Multimodel Inference

Sociological Methods and Research - Tập 33 Số 2 - Trang 261-304 - 2004
Kenneth P. Burnham, David R. Anderson1
1Colorado Cooperative Fish and Wildlife Research Unit (USGS-BRD)

Tóm tắt

The model selection literature has been generally poor at reflecting the deep foundations of the Akaike information criterion (AIC) and at making appropriate comparisons to the Bayesian information criterion (BIC). There is a clear philosophy, a sound criterion based in information theory, and a rigorous statistical foundation for AIC. AIC can be justified as Bayesian using a “savvy” prior on models that is a function of sample size and the number of model parameters. Furthermore, BIC can be derived as a non-Bayesian result. Therefore, arguments about using AIC versus BIC for model selection cannot be from a Bayes versus frequentist perspective. The philosophical context of what is assumed about reality, approximating models, and the intent of model-based inference should determine whether AIC or BIC is used. Various facets of such multimodel inference are presented here, particularly methods of model averaging.

Từ khóa


Tài liệu tham khảo

Akaike, Hirotugu, 1973, Second International Symposium on Information Theory, 267

10.1109/TAC.1974.1100705

10.1016/0304-4076(81)90071-3

Akaike, Hirotugu, 1983, International Statistical Institute, 44, 277

10.1007/978-1-4613-8560-8_1

10.1007/978-1-4612-0919-5_38

Akaike, Hirotugu, 1994, Engineering and Scientific Applications: Vol. 3. Proceedings of the First US/Japan Conference on the Frontiers of Statistical Modeling: An Informational Approach, 27

Andserson, David R., 2002, Journal of Wildlife Management, 66, 910

Azzalini, Adelchi, 1996, Statistical Inference Based on the Likelihood

Boltzmann, Ludwig, 1877, Wiener Berichte, 76, 373

10.1080/01621459.1992.10475276

Breiman, Leo, 2001, Statistical Science, 26, 199

10.2307/2533961

10.1007/978-1-4757-2917-7

Burnham, Kenneth P., 2002, Model Selection and Multimodel Inference: A Practical Information-Theoretical Approach, 2

10.1080/03610929908832282

Chamberlin, Thomas, 1890, Science, 148, 754, 10.1126/science.148.3671.754

10.1007/978-1-4612-0919-5_37

Edwards, AnthonyW. F., 1992, Likelihood, 10.56021/9780801844454

10.1006/jmps.1999.1284

Forster, Malcolm R., 2001, Simplicity, Inference and Modelling: Keeping It Sophisticatedly Simple, 83

10.1093/bjps/45.1.1

Gelfand, Alan, 1994, Journal of the Royal Statistical Society, Series B, 56, 501, 10.1111/j.2517-6161.1994.tb01996.x

10.1201/9780429258411

10.1198/0003130031423

10.1214/ss/1023798997

Hoeting, Jennifer A., 1999, ” Statistical Science, 14, 382

10.1093/biomet/76.2.297

10.2307/2533006

Johnson, Roger W., 1996, Journal of Statistics Education, 4

10.1080/01621459.1995.10476572

Key, Jane T., 1999, Bayesian Statistics 6, 343

10.1214/aoms/1177729694

Lahiri, Partha, 2001, Model Selection, 10.1214/lnms/1215540957

10.1214/ss/1177012164

Linhart, H., 1986, Model Selection

10.1142/3573

10.1198/016214502388618654

10.1007/978-1-4612-1694-0

10.2307/271063

10.1093/biomet/83.2.251

10.1080/03610929608831716

Royall, Richard M., 1997, Statistical Evidence: A Likelihood Paradigm

Stone, Mervyn, 1974, Journal of the Royal Statistical Society, Series B, 39, 111, 10.1111/j.2517-6161.1974.tb00994.x

Stone, Mervyn, 1977, Journal of the Royal Statistical Society, Series B, 39, 44, 10.1111/j.2517-6161.1977.tb01603.x

10.1214/aos/1176344136

Spiegelhalter, David J., 2002, Journal of the Royal Statistical Society, Series B, 64, 1, 10.1111/1467-9868.02022

10.1080/03610927808827599

Takeuchi, Kei, 1976, Suri-Kagaku (Mathematic Sciences), 153, 12

10.1006/jmps.1999.1278

10.1177/0049124199027003002

10.1017/CBO9781139164795

Thông tin
Thông tin xuất bản

Sociological Methods and Research

Tập 33 Số 2

261-304

Thông tin tác giả