Configural Frequencies Analysis Using Log-Linear Modeling

Offers several functions for Configural Frequencies Analysis (CFA), which is a useful statistical tool for the analysis of multiway contingency tables. CFA was introduced by G. A. Lienert as 'Konfigurations Frequenz Analyse - KFA'. Lienert, G. A. (1971). Die Konfigurationsfrequenzanalyse: I. Ein neuer Weg zu Typen und Syndromen. Zeitschrift für Klinische Psychologie und Psychotherapie, 19(2), 99–115.


News

Changes in Version 1.5.4-3

o introduced sequential alpha correction according to Bonferroni-Holm in summary function summary.CFA()

o fixed internal issue regarding the argument 'form' when defining a designmatrix

Changes in Version 1.5.3

o fixed some minor internal issues regarding the argument 'form' in main function 'CFA()' to maintain downward compatibility with earlier versions of confreq.

Changes in Version 1.5.0

o added the arguments 'blank' and 'cova' to extend the function CFA() introducing covariate analysis.

o added function 'dat2cov'.

o extended the argument 'blank' as a convenient option to perform functional CFA.

Changes in Version 1.4.1

o fixed some typing errors in descriptions for functions.

Changes in Version 1.4

o added import of functions from default packages, as required by the new CRAN-check.

o added the argument 'showall' in summary function for objects of class c("CFA","list").

o changed the numerical precision in calculation of the binomial test to avoid '-Inf' of 'Inf' results Under some data conditions.

o added the function expected_margin_cfa() for calculating expected counts based on margins with sparse tables.

o added the arguments 'method' and 'blank' to extend the function CFA() when using functional CFA with sparse tables.

Changes in Version 1.3-1

o added the Type index (b) for functional CFA in the summary method for object returned by function CFA().

o added a sorting option in summary method for object returned by function CFA().

o added information on function call in result of function CFA() and summary method.

o changed the internal function 'binomial_test_cfa' to avoid NaN 'values' for the (exact) binomial test under some sparse data situations.

Changes in Version 1.3

o added Information Theoretic Criteria (AIC, BIC) to the output of the main function CFA.

o extended the argument 'form' in main function CFA.

o added another data example (Lienert1978) used in the textbook by Mark Stemmler.

o added the function 'S2CFA' for two-sample-CFA and the respective summary S3 method for the result objects of class 'S2CFA'.

o due to numerical challenges in function 'S2CFA' when calculating factorials with big numbers, the package 'confreq' now has a depends on the package 'gmp'.

Changes in Version 1.2

o added another data example (newborns) taken from the textbook by Mark Stemmler.

o added the Likelihood Ratio Chi-square statistic.

o added a summary S3 method for the result objects of class 'CFA'.

Changes in Version 1.1

o fixed a bug in function dat2fre() .

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("confreq")

1.5.5-2 by Joerg-Henrik Heine, 15 days ago


Browse source code at https://github.com/cran/confreq


Authors: Joerg-Henrik Heine , R.W. Alexandrowicz (function stirling_cfa() ) and some package testing by Mark Stemmler


Documentation:   PDF Manual  


GPL-3 license


Depends on stats, gmp, methods


See at CRAN