generate.heatmap.matrix: Given an input matrix, we can split it into smaller...

In RajeswaranV/vcdPlus: Summary and inference of categorical data and contingency tables

Description

Given an input matrix, we can split it into smaller sub-matrix (min 2x2) and then find the Chi-squared test for each sub-matrix. The smaller matrix can "support" or "oppose" (have a different conclusion at 95 test value of the full input matrix. We count the number of times each cell supports or opposes the overall Chi-squared test. We also generate the possible list of sub-matrix.

Usage

generate.heatmap.matrix(mat, details = FALSE)

Arguments

mat	- matrix for which the sub-matrix is to be generated
details	- If this is set to TRUE, the the return value includes the full list of sub-matrix

Details

This can be used as an outlier detection method as well as observing the individual cells within an IxJ table

Value

A list with

Hot.df	Dataframe with the difference between the supporting matrix and the opposing matrix
Suport.df	Dataframe of the cell counts for support of table level Chi-sqaured
Oppose.df	Dataframe of the cell counts for opposing of table level Chi-sqaured
sub-matrix	list of sub-matrix - this is returned only if the details flag is set to TRUE

References

[1] Mosteller F, Parunak A (2006) Identifying extreme cells in a sizable contingency table: Probabilistic and exploratory approaches. In: Hoaglin DC, Mosteller F, Tukey JW (eds) Exploring Data Tables, Trends, and Shapes, John Wiley & Sons, pp 189-224

See Also

Other IxJ Inference methods: Local.Odds.Ratio, Nominal.Odds.Ratio, Plot.heatmap, Reversal.point, Subtable.Odds.Ratio

Examples

Drills=c(2,	10,	4,	2 ) # Example data from [reference 1]
Pots= c(3,	8,	4,	6)
Grinding.Stones=c( 13, 5, 3, 9)
Point.Fragments=c(20, 36, 19, 20)
mat=rbind(Drills,Pots,Grinding.Stones,Point.Fragments)
generate.heatmap.matrix(mat,details=FALSE)

RajeswaranV/vcdPlus documentation built on May 27, 2019, 7:28 a.m.