1
عمومی::
کمترین توانهای دوم عادی
The econometric reasons are rooted in the inadequacies of traditional linear modelling (and the associated estimate using the Ordinary Least Squares -OLS- method) when the assumptions necessary for its implementation are no longer valid.
This dependency in the observations may either impair the OLS method (the estimators will be without bias but less precise, and the tests will no longer have the usual statistical properties), or produce biased estimators.
Let consider the case where, from the residuals of the OLS model, the Lagrange multiplier tests (LMr and LMl ) 5 it is concluded that there is an autoregressive term, i.e.r = 0 and l = 0 (left branch of Figure 6.1).
Likelihood ratio testing makes it possible to choose between the OLS, SLX and SDM models.
This indicator can be interpreted in a way similar to that of the b coefficients of a non-spatial linear model calculated using the OLS method.
واژگان شبکه مترجمین ایران