共查询到18条相似文献，搜索用时 328 毫秒
1.
利用2种非线性混合效应模型(2水平)对杉木林胸径生长量的分析 总被引：4，自引：0，他引：4
选择2种2水平非线性混合模型对杉木林胸径生长量进行分析,其中模型1为一般的2水平非线性混合模型,模型2在模型1的基础上进一步考虑固定效应参数随某一特定因子水平变化而变化。本文通过对这2种模型的分析,首先确定构建2水平非线性混合模型的基础模型,然后对模型1衍生出的665种模型及模型2衍生出的2703种模型进行计算和比较:对于模型1,有57种模型计算收敛,当形参b0同时考虑区组和样地效应、而b4和b5只考虑区组效应时,模型拟合效果最好,因此把该模型作为模型1的最佳拟合模型;对于模型2,有24种模型计算收敛,当形参b5同时考虑区组和样地效应、b1只考虑区组效应并且固定效应b0的取值与各区组水平有关时,模型拟合效果最好,因此把该模型作为模型2的最佳拟合模型。最后对传统的非线性回归模型、模型1及模型2进行比较:模型1和模型2的拟合效果都比传统的非线性回归模型好,且模型2的拟合效果最好。 相似文献
2.
本文结合大样本的立木生物量实测数据,对非线性模型对数回归的偏差校正问题进行了探讨,并与加权回归结果进行了对比分析。首先,分析了对数回归产生偏差的内在原因,并提出了一个新的校正因子,同时对另外3个偏差校正因子一并进行了检验,结果表明本文和Baskerville(1972)提出的校正因子,能保证与加权回归估计结果趋于一致;然后,对非线性加权回归中基于普通回归残差推导的权函数与通用权函数(W＝1/f(x)2)的拟合效果进行了对比分析,结果表明二者基本相当,而通用权函数更具有广泛的适应性。建议对带有异方差的非线性模型,最好直接采用加权回归进行估计;当按照通用权函数进行估计其总相对误差超出一定范围时,应该根据普通回归估计的残差推导效果最佳的权函数后再进行加权回归。 相似文献
3.
以黑龙江省带岭林业局大青川林场80株人工兴安落叶松解析木数据为例,采用Richards生长模型作为基础模型,利用S-PLUS软件中的NLME过程,分别拟合非线性树高和直径生长模型。采用AIC、BIC、对数似然值和似然比检验等模型评价统计指标对不同模型的精度进行比较分析。结果表明:当对树高-年龄关系进行拟合时,b1、b3同时作为混合参数时模型拟合最好;当对直径-年龄关系进行拟合时,b1、b3同时作为混合参数时模型拟合最好。把相关性结构包括一阶自回归结构AR(1)、一阶移动平均结构MA(1)及一阶自回归与移动平均结构[ARMA(1,1)]加入到树高和直径最优混合模型中,一阶自回归结构AR(1)显著提高了树高混合模型的拟合精度,一阶移动平均结构MA(1)显著提高了直径混合模型的拟合精度。模型检验结果表明:混合模型通过校正随机参数值能提高模型的预测精度。因此,混合模型在应用上不但能反映树高和直径的平均预测趋势,还能用方差协方差结构和误差相关性结构校正随机参数来反映个体之间的差异。 相似文献
4.
基于计数模型方法的林分枯损研究 总被引：4，自引：0，他引：4
利用吉林省汪清林业局金沟岭林场落叶松林分连续观测数据,分别利用Poisson回归模型、负二项模型、零膨胀模型和Hurdle模型拟合林木枯损株数,并通过AIC值以及Vuong检验对这些模型进行详细分析比较。结果表明:Poisson回归模型不适用于模拟林木枯损株数,负二项回归模型相对于Poisson回归模型比较适用;但是对于零枯损过多的数据,这2类模型拟合效果较差。零膨胀模型和Hurdle模型对这类数据有很好的解决办法,其中,零膨胀负二项模型和Hurdle-NB模型拟合效果优于其他几种模型,且Hurdle-NB模型略好于零膨胀负二项模型。 相似文献
5.
