摘要
本文以vonBertalanffy鱼类体长生长方程为模型,对12个不同鱼类群体的参数统计量分别作1000次模拟,进一步采用HotellingT2检验及似然比检验两种方法对原始参数统计量与模拟参数估计量一一作比较.似然比检验结果表明,两种估计量的差异几乎皆不显著;而HotellingT2检验结果却与鱼类群体的样本含量有关:随着样本含量的增多,差异不显著的次数逐渐减少.因此,在比较不同的vonBertalanffy鱼类体长生长方程时,不宜应用HotellingT2检验方法.
Using the von Bertalanffy's fish length growth equation as the model, 1000 groups of parameter estimators are simulated for 12 different fish stocks. The methods of Hotelling T2 test and likelyhood ratio test are then used for comparison on the original and simulated estimators. The results of the likelyhood ratio test show that there is hardly any difference in parameters between original estimators and the simulated ones, while the results of Hotelling T2 test are related to the sample size, i. e., with the increase of sample size, the number of non-signification is gradually decreasing. Thus, it is advisable not to apply the method of Hotelling T2 in the comparison between different von Bertalanffy's fish length growth equations.
出处
《汕头大学学报(自然科学版)》
1994年第2期10-14,共5页
Journal of Shantou University:Natural Science Edition
关键词
鱼类
体长
生长方程
参数估计
von Bertalanffy's fish length growth equation
parameter estimation
simulation study
Hotelling T ̄2 test
likelyhood ratio test