Log-linear Models

Log-Linear Models is a class of statistical models for categorical data that represent the logarithm of expected cell counts (or probabilities) in contingency tables as a linear function of parameters associated with the main effects and interactions of the categorical variables, typically treating all variables symmetrically without designating a single response variable.

1.1K

Publications

156.8K

Citations

1.6K

Authors

779

Institutions

Publications per year

2017–2026

124

Authors

1.6K

  1. AA
    Alan Agresti

    University of Florida, United States

    23 publications · 2.4K citations

    19

    h-index

  2. SJ
    Shelby J. Haberman

    Educational Testing Service, United States

    19 publications · 2.2K citations

    17

    h-index

  3. GM
    Gauss M. Cordeiro

    Universidade Federal de Pernambuco, Brazil

    12 publications · 315 citations

    11

    h-index

  4. AV
    Alexander von Eye

    Michigan State University, United States

    11 publications · 305 citations

    11

    h-index

  5. EM
    Edwin M. M. Ortega

    Universidade de São Paulo, Brazil

    12 publications · 330 citations

    11

    h-index

1–5 of 1.6K

Venues

  1. Journal of the American Statistical Association

    83 publications · 18.6K citations

    42

    h-index

  2. Biometrics

    43 publications · 4.6K citations

    30

    h-index

  3. Technometrics

    24 publications · 12.4K citations

    23

    h-index

  4. Biometrika

    31 publications · 2.5K citations

    23

    h-index

  5. Sociological Methods & Research

    SMR · 34 publications · 4K citations

    21

    h-index

1–5