# Agg.Sim: Aggregation of expert's estimatives by similarity of values In CPP: Composition of Probabilistic Preferences (CPP)

## Description

This function computes the aggregated value of different expert's estimatives, using Beta PERT distributions to randomize the decision matrix.

## Usage

 `1` ```Agg.Sim(x, min, max, s, w, b) ```

## Arguments

 `x` Decision matrix of expert estimatives (rows) and criteria (columns). Benefit criteria must be positive and cost criteria must be negative. `min` Vector of minimum values in each criterion scale. For common scales to all criteria, the vector must repeat the minimum value as many times as the number of criteria. `max` Vector of maximum values in each criterion scale. For common scales to all criteria, the vector must repeat the maximum value as many times as the number of criteria. `s` Shape of a Beta PERT distribution, as described in the package 'mc2d'. There is no default value, however the higher the shape the higher the kurtosis of the random variable. `w` Weights describing the expert experience in the subject matter. `b` Beta describes the balance between the expert weights and their opinions. Beta varies in the interval [0,1]. The higher the index, the higher the importance of weights.

## Value

SM are the Similarity Matrices per criterion. CDC describes the Consensus Coefficient matrix. Agg.value gives the aggregated value of expert opinions per criterion.

## Examples

 ``` 1 2 3 4 5 6 7 8 9 10 11 12 13 14``` ```## Expert's estimatives on four criteria Exp.1 = c(4,7,6,8) Exp.2 = c(4,3,6,5) Exp.3 = c(3,8,2,9) Exp.4 = c(6,8,9,7) Exp.5 = c(5,9,2,4) Exp.6 = c(7,6,5,5) x = rbind(Exp.1,Exp.2,Exp.3,Exp.4,Exp.5) # Decision matrix min = c(0,0,0,0) # Minimum scale values. max = c(10,10,10,10) # Maximum scale values. s = 4 # Shape w = c(0.4,0.3,0.2,0.06,0.04) # Expert relevance. b = 0.4 Agg.Sim(x,min,max,s,w,b) ```

CPP documentation built on May 2, 2019, 1:34 p.m.