Prize (version 1.2.0)

gaggregate: gaggregate

Description

Aggregating individual judgments (pairwise comparison matrices - PCMs) into a group judgement or group priority.

Usage

gaggregate(srcfile, method = "geometric", simulation = 500)

Arguments

srcfile

a matrix with one or two columns. Column one (required) includes the path (location) to each individual pairwise comparison matrix and column two (optional) includes the individual weights. The matrix rowname is individuals identifier.

method

two methods are available for aggregation of individual opinions, (1) arithmetic, which compute the arithmetic mean of individual priorities, (2) geometric, which computes the geometric mean of individual PCMs. If individuals are assigned with a weight, the weighted arithmetic/geometric mean will be computed. The default method is 'geometric'.

simulation

simulation size for computation of Satty's inconsistency. The default value is 500.

Value

An S4 object including group PCM/prioritise;If geometric mean is used, the returning object includes: aggregated group PCM (AIJ), group consistency ratio (GCR), individual consistency ratios (ICR), consensus index (CI), and priority matrix (IP).If aritmetic mean is used, the returning object includes: agrregated group priority (AIP), individual consistency ratios (ICR), and priority matrix (IP).

References

E. Forman and K. Peniwati. Aggregating individual judgments and priorities with the analytic hierarchy process. European Journal of Operational Research, 108(1):165-169, 1998.

Examples

mat <- matrix(nrow = 4, ncol = 1, data = NA)
mat[,1] <- c(system.file('extdata','ind1.tsv',package = 'Prize'),
            system.file('extdata','ind2.tsv',package = 'Prize'),
            system.file('extdata','ind3.tsv',package = 'Prize'),
            system.file('extdata','ind4.tsv',package = 'Prize'))
rownames(mat) <- c('ind1','ind2','ind3', 'ind4')
colnames(mat) <- c('individual_judgement')

# non-weighted aggregation
res <- gaggregate(srcfile = mat, method = 'geometric', simulation = 500)

# weighted aggregation
# Decision makers are assigned with a priority value based on their specialization and perspectives.
mat <- cbind(mat, c(0.35,0.25,0.15,0.25))
colnames(mat)[2] <- 'individual_weight'

res <- gaggregate(srcfile = mat, method = 'geometric', simulation = 500)