Type Package Title Game-Theoretic Probability Combination Version 1.0 Date 2015-08-30 Package Combine September 4, 2015 Author Alaa Ali, Marta Padilla and David R. Bickel Maintainer M. Padilla <padilla.mpf@gmail.com> Description Suite of R functions for combination of probabilities using a game-theoretic method. License GPL-3 Depends R (>= 2.14.0), methods URL http://www.cran.r-project.org, http://www.statomics.com NeedsCompilation no Repository CRAN Date/Publication 2015-09-04 21:49:35 R topics documented: Combine-package...................................... 1 ncomb.prob......................................... 2 Index 5 Combine-package Game-Theoretic Probability Combination. Description Details Suite of R functions for combining probability distributions according to a game-theoretic probability combination. 1
2 ncomb.prob Package: Combine Type: Package Version: 1.0 Date: 2015-08-30 License: GPL-3 Depends: R (>= 2.14.0), methods URL: http://www.cran.r-project.org, http://www.bioconductor.org, http://www.statomics.com Author(s) Code: David R. Bickel and Marta Padilla (modifications) Documentation: Alaa Ali and Marta Padilla Maintainer: D. R. Bickel <dbickel@uottawa.ca> References Bickel, D. R. (2012). Game-theoretic probability combination with applications to resolving conflicts between statistical methods. International Journal of Approximate Reasoning, 53, 880-891. Examples #Two probability distributions to combine x1<-c(a =.5, AA =.9, AAA =.6) x2<-c(a =.3, AA = NA, AAA =.5) z1 <- ncomb.prob(x = x1,y= x2,independent=true) z2 <- ncomb.prob(x = list(x1=x1,x2=x2),independent=false) ncomb.prob Combination of probability distributions. Description Usage It computes the combination of probability distributions according to few parameters. ncomb.prob(x, y = NULL, independent =!is_nothing(nsample), lower.plausible = 0, upper.plausible = 1, method.name = character(0), nsample = numeric(0), tolerance = 0.005, arithmetic = TRUE, loss.type = c("information","quadratic","harmonic","geometric","logarithmic", "evidential"), plots = FALSE,...)
ncomb.prob 3 Arguments x y Value tolerance List of numeric vectors of probabilities or a numeric vector of probabilities (see note). A numeric vector of probabilities. Default is NULL (see note). Small quantity to control the failure of the method. independent Logical. If independent=true, one weight is computed, otherwise one weight is computed per pair of elements to be combined (see note). lower.plausible A number within [0,1]. upper.plausible A number within [0,1]. method.name nsample arithmetic loss.type plots Names of the probabilities distributions to be combined. Number of samples (for Monte Carlo). Logical. If arithmetic=false, the logarithmic approach is applied. specifies loss function type: "information", "quadratic", "harmonic", "geometric", "logarithmic", "evidential". option to plot (plot=true) the input and output probabilities.... Other numeric vectors of probabilities to combine and further arguments passed to function optimize. A list: combined weight info A numeric vector that results of the combination of the data. Computed weights: a numeric value (if input independent=true) or vector (if input independent=false) with elements in [0,1]. Other information. Note - All input vectors elements must be within [0,1] - If input vectors do not have names, they will be created (see examples). - Elements of different vectors with same names are those to be combined. - If the input y = NULL and x is a numeric vector all its elements will be combined. Author(s) Code: David R. Bickel and Marta Padilla (modifications) Documentation: Alaa Ali and Marta Padilla References Bickel, D. R. (2012). Game-theoretic probability combination with applications to resolving conflicts between statistical methods. International Journal of Approximate Reasoning, 53, 880-891.
4 ncomb.prob Examples #Two probability distributions to combine x1<-c(a = 0.5, b = 0.2, d = NA, e = 0, 0.3, 0.8) x2<-c(b = 0.4, a = 0.3, e = NA, b = 0.2, 0.13, 0.28) z1 <- ncomb.prob(x = x1,y= x2,independent=true) z2 <- ncomb.prob(x = list(x1=x1,x2=x2),independent=false) #not yet implemented for independent=true: z3 <- ncomb.prob(x = x1,independent=false,loss.type="quadratic") z4 <- ncomb.prob(x = as.list(x1),independent=false)
Index Topic Combination of probability distributions Topic Combination Topic Combine Topic Game-theoretic Topic list(ncomb.prob) ncomb.prob, 2 Topic mutual information Topic package Combine (Combine-package), 1 ncomb.prob, 2 5