Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
This note shows that for a spatial regression with equal weights, the LM test is always equal to NÂ /Â 2(NÂ -Â 1), where N is the sample size. This means that this test statistics is a function of N and not a function of the spatial parameter [rho]. In fact, this test statistic tends to one half for N tending to infinity. The null hypothesis of no spatial correlation is never rejected no matter what [rho] is.