reusableDataForGLoMoSampling: Calculate GLoMo data that is usable for repeated 'completing'...
In GLoMo: Naive General Location Model

Description Usage Arguments Value Note Author(s) References See Also Examples

View source: R/GLoMo.r

Calculate GLoMo data that is usable for repeated 'completing' of the same data row.

1	reusableDataForGLoMoSampling(glomo, dfr, forrows = seq(nrow(dfr)), guiddata = NULL, verbosity = 0)

`glomo`	`GLoMo` object
`dfr`	`data.frame` or `numdfr` that needs to be 'completed'.
`forrows`	which of the rows in `dfr` need completion (defaults to all of them)
`guiddata`	"GuidData" class object for the rows in question, or character vector of uids for those rows, or `NULL`
`verbosity`	The higher this value, the more levels of progress and debug information is displayed (note: in R for Windows, turn off buffered output)

A list of class "ReusableDataForGLoMoSampling", holding items:

`guiddata`	like to the return value of `getGuidData`
`forrows`	copy of the `forrows` that was passed in the function
`perrow`	list that holds one item of class "ReusableDataForGLoMoSamplingForOneRow" per element of `forrows`

The structure of lists of class "ReusableDataForGLoMoSamplingForOneRow" is like this:

`a`	See "Analysis of Incomplete Multivariate Data" around p349
`useSigma`	covariance for missing continuous values of that row
`sigLeft`	See "Analysis of Incomplete Multivariate Data" around p349
`probs`	conditional probabilities of each 'cell' (see the members of `guiddata`)
`whichCntColNotNA`	within the continuous columns, the how manieth of them was not NA for this row
`whichCntColNA`	within the continuous columns, the how manieth of them was NA for this row
`presentCntColsInDfr`	column indices within `dfr` of the continuous columns that did not have NA for this row
`missingCntColsInDfr`	column indices within `dfr` of the continuous columns that had NA for this row

This method is mainly present because of predict.conditional.GLoMo, where there is repeated sampling from the same row.

Nick Sabbe (nick.sabbe@ugent.be)

"Analysis of Incomplete Multivariate Data" around p349, and also "Statistical Analysis with Missing Values"

GLoMo-package, NumDfr, predict.conditional.GLoMo

iris.md<-randomNA(iris, 0.1)
iris.md.nd<-numdfr(iris.md)
mdrow<-min(which(apply(iris.md, 1, function(currow){any(is.na(currow))})))
iris.nd.rnd<-rCatsAndCntInDfr(iris.md.nd, orgriName=NULL, verbosity=1)
iris.weights<-iris.nd.rnd$weights
iris.nd.rnd<-iris.nd.rnd[,1:5]
iris.glomo<-GLoMo(iris.nd.rnd, weights=iris.weights, verbosity=1)
reusableDataForGLoMoSampling(glomo=iris.glomo, dfr=iris.md.nd, forrows = mdrow,
	verbosity = 1)