利用吉林省汪清林业局金沟岭林场落叶松林分连续观测数据,以计数类模型为基础,分别利用Poisson回归模型、负二项模型、零膨胀模型和Hurdle模型拟合林木进界株数,并通过AIC值,Pearson残差图以及Vuong检验对这些模型进行了详细分析比较.结果表明:Poisson回归模型不适用于模拟林木枯损株数;负二项回归模型相对于Poisson回归模型比较适用,但是对于零枯损过多的数据,这两类模型拟合效果较差;零膨胀模型和Hurdle模型对这类数据有很好的解决办法,而且,零膨胀负二项模型拟合效果最好. 相似文献
6.
以黑龙江省七台河市林业局金沙林场9株人工落叶松2 790个样品数据为例,选择6个常用方程进行非线性回归分析,把拟合精度最高的修正Logistic模型作为微纤丝角基础模型y=b1/[1+ exp(b2x)]+b3,然后,利用S-PLUS软件中的NLME过程,拟合非线性微纤丝角模型.采用AIC、BIC、对数似然值和似然比检验等模型评价统计指标对不同模型的精度进行比较分析.结果表明:当对微纤丝角-年龄关系进行拟合时,b1,b2,b3同时作为混合参数时模型拟合效果最好.把相关性结构包括复合对称结构(CS)、一阶自回归结构AR(1)、一阶移动平均结构MA(1)及一阶自回归与移动平均结构[ARMA(1,1)]加入到微纤丝角最优混合模型中,一阶自回归与移动平均模型[ ARMA(1,1)]显著提高了微纤丝角混合模型的拟合精度.模型检验结果表明:混合模型通过校正随机参数值能提高模型的预测精度.因此,混合模型在应用上不仅能反映总体微纤丝角预测,而且能通过方差协方差结构和误差相关性结构校正随机参数来反映个体微纤丝角差异. 相似文献
7.
8.
《林业科学》2021,57(5)
【目的】构建树冠最大外部轮廓非线性混合效应模型和非线性分位数回归模型,为准确预测树冠生长发育规律及预估生产力提供科学依据。【方法】以河北省塞罕坝机械林场华北落叶松人工林为研究对象,基于58株解析木数据和1 789个枝条解析数据,利用幂函数、修正Kozak方程、修正Weibull方程选取基础模型,构建华北落叶松人工林树冠外部轮廓非线性混合效应模型和非线性分位数回归模型。【结果】在幂函数、修正Kozak方程和修正Weibull方程中,幂函数拟合树冠外部轮廓效果较好,作为树冠外部轮廓基础模型;林分年龄(Age)、冠长(CL)、胸径(DBH)、树高(HT)、冠高比(CHR)、高径比(HDR)对树冠外部轮廓影响较大。在混合效应模型中,两水平混合效应模型优于单水平混合效应模型,可明显提高模型拟合精度,HDR相关的参数a6考虑样地效应,相对着枝深度(RDINC)、CHR相关的参数a4、a5考虑样木效应,模型确定系数(R2)为0.873,均方根误差(RMSE)为0.319 m,平均相对误差(MRE)为6.642 m。在分位数回归模型中,当分位数q=0.90时模型曲线最接近树冠最大外部轮廓,R2为0.672。【结论】混合效应模型拟合精度较高,可准确描述树冠最大枝条的平均趋势。分位数回归模型可确定树冠最外部轮廓,在预测条件均值之外的研究中发挥重要作用。 相似文献
9.
10.
基于非线性混合模型的落叶松云冷杉林分断面积模型 总被引：7，自引：0，他引：7
以吉林省汪清林业局金沟岭林场20块落叶松云冷杉样地为研究对象.首先选择传统的回归方法从4个常用的断面积模型中找出模拟精度最高的模型作为基础模型,利用基础模型及模拟数据构建非线性混合模型,考虑样地效应,采用SAS软件进行模拟,选择模型收敛及其对数似然值、AIC和BIC值最小的混合模型作为最优模型;然后,在此基础上考虑断面积连续观测数据的时间序列相关性,并把间伐强度以哑变量形式考虑进去,再进行混合模型的模拟;最后,利用验证数据对混合模型方法与传统的非线性回归模拟方法进行精度比较.结果表明:林分密度指数作为自变量的Schumacher式的模拟精度最高,而考虑样地效应的混合模型模拟精度优于传统的回归模型方法;一阶自回归误差结构矩阵模型在解释断面积的时间序列相关性时不仅提高了混合模型的模拟精度,而且能够很好地表达连续观测数据问误差分布情况;同时考虑样地的随机效应、观测数据的时间序列相关性及间伐强度的混合模型模拟精度比传统的非线性回归方法模拟精度高. 相似文献
11.
