The Reshaped Sequential Replacement Toolbox is a collection of MATLAB modules for carrying out variable selection based on the Reshaped Sequential Replacement (RSR) algorithm. The RSR algorithm can be used both in regression and classification. The implemented methods are Ordinary Least Squares (OLS) (sometimes called Multiple Linear Regression – MLR) and Principal Component Regression (PCR) in regression and K Nearest Neighbours (kNN) in classification. A pseudo-graphical user interface (p-gui), which assists loading the data, creating the options and launching the calculation, is also provided with the toolbox.
Help files
HTML files are provided toghter with the MATLAB files in order to help the user. The HTML help provides some underlying information on variable selection (see Theory section); it also explains how to prepare your data, how to create the options and how to launch the variable selection algorithm.
Conditions and warranty
The toolbox is freeware and may be used (but not modified) if proper reference is given to the authors. Preferably refer to the followign papers:
Cassotti, M., Grisoni, F., Todeschini, R. (2014). Reshaped Sequential Replacement: an efficient approach to variable selection. Chemometrics and Intelligent Laboratory Systems, 133, 136-148. doi: 10.1016/j.chemolab.2014.01.011
Grisoni, F., Cassotti, M., Todeschini, R. (2014). Reshaped Sequential Replacement for variable selection in QSPR: comparison with other reference methods. Journal of Chemometrics, 28, 249-259. doi: 10.1002/cem.2603
In short, no guarantees, whatsoever, are given for the quality of this toolbox or for the consequences of its use. It is inevitable that there will be some bugs, but we have tried to test the algorithms thoroughly.
Download
Fill in the following form. Your personal data will be used only for notification via email of new releases of the toolbox and will not be communicated to external third parties. Once the form has been submitted, download the rar file containing the toolbox on a local folder, unzip the rar file and extract all the Matlab modules in a unique folder. Before starting calculations, please read the HELP files provided in HTML format. A complete guide on how to calculate models is provided.