Methodology for proper diagnosis of error process in cross section: If neither RSρ nor RSλ are significant, but robust tests (RSρ* RSλ*) are, then ignore the robust tests. When RSρ is more significant (lower p-value) than RSλ, and RSρ* is significant while RSλ* is not, then lag autocorrelation is most likely the correct error structure. When RSλ is more significant (lower p-value) than RSρ, and RSλ* is significant while RSρ* is not, then error autocorrelation is most likely the correct error structure. We find that RSρ is more significant then RSλ, as it has a larger test statistic value (and the same degrees of freedom). The same is also true of the robust tests, so we conclude that a lag process is more likely than an error process in these data.