Nonlinear mixed effects model（NLMEM） is based on the relationship between the fixed and random effects in the regression function.The NLMEM has a competitive advantage in analyzing repeated measures data,the longitudinal data and multilevel data.This paper chose two kinds of two-level nonlinear mixed model to analyze basal area growth for Chinese Fir（Cunninghamia lanceolata）. Model 1 is a general two-level NLMEM and Model 2 is based on Model 1 to further consider the fixed effects parameters changes with a specific factor. Firstly,through the analysis of these two models, this paper defined the basic model to build the two-level NLMEM.Secondly,665 kinds of models derived from Model 1 and 2 703 kinds of models derived from Model 2 were calculated and compared. The results showed that:for Model 1,there were 57 kinds of models converging,and when the formal parameter b0 considered the block effects and plot effects,b1 and b4 only considered the block effects, the model fitted the best;and for Model 2,there were 24 kinds of model converging,and when the formal parameter bs considered the block effects and plot effects,b1 only considered block effects and the fixed effects b0 changed with any level of block level, Model 2 fitted the best.Finally,by comparing the traditional nonlinear regression model,Model 1 and Model 2,the results showed that Model 1 and Model 2 fitted better than the traditional nonlinear regression, and Model 2 was best fitting model. 相似文献
12.
The varying (local) parameter(s) in site index models can be treated as fixed or random. Two primary subject-specific approaches to height modeling, the dummy variable method (fixed individual effects) and the mixed model method (random individual effects), were compared using Chapman–Richards type models fitted to second-rotation loblolly pine (Pinus taeda L.) data from a designed experiment. For height prediction of new growth series, tested on our validation subset data, the mixed model provides a new (local) parameter prediction method (termed as mixed predictor), which generally performed better than the traditional method of recovering local parameters (the least squares (LS) predictor we used). However, using the LS predictor, both the dummy variable estimation method and mixed model estimation showed almost identical prediction results. With multiple pairs of height–age measurements, no big difference was found in empirical site index prediction between the LS and mixed predictor. Theoretically, one main advantage of the mixed model approach is the ability of its mixed predictor to predict several local parameters using a single height–age pair. However, our empirical results failed to support this point. 相似文献
13.
Nonparametric modelling has been popular in recent forestry applications. However, nonparametric modelling methods usually assume independent observations, that is, do not acknowledge the spatial relationships of most forest data sets. For these situations, mixed model and kriging approaches have been used. The aim of this paper was to compare accuracy of spatial parametric and nonparametric approaches, namely mixed models and a combination of k-nn method and mixed models, in prediction of tree height. The spatial approaches were compared to a nonspatial parametric model and k-nn method. Tree height was first modelled using either mixed model or k-nn. The residual error was divided into plot and tree effects. A nonspatial prediction was obtained using the fixed part of the models. The spatial prediction was obtained when this prediction was further adjusted using the estimates of within-plot correlation of errors and best linear predictor. The influence of the quality of modelling data was also considered. The adjustment of nonspatial estimates of both parametric and nonparametric approaches markedly improved the predictions in all study cases. For many applications, the combination of the nonparametric k-nn method for the fixed component of the model, along with random effects for spatial correlations to create a mixed model, could be used. This would allow for spatial prediction, which would likely provide improved predictions, as shown for predicting height in this paper. Also, there is the added benefit that the nonparametric k-nn does not require a particular model form. 相似文献
14.
基于混合效应模型的杉木人工林蓄积联立方程系统 总被引：1，自引：0，他引：1
建立江西杉木人工林基于非线性混合效应方法的林分优势木平均高和断面积模型以及基于对数形式线性混合效应蓄积模型的联立方程组,利用验证数据与传统模型回归方法的模拟结果进行比较分析。结果表明,优势木平均高是联立方程组最基本的组成部分。通过考虑优势木平均高和林分断面积模型中参数的随机效应以及3个因变量间的相关性,则蓄积模型中参数的随机效应可以忽略。优势木平均高决定着林分断面积预测的准确性,而优势木平均高和林分断面积又是预测蓄积的主要误差来源。基于混合效应模型方法的模拟结果明显好于传统回归估计方法。进行预测时,通过解释联立方程组中因变量相互间的相关性,利用已被观测的变量能够提高未观测变量的估计精度。 相似文献
15.
