If you have any questions or comments, please do not hesitate to contact us via filing an issue on Github, writing an email to or join our zulipchat group or via personal emails.
The respy development team is currently a group of researchers, doctoral students, and students at the University of Bonn.
Philipp Eisenhauer (email )
Janos Gabler (email )
Tobias Raabe (email )
Annica Gehlen (MSM interface)
Moritz Mendel (Flexible choice sets, MSM interface)
Sofia Badini (Hyperbolic discounting)
Linda Maokomatanda (Robust OLS)
Tim Mensinger (Recommended reading)
Rafael Suchy (Quasi-Monte Carlo simulation)
We are grateful to the Social Science Computing Services at the University of Chicago who let us use the Acropolis cluster for scalability and performance testing. We appreciate the financial support of the AXA Research Fund and the University of Bonn.
We are indebted to the open source community as we build on top of numerous open source tools such as the SciPy and PyData ecosystems. In particular, without respy’s interface would not work without pandas and it could not rival any program written in Fortran in terms of speed without Numba.
respy was completely rewritten in the second release and evolved into a general framework for the estimation of Eckstein-Keane-Wolpin models. Please cite it with
@Unpublished{Gabler2020, Title = {respy - A Framework for the Simulation and Estimation of Eckstein-Keane-Wolpin Models.}, Author = {Janos Gabler and Tobias Raabe}, Year = {2020}, Url = {https://github.com/OpenSourceEconomics/respy}, }
Before that, respy was developed by Philipp Eisenhauer and provided a package for the simulation and estimation of a prototypical finite-horizon discrete choice dynamic programming model. At the heart of this release is a Fortran implementation with Python bindings which uses MPI and OMP to scale up to HPC clusters. It is accompanied by a pure Python implementation as teaching material. If you use respy up to version 1.2.1, please cite it with
@Software{Eisenhauer2019, Title = {respy - A Package for the Simulation and Estimation of a prototypical finite-horizon Discrete Choice Dynamic Programming Model.}, Author = {Philipp Eisenhauer}, Year = {2019}, DOI = {10.5281/zenodo.3011343}, Url = {https://doi.org/10.5281/zenodo.3011343} }
We appreciate citations for respy because it helps us to find out how people have been using the package and it motivates further work.