# linearmodels.iv.results.IVResults.anderson_rubin¶

property IVResults.anderson_rubin: InvalidTestStatistic | WaldTestStatistic[source]

Anderson-Rubin test of overidentifying restrictions

Returns:
WaldTestStatistic

Object containing test statistic, p-value, distribution and null

Notes

The Anderson-Rubin test examines whether the value of $$\kappa$$ computed for the LIML estimator is sufficiently close to one to indicate the model is not overidentified. The test statistic is

$n \ln(\hat{\kappa}) \sim \chi^2_{q}$

where $$q = n_{instr} - n_{endog}$$.