Fetching the paper…

Reading the bibliography…

2007

The Residual Information Criterion, Corrected

Leng, Chenlei

Original
PDF
Post on X

Understand

Shi and Tsai (JRSSB, 2002) proposed an interesting residual information criterion (RIC) for model selection in regression.

Their RIC was motivated by the principle of minimizing the Kullback-Leibler discrepancy between the residual likelihoods of the true and candidate model.
We show, however, under this principle, RIC would always choose the full (saturated) model.
The residual likelihood therefore, is not appropriate as a discrepancy measure in defining information criterion.

The Residual Information Criterion, Corrected · Around

Built on

Regression model selection-a residual likelihood approach
Original
Shi, P. and Tsai, C.-L. (2002) · 1918
Earlier work this paper cites.
Statistical predictor identification
Akaike, H. (1970) · 1970
Earlier work this paper cites.
Bayesian inference for variance components using only error contrasts
Harville, D.A. (1974) · 1974
Earlier work this paper cites.

Similar

Estimating the dimension of a model
Scharwz, G. (1978) · 1978
Cited alongside, same era.
Regression and time series model selection in small samples
Hurvich, C. M., and Tsai, C.-L. (1989) · 1989
Cited alongside, same era.
An asymptotic theory for linear model selection (with discussion)
Shao, J. (1997) · 1997
Cited alongside, same era.

Then

Analysis of longitudinal data. (2nd edition)
Diggle, P.J., Heagerty, P.J., Liang, K.-Y. and Zeger, S.L. (2002) · 2002
Later among the works it cites.
A note on shrinkage sliced inverse regression
Ni, L., Cook, R. D., and Tsai, C-L. (2005) · 2005
Later among the works it cites.
Longitudinal data model selection
Azari, R., Li, L., and Tsai, C.-L. (2006) · 2006
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…