棉花苗期棉蚜的二项式抽样设计及其精度分析

Binomial sampling plans and the sampling precision analysis for cotton aphid on vegetable stage

基于棉花苗期棉蚜 ( Aphis gossypii)的 2 4组调查数据 ,利用每样方虫口不超过数阈值 T(为 0 ,1,2 ,...,9,10 ,15,2 0 ,30 )头蚜虫的植株比例 ( PT)与种群密度 ( m,头 /株 )的关系 ,拟合经验关系式 ln( m) =a+bln[- ln( PT) ]设计二项式抽样。通过对不同数阈值 T的决定系数 ( r2 )、估计方差 ( Var( m) )和抽样精度 ( d估计 )等进行综合分析 ,结果表明该蚜虫在数阈值 T为 15时 ,估计方差最小 ,决定系数 r2和抽样精度 d值最大 ,因而 T=15为理想数阈值 ;当田间苗期棉蚜种群密度 m≥ 3时 ,T=15可用于二项式抽样设计。而传统的 0- 1抽样由于产生估计方差太大 ,r2和 d值最小即精度最低 ,因而不宜在实际中应用于棉蚜的二项式抽样设计。

Field sampling of cotton aphid, Aphis gossypii , on cotton vegetable stage was conducted in Quzhou, Hebei province in 1991. From the data, estimates of mean aphid density ( m ), variance ( s 2 ) and the proportion of plants ( P T ) with no more than T (=0,1,2,...,9,10,15,20 and 30, respectively) aphids, were calculated (where T is defined as the tally threshold). There were 24 estimates for Aphis gossypii population. The empirical relationship between m and P T was developed using the parameters estimated from the linear regression of ln( m ) on ln[-ln( P T )]. The determination coefficients, r 2, prediction variance of m from P T , Var(m), and the sampling precision, denoted as d , obtained with different T values were analysed. The results indicated that the optimal T for this aphid should be 10 when its population density is higher than 10 aphids per plant. The results also showed that the conventional binomial sampling (0-1) method produced unacceptable low levels of sampling precision and thus could not be used in sampling of cotton aphid on cotton vegetable stage.