The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
|
Activity Number:
|
249
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 1, 2011 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #303433 |
|
Title:
|
Using AIC on Transformed Data
|
|
Author(s):
|
Mark C. Otto*+
|
|
Companies:
|
Fish and Wildlife Service
|
|
Address:
|
2302 Lackawanna St, Adelphi,, 20783,
|
|
Keywords:
|
model fit ;
model selection
|
|
Abstract:
|
Akaike's Information Criterion (AIC) uses information theory to compare statistical models for the same data. AIC can be used to compare model s with that have different distributions or with regression variables that are not nested. AIC can also be used to compare models with different transformations. David Findley applied a transformation of variables to derive an AIC on the original scale for models on transformed data. The AICs differ only in their Jacobian of transformation. This calculation has been used on time series models in the Census Bureau's RegARIMA, time series and regression modeling program and is presented in G. Kitagawa's Introduction to Time Series Modeling but is not otherwise widely used. AIC for transformations can be used on regression and generalized linear models. We show its effectiveness on simulated and real data.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2011 program
|
2011 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.