Felipe Crecente-Campo Margarida Tomé Paula Soares Ulises Diéguez-Aranda 《Forest Ecology and Management》2010
A generalized height–diameter model was developed for Eucalyptus globulus Labill. stands in Galicia (northwestern Spain). The study involved a variety of pure stands ranging from even-aged to uneven-aged. Data were obtained from permanent circular sample plots in which trees were sampled within different radii according to their diameter at breast height. A combination of weighted regression, to take into account the unequal selection probabilities of such an inventory design, and mixed model techniques, to accommodate local random fluctuations in the height–diameter relationship, were applied to estimate fixed and random parameters for several models reported in the relevant literature. The models that provided the best results included dominant height and dominant diameter as fixed effects. These models explained more than 83% of the observed variability, with mean errors of less than 2.5 m. Random parameters for particular plots were estimated with different tree selection options. Height–diameter relationships tailored to individual plots can be obtained by calibration of the height measurements of the three smallest trees in a plot. An independent dataset was used to test the performance of the model with data not used in the fitting process, and to demonstrate the advantages of calibrating the mixed-effects model. 相似文献
16.
基于两层次线性混合效应模型的杉木林单木胸径生长量模型 总被引：8，自引：0，他引：8
基于两层次线性混合效应模型方法,建立江西省杉木人工林单木胸径生长量模型.研究所用数据来自于长期观测的固定样地数据,数据库包括82个区域、365个样地、5416株树木共计16248条记录.为了解决不同区域及不同样地之间的差异,本文构建的混合模型分别考虑样地层次、区域层次及两层次的随机参数效应.针对数据存在的重复测量及嵌套结构特性,在模拟时选择合适的异方差和自相关模型矩阵来解决此类问题.最后利用独立的抽样验证数据对模拟结果进行验证.结果表明:林分断面积、对象木胸径、林分内大于对象木的断面积之和与对象木胸径的比值以及海拔对单木胸径生长量有显著影响.与林业中常用的传统最小二乘方法相比,采用混合效应模型方法后模型的模拟精度和验证精度均有提高.选择适合的异方差和自相关函数后,模型比只考虑参数的随机效应有更好的适应性,并体现出了混合效应模型的灵活性和准确性. 相似文献
17.
Using historical growth series data of Scots pine (Pinus sylvestris L.) in Central Europe we examine all the dynamic site equations previously used for modeling the height growth of this species as well as a new dynamic site equation that has not been used previously in the context of this forestry data. The tested models included two groups of anamorphic and polymorphic dynamic site equations (three-dimensional site–height–age models, such as Y = f(t,t0,y0)). One group of the models is based on the algebraic difference approach (ADA) implementation of different, preexisting base equations (two-dimensional equations, such as Y = f(t)). The other group of models is based on newer generalized algebraic difference approach (GADA) formulations of new site–height–age relationships that may use older models only as a part of their structure. The models were selected because they were relevant to Scots pine height growth modeling in other studies. We compared all the models with each other in terms of the sum of square deviations associated with fitting them simultaneously to all sites represented by the Scots pine data. All the fits were based on base-age invariant stochastic regressions, in which the global model parameters that are common to all growth series are estimated simultaneously with the site-specific effects that are different for each of the site productivity series. Cieszewski's model [Cieszewski, C.J., 2005. A new flexible GADA based dynamic site equation with polymorphism and variable asymptotes. PMRC Technical Report 2005-2] best described the data. 相似文献
18.
对农户林地流转意愿与行为及影响因素的计量研究文献进行定量分析, 以探析该领域研究特征, 为今后的研究提供方法和视角选择等方面的参考。文中构建了理论分析框架, 并通过投票计数法汇总了10个农户林地转入意愿与行为和11个农户林地转出意愿与行为的计量回归模型信息, 以及不同模型选择的影响因素变量及分析结果。建议在现有大量使用Probit和Logit模型的基础上, 拓展使用时序、混合截面和面板数据模型; 合理选择家庭特征因素、市场驱动因素类变量和森林经营类变量, 并关注不同变量分析结果的冲突; 将研究区域从福建、江西、辽宁、浙江、云南等改革先行开展省份拓展到其他省份。 相似文献