hcfa {cfa}

Hierachical analysis of configuration frequencies

Description

Recursively eliminates one variable in the configuration to generate all possible sub-tables and performs a global chi-squared-test on them

Usage

hcfa(configs, cnts)

Arguments

configs

Contains the configurations. This can be a dataframe or a matrix. The dataframe can contain numbers, characters, factors or booleans. The matrix can consist of numbers, characters or booleans (factors are implicitely re-converted to numerical levels). There must be >=3 columns.

cnts

Contains the counts for the configuration. If it is set to NA, a count of one is assumed for every row. This allows untabulated data to be processed. cnts can be a vector or a matrix/dataframe with >=2 columns.

Details

The hierarchical CFA assists in the selection of configuration variables by showing which variables contribute the most to the variability. If eliminating a variable does not markedly decrease the global chi squared the variable is likely to be redundant, provided there are no extraneous reasons for retaining it.

The output is in decreasing order of chi squared so the most useful combinations of variables come first.

Value

chisq

Global chi squared

df

Degrees of freedom for this subtable

order

Order (number of configuration variables)

Note

The p for the test of significance ist provided by the print method

Author(s)

Stefan Funke <[e-mail]>

References

Lautsch, E., von Weber S. (1995) Methoden und Anwendungen der Konfigurationsfrequenzanalyse in Psychologie und Medizin, Beltz Psychologie Verlagsunion

See Also

cfa, scfa, mcfa

Examples

# library(cfa) if not yet loaded
# Some random configurations:
configs<-cbind(c("A","B")[rbinom(250,1,0.3)+1],
c("C","D")[rbinom(250,1,0.1)+1],
c("E","F")[rbinom(250,1,0.3)+1],c("G","H")[rbinom(250,1,0.1)+1])
counts<-trunc(runif(250)*10)
hcfa(configs,counts)