StatRank0.0.6 package

Statistical Rank Aggregation: Inference, Evaluation, and Visualization

Breaking

Breaks full or partial orderings into pairwise comparisons

convert.vector.to.list

Helper function for the graphing interface

Estimation.GRUM.MLE

Performs parameter estimation for a Generalized Random Utility Model w...

Estimation.Normal.GMM

GMM Method for Estimating Random Utility Model wih Normal dsitribution...

Estimation.PL.GMM

GMM Method for estimating Plackett-Luce model parameters

Estimation.PL.MLE

Performs parameter estimation for the Plackett-Luce model using an Min...

Estimation.RUM.MLE

Performs parameter estimation for a Random Utility Model with differen...

Estimation.RUM.MultiType.MLE

Performs parameter estimation for a Multitype Random Utility Model

Estimation.RUM.Nonparametric

Nonparametric RUM Estimator

Estimation.Zemel.MLE

Estimates Zemel Parameters via Gradient Descent

Evaluation.AveragePrecision

Calculates the Average Precision

Evaluation.KendallTau

Calculates the Kendall Tau correlation between two ranks

Evaluation.KL

Calculates KL divergence between empirical pairwise preferences and mo...

Evaluation.LocationofWinner

Calculates the location of the True winner in the estimated ranking

Evaluation.MSE

Calculates MSE between empirical pairwise preferences and modeled pair...

Evaluation.NDCG

Calculates the Normalized Discounted Cumluative Gain

Evaluation.Precision.at.k

Calculates the Average Precision at k

Evaluation.TVD

Calculates TVD between empirical pairwise preferences and modeled pair...

Expo.MultiType.Pairwise.Prob

Pairwise Probability for PL Multitype Model

Generate.NPRUM.Data

Generate data from an NPRUM model

Generate.RUM.Data

Generate observation of ranks given parameters

Generate.RUM.Parameters

Parameter Generation for a RUM model

Generate.Zemel.Parameters

Generates possible scores for a Zemel model

Generate.Zemel.Ranks.Pairs

Generates pairwise ranks from a Zemel model given a set of scores

generateC.model.Nonparametric

Generate pairwise matrix for an NPRUM model

generateC.model

Turns inference object into modeled C matrix.

generateC

Generate a matrix of pairwise wins

KL

Calculates KL Divergence between non-diagonal entries of two matrices

Likelihood.Nonparametric

Calculate Likelihood for the nonparametric model

Likelihood.PL

A faster Likelihood for Plackett-Luce Model

Likelihood.RUM.Multitype

Likelihood for Multitype Random Utility Models

Likelihood.RUM

Likelihood for general Random Utility Models

Likelihood.Zemel

Gives Zemel pairwise Log-likelihood with data and scores

MSE

Calculates MSE between non-diagonal entries of two matrices if the dia...

Normal.MultiType.Pairwise.Prob

Pairwise Probability for Normal Multitype Model

Normal.Pairwise.Prob

Pairwise Probability for Normal Model

PL.Pairwise.Prob

Pairwise Probability for PL Model

scores.to.order

Converts scores to a ranking

scramble

Scramble a vector

turn_matrix_into_table

Converts a matrix into a table

TVD

Calculates TVD between two matrices

Visualization.Empirical

RPD Visualization

Visualization.MultiType

Multitype Random Utility visualizer

Visualization.Pairwise.Probabilities

Creates pairwise matrices to compare inference results with the empiri...

Visualization.RUMplots

RUMplot visualization

Zemel.Pairwise.Prob

Pairwise Probability for Zemel

A set of methods to implement Generalized Method of Moments and Maximal Likelihood methods for Random Utility Models. These methods are meant to provide inference on rank comparison data. These methods accept full, partial, and pairwise rankings, and provides methods to break down full or partial rankings into their pairwise components. Please see Generalized Method-of-Moments for Rank Aggregation from NIPS 2013 for a description of some of our methods.

  • Maintainer: Hossein Azari Soufiani
  • License: GPL (>= 2)
  • Last published: 2015-09-09