approx_rank_expected function

Approximation of expected ranks

Implements a variety of functions to approximate expected ranks for partial rankings.

approx_rank_expected(P, method = "lpom")

Arguments

• P: A partial ranking as matrix object calculated with neighborhood_inclusion

  or positional_dominance .

• method: String indicating which method to be used. see Details.

Returns

A vector containing approximated expected ranks.

Details

The method parameter can be set to

• lpom: local partial order model
• glpom: extension of the local partial order model.
• loof1: based on a connection with relative rank probabilities.
• loof2: extension of the previous method.

Which of the above methods performs best depends on the structure and size of the partial ranking. See vignette("benchmarks",package="netrankr") for more details.

Examples

P <- matrix(c(0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, rep(0, 10)), 5, 5, byrow = TRUE)
# Exact result
exact_rank_prob(P)$expected.rank

approx_rank_expected(P, method = "lpom")
approx_rank_expected(P, method = "glpom")

References

Brüggemann R., Simon, U., and Mey,S, 2005. Estimation of averaged ranks by extended local partial order models. MATCH Commun. Math. Comput. Chem., 54:489-518.

Brüggemann, R. and Carlsen, L., 2011. An improved estimation of averaged ranks of partial orders. MATCH Commun. Math. Comput. Chem., 65(2):383-414.

De Loof, L., De Baets, B., and De Meyer, H., 2011. Approximation of Average Ranks in Posets. MATCH Commun. Math. Comput. Chem., 66:219-229.

See Also

approx_rank_relative , exact_rank_prob , mcmc_rank_prob

Author(s)

David Schoch