作者: Washington Martins Silva , Osvaldo Candido
关键词: Normal distribution 、 Regression analysis 、 Copula (probability theory) 、 Common value auction 、 Electric power transmission 、 Joint probability distribution 、 Normality 、 Selection bias 、 Computer science 、 Econometrics
摘要: This paper aims to assess all the Brazilian electric power transmission line auctions occurred between 1999 and 2017.,A copula-based Roy/endogenous switching regression model is used. The suitability of this twofold: it takes into account selection bias problem involving data allows more flexibility in modeling joint distribution unobserved components outcome equations; thus, normal assumptions are not needed.,The main results suggest that stated-owned companies have highest probability winning an auction, there a non-competitive behavior among players auction. also some departure from normality data.,The sample approach used consistent under non-normality one address different types nonlinearities such as asymmetry heavy tails.