Answers are grounded in this paper and cite their sources.
One of the basic assumptions of Seemingly Unrelated Regression Equations (SURE) is the normality of error terms in the regressions model. This paper thus considers estimating SUR model when the normality assumption of the error term is violated. Small and asymptotic properties are examined using Ordinary Least Squares (OLS) and Feasible Generalized Least Squares (FGLS) estimators. The results revealed that the SUR estimator (FGLS) was diminishingly efficient as sample size increases with their standard errors converging at large sample size of 1000.
No takes yet. Share an insight, caveat, or question.
Emmanuel Idowu Olamide (2018) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: