A new version of the R package abcrf has been posted on Friday by Jean-Michel Marin, in conjunction with the recent arXival of our paper on point estimation via ABC and random forests. The new R functions come to supplement the existing ones towards implementing ABC point estimation:
- covRegAbcrf, which predicts the posterior covariance between those two response variables, given a new dataset of summaries.
- plot.regAbcrf, which provides a variable importance plot;
- predict.regabcrf, which predicts the posterior expectation, median, variance, quantiles for a given parameter and a new dataset;
- regAbcrf, which produces a regression random forest from a reference table aimed out predicting posterior expectation, variance and quantiles for a parameter;
- snp, a simulated example in population genetics used as reference table in our Bioinformatics paper.
Unfortunately, we could not produce directly a diyabc2abcrf function for translating a regular DIYABC output into a proper abcrf format, since the translation has to occur in DIYABC instead. And even this is not a straightforward move (to be corrected in the next version of DIYABC).