关键词:
摘要: Based upon the idea of construction data driven smooth tests for composite hypotheses presented in Inglotet al.(1997) and Kallenberg Ledwina (1997), two versions test bivariate normality are proposed. Asymptotic null distributions derived, consistency newly introduced against every alternative with marginals having finite variances is proved. Included results power simulations show that one proposed performs very well comparison other commonly used normality.