The np Package - NexTag Supports Open Source Initiatives

108 npsigtestValuexdatydatboot.methodboot.numboot.typeindexrandom.seeda p-variate data frame of explanatory data (training data) used to calculate theregression estimators.a one (1) dimensional numeric or integer vector of dependent data, each elementi corresponding to each observation (row) i of xdat.a character string used to specify the bootstrap method. iid will generate independentidentically distributed draws. wild will use a wild bootstrap. wildrademacherwill use a wild bootstrap with Rademacher variables. Defaultsto bootstrap.an integer value specifying the number of bootstrap replications to use. Defaultsto 399.a character string specifying whether to use a ‘Bootstrap I’ or ‘Bootstrap II’method (see Racine, Hart, and Li (2006) for details). The ‘Bootstrap II’ methodre-runs cross-validation for each bootstrap replication and uses the new crossvalidatedbandwidth for variable i and the original ones for the remaining variables.Defaults to boot.type="I".a vector of indices for the columns of xdat for which the test of significanceis to be conducted. Defaults to (1,2,. . . ,p) where p is the number of columns inxdat.an integer used to seed R’s random number generator. This is to ensure replicability.Defaults to 42.... additional arguments supplied to specify the bandwidth type, kernel types, selectionmethods, and so on, detailed below.npsigtest returns an object of type sigtest. summary supports sigtest objects. It hasthe following components:InPthe vector of statistics Inthe vector of P-values for each statistic in InIn.bootstrap contains a matrix of the bootstrap replications of the vector In, each columncorresponding to replications associated with explanatory variables in xdat indexedby index (e.g., if you selected index = c(1,4) then In.bootstrapwill have two columns, the first being the bootstrap replications of In associatedwith variable 1, the second with variable 4).Usage IssuesIf you are using data of mixed types, then it is advisable to use the data.frame function toconstruct your input data and not cbind, since cbind will typically not work as intended onmixed data types and will coerce the data to the same type.Caution: bootstrap methods are, by their nature, computationally intensive. This can be frustratingfor users possessing large datasets. For exploratory purposes, you may wish to override the defaultnumber of bootstrap replications, say, setting them to boot.num=99 A version of this package usingthe Rmpi wrapper is under development that allows one to deploy this software in a clusteredcomputing environment to facilitate computation involving large datasets.