Hooker, Ph.D.
Associate Professor of Pharmacometrics
Dept. of Pharmaceutical Biosciences
Uppsala University
Box 591, 751 24, Uppsala, Sweden
Phone: +46 18 471 4355
Mobile: +46 768 000 725
http://www.farmbio.uu.se/research/researchgroups/pharmacometrics/