Calculate posterior probabilities

This function calculates the probability P(Y | X, data), where Y and X are two (non overlapping) sets of joint variates. The function also gives quantiles about the possible variability of the probability P(Y | X, newdata, data) that we could have if more learning data were provided, as well as a number of samples of the possible values of such probabilities. If several joint values are given for Y or X, the function will create a 2D grid of results for all possible compbinations of the given Y and X values. This function also allows for base-rate or other prior-probability corrections: If a prior (for instance, a base rate) for Y is given, the function will calculate the P(Y | X, data, prior) from P(X | Y, data) and the prior by means of Bayes's theorem.

Usage

Pr(
  Y,
  X = NULL,
  learnt,
  priorY = NULL,
  nsamples = 100L,
  quantiles = c(0.055, 0.25, 0.75, 0.945),
  parallel = TRUE,
  silent = TRUE,
  usememory = TRUE,
  keepYX = TRUE
)

Arguments

Y: matrix or data.table: set of values of variates of which we want the joint probability of. One variate per column, one set of values per row.
X: matrix or data.table or NULL: set of values of variates on which we want to condition the joint probability of Y. If NULL (default), no conditioning is made (except for conditioning on the learning dataset and prior assumptions). One variate per column, one set of values per row.
learnt: Either a string with the name of a directory or full path for a 'learnt.rds' object, produced by the learn function, or such an object itself.
priorY: numeric vector with the same length as the rows of Y, or TRUE, or NULL (default): prior probabilities or base rates for the Y values. If TRUE, the prior probabilities are assumed to be all equal.
nsamples: integer or NULL or "all": desired number of samples of the variability of the probability for Y. If NULL, no samples are reported. If "all" (or Inf), all samples obtained by the learn function are used. Default 100.
quantiles: numeric vector, between 0 and 1, or NULL: desired quantiles of the variability of the probability for Y. Default c(0.055, 0.25, 0.75, 0.945), that is, the 5.5%, 25%, 75%, 94.5% quantiles (these are typical quantile values in the Bayesian literature: they give 50% and 89% credibility intervals, which correspond to 1 shannons and 0.5 shannons of uncertainty). If NULL, no quantiles are calculated.
parallel: logical or integer: whether to use pre-existing parallel workers, or how many to create and use. Default TRUE.
silent: logical: give warnings or updates in the computation? Default FALSE.
usememory: logical: save partial results to disc, to avoid crashes? Default TRUE.
keepYX: logical, default TRUE: keep a copy of the Y and X arguments in the output? This is used for the plot method.

Value

A list of class probability, consisting of the elements values, and possibly the elements quantiles (if non-NULL argument quantiles), samples (if non-NULL argument nsample), Y, X. Element values: a matrix with the probabilities P(Y|X,data,assumptions), for all combinations of values of Y (rows) and X (columns). Element quantiles: an array with the variability quantiles (3rd dimension of the array) for such probabilities. Element samples: an array with the variability samples (3rd dimension of the array) for such probabilities. Elements Y, X: copies of the Y and X arguments.