Learn R Programming

crimelinkage (version 0.0.4)

Statistical Methods for Crime Series Linkage

Description

Statistical Methods for Crime Series Linkage. This package provides code for criminal case linkage, crime series identification, crime series clustering, and suspect identification.

Copy Link

Version

Install

install.packages('crimelinkage')

Monthly Downloads

14

Version

0.0.4

License

GPL-3

Maintainer

Michael Porter

Last Published

September 19th, 2015

Functions in crimelinkage (0.0.4)

Make crime series data

Make levels for merging category predictors

compareCategorical

Make evidence variables from categorical crime data

Ficticious dataset of crime events

Make break points for binning continuous predictors

Crime series identification

Cacluate ROC like metrics.

Generate a list of crimes for a specific offender

crimeClust_bayes

Bayesian model-based partially-supervised clustering for crime series identification

Make spatial evidence variables

Ficticious offender data

plots 1D bayes factor

expAbsDiff.circ

Expected absolute difference of two circular uniform RVs

Lookup the offenders responsible for a set of solved crimes

Creates evidence variables by calculating ‘distance’ between crime pairs

Naive bayes classifier using histograms and shrinkage

Generates indices of linked and unlinked crime pairs (with weights)

Follows path of one crime up a dendrogram

crimelinkage-package

crimelinkage package: Statistical Methods for Crime Series Linkage

Generate a list of offenders and their associated crime series.

Make evidence variables from numeric crime data

predict.naiveBayes

Generate prediction (sum of log bayes factors) from a naiveBayes object

Creates transparent colors

Plot a hierarchical crime clustering object

plot.naiveBayes

Plots for Naive Bayes Model

Estimates the bayes factor for continous and categorical predictors.

Hierarchical Based Linkage

Generate a background plot

crimeClust_hier

Agglomerative Hierarchical Crime Series Clustering

Expected absolute distance of a circular uniform RV to a point

compareTemporal

Make temporal evidence variable from (possibly uncertain) temporal info

Generate prediction of a component bayes factor

Generates crime groups from crime series data

Extracts the crimes with the largest probability of being linked.

Expected absolute difference of two uniform RVs

Calculates time between two vectors of datetimes