Likelihood Ratio Test

The test statistic is:

$X^2=2(L{L}_u-L{L}_r)$

where:

$L{L}_u$ is the log-likelihood of the unrestricted model estimated using the Calibrated Weight,

$L{L}_r$ is the log-likelihood of the restricted model estimated using the Calibrated Weight,

$p\approx \mathrm{Pr}({\chi }_{k_u-k_r}^2\ge X^2)$, and

$k_u$ and $k_r$ are the number of parameters of the unrestricted and restricted models respectively.

See also

• Reading Tables and Interpreting Significance Tests
• Overview of Statistical Testing in Q