BazEkon - The Main Library of the Cracow University of Economics

BazEkon home page

Main menu

Brzezińska Justyna (The Karol Adamiecki University of Economics in Katowice, Poland)
Hierarchical Log-linear Models for Contingency Tables
Hierarchiczne modele logarytmiczno-liniowe dla tablic kontyngencji
Acta Universitatis Lodziensis. Folia Oeconomica, 2012, t. 269, s. 123-129, bibliogr. 14 poz.
Issue title
Multivariate Statistical Analysis : Methodological Aspects and Applications
Modele logarytmiczno-liniowe, Analiza statystyczna, Analiza danych, Analiza wielokryterialna
Log-linear models, Statistical analysis, Data analysis, Multicriteria analysis
summ., streszcz.
Hierarchiczne modele logarytmiczno-liniowe służą do analizy struktury zależności zmiennych w postaci tablicy kontyngencji. Modele budowane według zasady hierarchiczności są modelami hierarchicznymi. Do modeli tych zaliczany jest model pełny, model niezależności homogenicznej, model niezależności warunkowej oraz model niezależności całkowitej. Do kryteriów wyboru modelu należą: współczynnik największej wiarygodności, kryterium informacyjne AIC oraz BIC. Analiza logarytmiczno-liniowa w programie R możliwa jest dzięki funkcji loglm () z pakietu MASS oraz funkcji glm z pakietu stats. (abstrakt oryginalny)

Log-linear models are widely used for qualitative data in multidimensional contingency tables. Hierarchical log-linear models are models that include all lower-order terms composed from variables contained in a higher-order model term. The starting point is a saturated model, then homogenous associations, conditional independence and complete independence. There are several statistics that help to choose the best model. The first is the likelihood ratio approach, next is AIC and BIC information criteria. In R software there is loglm () function in MASS library and glm in stats library. The first approach is presented in this paper. (original abstract)
The Main Library of the Cracow University of Economics
The Library of Warsaw School of Economics
The Library of University of Economics in Katowice
The Main Library of Poznań University of Economics and Business
The Main Library of the Wroclaw University of Economics
Full text
  1. Agresti A. (2002), Categorical Data Analysis, Wiley & Sons, Hoboken, New Jersey.
  2. Akaike H. (1987), Factor Analysis and AIC Psychometrika, 52.
  3. Bartlet M. S., (1935), Contingency table interactions, in: Journal of the Royal Statistical Society, Supplement 2.
  4. Birch M. W. (1963), Maximum likelihood in three-way contingency tables, in: Journal of the Statistical Society, Series B, 25.
  5. Bishop Y. M. M., Fienberg E. F., Holland P. W. (1975), Discrete Multivariate Analysis, MIT Press, Cambridge, Massachusetts.
  6. Christensen R. (1997) Log-Linear Models and Logistic Regression, Springer-Verlag, New York.
  7. Darroch J. N. (1963), Interactions in multi-factor contingency tables, in: Journal of the Royal Statistical Society, Series B, 24.
  8. Goodman L. (1970), The Multivariate Analysis of Qualitative Data: Interaction among Multiple Classifications, in: Journal of the American Statistical Association, 65.
  9. Knoke D., Burke P. J. (1980), Log-linear Models, Quantitative Applications in the Social Science", nr 20, Sage University Papers, Sage Publications, Newbury Park, London, New Delhi.
  10. Mair P. (2006), Interpreting Standard and Nonstandard Log-linear Models, Waxmann Verlag, Minister.
  11. Raftery A. E. (1986), A note on Bayesian Factors for log-linear contingency table models with vague prior information, Journal of the Royal Statistical Society, Ser. B, 48.
  12. Reynolds H. T. (1977), Analysis of Nominal Data, Beverly Hills, CA: Sage.
  13. Roy S. N., Kastenbaum M. A. (1956), On the hypothesis of no interaction in a multiway contingency table, in: The Annals of Mathematical Statistics, 27.
  14. Venables, W. N., Ripley, B. D. (1999), Modern Applied Statistics with S-PLUS, Third Edition, Springer.
Cited by
Share on Facebook Share on Twitter Share on Google+ Share on Pinterest Share on LinkedIn Wyślij znajomemu