Decision rule robust experimental designs
Despite compelling evidence that decision-makers use a wide range
of decision rules when making choices, the design of Stated Choice
experiments has exclusively been based on the (often implicit)
assumption that decision-makers make choices using
(linear-additive) Random Utility Maximization (RUM) rules. In a
recent
study
I show that efficient experimental designs can also be created for
RRM. One particularly important result of this study is that
designs that are efficient for estimating RUM models can be highly
inefficient for estimating RRM models, and vice versa. Therefore,
it is appealing to take multiple decision rules into account when
creating efficient experimental designs.
Create your own decision rule robust experimental design!
I have created a software tool -called Robust Design Generator (RDG)- for creating efficient designs optimised for regret minimisation, utility maximisation, or both, see the screen shot below. A recent paper by Andrew Collins and me explains how to generate designs using this tool.
Installation
There are 2 ways to use the Robust Design Generator tool:As a MATLAB app, which runs within the MATLAB environment. Advantages of using the Matlab app are that it allows the analyst to extend and build upon the software code and that it is very easy to install. This approach requires the analyst to have installed MATLAB R2017 (or higher).
1- Click here to download the MATLAB app.
2- Open MATLAB
3- Browse to the "APPS" tab (top left)
4- Select "Install App" and browse to the download location
5- Click (once) on the icon, and wait for the app to start
As a stand-alone application (Freeware). This approach does not require a MATLAB license. Therefore, in this form the tool can be used by anybody, without the need to use commercial software. It does require MS Windows and about 2GB hard drive space.
1- For WINDOWS click here to download the standalone app.
2- Unzip the files.
3- Double click the MyAppInstaller_web.exe to install the MATLAB environment
4- Double click the Robust_Design_Generator.exe. The RDG will start.
5- For MacOS click here to download the MacOS standalone app.
6- Double-click the downloaded file, the installer opens and will guide you through the installation process.
7- Open Launchpad, then go to "Delft_University_of_Technology" and click in "RobustDesignGenerator". The app will start.
Further reading
Van Cranenburgh, S., Rose, J.M. & Chorus, C.G. “On the robustness of efficient experimental designs towards the underlying decision rule” Transportation Research Part A: Policy and Practice.Van Cranenburgh, S. & Collins, A.T. “New software tools for creating efficient stated choice experimental designs robust for regret minimisation and utility maximisation decision rules”. Journal of Choice Modelling, (31), pg 104-123.