以湖南省黄丰桥国有林场103块样地共2461株杉木为例,建立单木冠幅模型。由于所调查数据是在不同立地条件下相同样地中重复观察得到,数据间存在明显相关性,为解决此问题,将考虑立地指数和样地对冠幅生长的随机影响,即建立嵌套2水平非线...以湖南省黄丰桥国有林场103块样地共2461株杉木为例,建立单木冠幅模型。由于所调查数据是在不同立地条件下相同样地中重复观察得到,数据间存在明显相关性,为解决此问题,将考虑立地指数和样地对冠幅生长的随机影响,即建立嵌套2水平非线性混合冠幅模型。从12个常用林分模型中选出较好的冠幅直径模型作为构建混合模型的基础模型。除胸高直径外,还考虑其他17个林分或树木因子对冠幅的影响。通过指标AIC(akaike information criterion)和对数似然确定最佳形式参数随机效应组合类型,用指数函数、幂函数以及常数加幂函数3种形式的残差方差模型消除异方差,最后对混合模型和传统回归模型进行比较及评价。结果表明:逻辑斯蒂形式的冠幅直径模型[模型(13)]拟合效果较好,选择为基础模型;胸径、冠底高、树高和样地优势高是影响冠幅的主要因子;幂函数消除异方差效果最好;与立地指数相比,立地指数与样地的嵌套效应对冠幅影响更大;模型(15)的嵌套2水平比总体平均水平和立地指数水平预测精度高,相比于模型(13)有明显改进。本文主要为方法研究,对于其他树种可以用相似方法构建冠幅模型。展开更多
In this paper, we prove the following two main results: i) Let M be a mixed foliate non-trivial CR Submanifold of a Sasakian space form M(c). If the (D,⊥D) is ξ-horizontal, then c≤1. ii) Let M be a mixed faliate ge...In this paper, we prove the following two main results: i) Let M be a mixed foliate non-trivial CR Submanifold of a Sasakian space form M(c). If the (D,⊥D) is ξ-horizontal, then c≤1. ii) Let M be a mixed faliate generic Submanifold of a Sasakian Space form M^(2m)+1(c). If the(D,⊥) is ξ-horizontal and the f-structure P oa M is paralIel, then M is an (m+l)-dimensional anti-invariant Submanifold of M^(2m+1(c) or, c=1.展开更多
Mukerjee and Wu（2001） employed projective geometry theory to find the wordlength pattern of a regular mixed factorial design in terms of its complementary set, but only for the numbers of words of length 3 or 4. In ...Mukerjee and Wu（2001） employed projective geometry theory to find the wordlength pattern of a regular mixed factorial design in terms of its complementary set, but only for the numbers of words of length 3 or 4. In this paper, by introducing a concept of consulting design and based on the connection between factorial design theory and coding theory, we obtain some combinatorial identities that relate the wordlength pattern of a regular mixed-level （2^r）2^n factorial design to that of its consulting design. Consequently, a general rule for identifying minimum aberration （2^r）2^n factorial designs through their consulting designs is established. It is an improvement and generalization of the related result in Mukerjee and Wu（2001）.展开更多
文摘以湖南省黄丰桥国有林场103块样地共2461株杉木为例,建立单木冠幅模型。由于所调查数据是在不同立地条件下相同样地中重复观察得到,数据间存在明显相关性,为解决此问题,将考虑立地指数和样地对冠幅生长的随机影响,即建立嵌套2水平非线性混合冠幅模型。从12个常用林分模型中选出较好的冠幅直径模型作为构建混合模型的基础模型。除胸高直径外,还考虑其他17个林分或树木因子对冠幅的影响。通过指标AIC(akaike information criterion)和对数似然确定最佳形式参数随机效应组合类型,用指数函数、幂函数以及常数加幂函数3种形式的残差方差模型消除异方差,最后对混合模型和传统回归模型进行比较及评价。结果表明:逻辑斯蒂形式的冠幅直径模型[模型(13)]拟合效果较好,选择为基础模型;胸径、冠底高、树高和样地优势高是影响冠幅的主要因子;幂函数消除异方差效果最好;与立地指数相比,立地指数与样地的嵌套效应对冠幅影响更大;模型(15)的嵌套2水平比总体平均水平和立地指数水平预测精度高,相比于模型(13)有明显改进。本文主要为方法研究,对于其他树种可以用相似方法构建冠幅模型。
文摘In this paper, we prove the following two main results: i) Let M be a mixed foliate non-trivial CR Submanifold of a Sasakian space form M(c). If the (D,⊥D) is ξ-horizontal, then c≤1. ii) Let M be a mixed faliate generic Submanifold of a Sasakian Space form M^(2m)+1(c). If the(D,⊥) is ξ-horizontal and the f-structure P oa M is paralIel, then M is an (m+l)-dimensional anti-invariant Submanifold of M^(2m+1(c) or, c=1.
文摘Mukerjee and Wu（2001） employed projective geometry theory to find the wordlength pattern of a regular mixed factorial design in terms of its complementary set, but only for the numbers of words of length 3 or 4. In this paper, by introducing a concept of consulting design and based on the connection between factorial design theory and coding theory, we obtain some combinatorial identities that relate the wordlength pattern of a regular mixed-level （2^r）2^n factorial design to that of its consulting design. Consequently, a general rule for identifying minimum aberration （2^r）2^n factorial designs through their consulting designs is established. It is an improvement and generalization of the related result in Mukerjee and Wu（2001）.
