Bayesian Design of Experiments for GLMs
Code and TeX archives used in the undergraduate thesis Bayesian Design of Experiments for Generalized Linear Models by Gian Carlo Di-Luvi Martínez (2018). Code uploaded both in English and in Spanish (original language in which it was written).
The code implements Overstall and Woods' Approximate Coordinate Exchange (ACE) algorithm for finding optimal bayesian experimental designs (Overstall and Woods, 2016), particularly by using Overstall, Woods and Adamou's R package acebayes. It also produces graphs with Wickham's ggplot2 and Schloerke et al.'s GGally. See the bibliography for more references.
References
- Di-Luvi, G. C. (2018). Bayesian Design of Experiments for Generalized Linear Models (undergraduate thesis). Instituto Tecnológico Autónomo de México, Mexico City, Mexico.
- Overstall, A. M. and Woods, D. C. (2016). Bayesian Design of Experiments using Approximate Coordinate Exchange. Technometrics In Press, 1-13.
- Overstall, A. M., Woods, D. C., and Adamou M. (2017). acebayes: Optimal Bayesian Experimental Design Using the ACE Algorithm [Software Manual]. Downloaded from https://cran.r-project.org/package=acebayes (R package version 1.4.1).
- Schloerke, B., et al. (2017). GGally: Extension to 'ggplot2'. [Software Manual]. Downloaded from https://cran.r-project.org/package=GGally. (R package version 1.3.2).
- Wickham, H. (2009). ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York. Downloaded from http://ggplot2.org/