There is a package available for R called CosmoPhotoz, see CRAN. This package bundles code to conduct analyses as described in the paper "The Overlooked Potential of Generalized Linear Models in Astronomy-II: Gamma regression and photometric redshifts" by Elliott, de Souza, Krone-Martins, Cameron, Ishida, Hilbe (2014) available at http://arxiv.org/abs/1409.7699. The package contains functions facilitating the modeling of redshifts as a function of photometric data for multi-wavelength observations of galaxies. The models under consideration are (generalised) linear models. The dependent variable is the redshift z, which when estimated from photometric data is commonly referred to as photo-z. The independent variables or predictors in the models are magnitudes measured at different wavelengths. It is really nice that the authors provide their analysis routines as a package. This makes their proposed procedures a lot easier to understand and to reproduce. For amateurs and hobbyists interested in astrostatistics, such a package provides an excellent point of entry into the field. We explore the functionality of the CosmoPhotoz package using a data set that comes with the package. We repeat some of the analysis provided in the Elliot et al. paper and elaborate on some aspects. We put our analyses online at the RPubs website: http://rpubs.com/bbuelens/CosmoPhotozTrialRunv10 |

Projects >