api-parray function

Representation of and operations on multidimensional arrays

General representation of multidimensional arrays (with named dimnames, also called named arrays.)

parray(varNames, levels, values = 1, normalize = "none", smooth = 0)

as.parray(values, normalize = "none", smooth = 0)

data2parray(data, varNames = NULL, normalize = "none", smooth = 0)

makeDimNames(varNames, levels, sep = "")

Arguments

• varNames: Names of variables defining table; can be a right hand sided formula.
• levels: Either 1) a vector with number of levels of the factors in varNames or 2) a list with specification of the levels of the factors in varNames. See 'examples' below.
• values: Values to go into the array
• normalize: Either "none", "first" or "all". Should result be normalized, see 'Details' below.
• smooth: Should values be smoothed, see 'Details' below.
• data: Data to be coerced to a parray; can be data.frame, table, xtabs, matrix.
• sep: Desired separator in dim names; defaults to "".

Returns

A a named array.

Details

A named array object represents a table defined by a set of variables and their levels, together with the values of the table. E.g. f(a,b,c) can be a table with a,b,c representing levels of binary variable

If normalize="first" then for each configuration of all other variables than the first, the probabilities are normalized to sum to one. Thus f(a,b,c) becomes a conditional probability table of the form p(a|b,c).

If normalize="all" then the sum over all entries of f(a,b,c) is one.

If smooth is positive then smooth is added to values before normalization takes place.

Examples

t1 <- parray(c("gender","answer"), list(c('male','female'),c('yes','no')), values=1:4)
t1 <- parray(~gender:answer, list(c('male','female'),c('yes','no')), values=1:4)
t1 <- parray(~gender:answer, c(2,2), values=1:4)

t2 <- parray(c("answer","category"), list(c('yes','no'),c(1,2)), values=1:4+10)
t3 <- parray(c("category","foo"), c(2,2), values=1:4+100)

varNames(t1)
nLevels(t1)
valueLabels(t1)

## Create 1-dimensional vector with dim and dimnames
x1 <- 1:5
as.parray(x1)
x2 <- parray("x", levels=length(x1), values=x1)
dim(x2)
dimnames(x2)

## Matrix
x1 <- matrix(1:6, nrow=2)
as.parray(x1)
parray(~a:b, levels=dim(x1), values=x1)

## Extract parrays from data
## 1) a dataframe
data(cad1) 
data2parray(cad1, ~Sex:AngPec:AMI)
data2parray(cad1, c("Sex","AngPec","AMI"))
data2parray(cad1, c(1,2,3))
## 2) a table
data2parray(UCBAdmissions,c(1,2), normalize="first")

See Also

is.named.array

Author(s)

Søren Højsgaard, sorenh@math.aau.dk