Abstract
This paper derives Lagrange Multiplier tests based on double-length artificial regressions (DLR) for testing linear and log-linear regressions with AR(1) disturbances against Box-Cox alternatives. These DLR tests are easier to compute than the corresponding likelihood ratio tests, and are easily generalized to test jointly for functional form and serial correlation. Two illustrative examples are given to show the importance of jointly testing for functional form and serial correlation.
Original language | English (US) |
---|---|
Pages (from-to) | 199-209 |
Number of pages | 11 |
Journal | Statistical Papers |
Volume | 40 |
Issue number | 2 |
DOIs | |
State | Published - Apr 1999 |
Externally published | Yes |
Keywords
- Box-Cox transformation
- Double-Length Regressions
- Lagrange Multiplier
- Serial Correlation
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty