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。
Finally, the precision of mixed models was compared with the precision of conventional nonlinear ordinary regression analysis method based on validation data.
模拟中选用了偏态的一阶自回归模型。
文章的研究基于数值模拟，采用三次样条曲线回归方法，推导出一套计算采动覆岩离层量大小的公式。
In this study, a suit of formula for mining overburden bed separation volume calculation was developed based on numerical simulation using cube shape curve regression method.
用幂函数模型描述的回归曲线以及根据试验参数得到模拟曲线与试验值比较误差均较小。
The errors of the data obtained using the power function model are very small from the test data.
运用MC模拟试验，建立了平均晶粒尺寸与蒙特卡罗步数之间的关系，利用回归分析方法确定了MC模型常数。
Through MC simulation test, the relation of average grain size and Monte Carlo steps was established and the parameters of MC model were work out by the method of regression analysis.
用幂函数模型描述的回归曲线以及根据试验参数得到模拟曲线与试验值比较误差均较小。
The errors are less as comparing the test data with regressive curve and simulative curve from test parameters using the power function model.
实例表明，在工艺优化设计和器件性能预测中用回归模型代替工艺-器件模拟具有较大的优越性。
The examples indicate that using regression model instead of process and device modelling is superior in process optimized design and device performance prediction.
对一般线性回归模型中有关参数估计分布的模拟问题，给出一种随机加权逼近的再构造方法。
A reconstructing method for random weighting approximations is proposed in approach to the distributions of the parameter estimates in general linear regression model.
利用模拟试验取得的数据，通过回归分析，拟合出不同场地条件下烟囱触地飞溅物距离的预测公式。
Through the regression analysis using the data from modeling tests, the formulae for predicting the spattering distances at different conditions of ground were fitted out.
利用已知的压缩因子分子动力学模拟数据，回归得到了这两个径向分布函数，从而建立了一个新的方阱流体状态方程。
The molecular dynamic data of compressibility factor are used to regress this two localized radial distribution functions. Therefore, a new equation of state of square well fluids is established.
模拟的结果显示ANN模型比线性回归模型有更好的预测能力，预测的平均相对误差：ANN模型为14.9%，线性回归模型为25.8%。
Simulation results showed that the ANN model gave better predictions than the regressive model. The average relative error of ANN was 14.9% and that of linear regression was 25.8%.
应用样本选择模型对模拟数据进行分析，并与传统线性回归模型进行比较。
The missing data were analysed with sample selection model and compared with traditional linear regression model.
利用装备战损模拟平台收集了大量的装备战损仿真数据，据此建立了各因素对于杀伤效果的一元回归方程；
A great deal of damage simulation data are collected based on the simulation platform and the unitary regression equation of damage effect for each factor is built.
运用回归分析，模拟出原生金矿化元素地球化学模型。利用变异性指数法确定了矿体原生晕垂向分带。
Element geochemistry model of the primary mineralization halo is simulated by regression analysis and vertical zoning of the ore body primary halo by variable index method.
广义回归神经网络（GRNN）和遗传算法（GA）都是在模拟人的生理活动进而提出的人工智能技术。
The generalized regression neural network(GRNN) and the genetic algorithm(GA) are regarded as the artificial intelligence techniques.
结果表明，用线性回归模型计算的左室射血分数、每搏量、心输出量在较低心率时模拟数值较为可信，在较高心率时每搏量模拟数值不可靠。
It showed that the simulation results of LVEF, SV and CO were reliable at a low heart rate with linear regression model, but unreliable at a high heart rate.
此系统利用了回归正交设计方法，可进行多变量变化的各种模拟试验；
This system utilizes the regression-orthogonal method, so it can be used for the multivariable simulation test.
通过多元线性回归建立了充型速度随真空度、模样密度、浇注温度、金属静压头变化的经验计算公式，并研究了该公式在充型过程数值模拟中的应用。
An empiric calculated formula of mold filling as a function of vacuum rate, pattern density, pouring temperature and metal static head was established through multiple regression.
通过实验获得的蠕变曲线和岩石参数，回归出了盐岩的蠕变本构方程，结果表明该方程能较好的模拟实验结果。
Through the creep characteristic curves and parameters, the creep constitutive equation of rock salt is regressed and agrees with the experiment result.
研究结果表明，优化回归得到的精对苯二甲酸结晶动力学方程能够较好地模拟PTA连续多级降压蒸发结晶过程。
The results show that the PTA crystallization kinetics parameters using optimization and regression can be utilized preferably to the modeling of purified terephthalic acid multistage crystallizer.
根据二次回归正交组合方法与油气藏射孔完井有限元模型进行了数值模拟试验的设计与计算。
According to the secondary regression in quadrature combined method, the design and computation of finite element numeric simulation were done.
建立屏山站日流量分期平稳自回归模型，并模拟了序列长度为5200年的日流量过程对该模型进行检验。
Divided period Stationary Autoregressive model for daily flow of Pingshan hydrological station is established in this paper. Daily flow procedure during 5200 years is simulated to test this model.
数值模拟结果和实际地震数据处理结果表明：自回归滑动平均（ARMA）模型比滑动平均（MA）模型具有参数节省、模型更为高效的特点；
The results of numeric simulation and real seismic data processing showed that the ARMA model was characterized by parameter-economic and high efficiency in comparison with MA model;
通过对五组分模拟汽油纯组分在PEG膜中的溶胀实验结果回归得到各组分在PEG膜中的吸附系数和扩散系数。
The adsorption coefficient and diffusion coefficient of pure component for five component simulated gasoline in PEG membrane can be regressed from sorption experiment.
同时应用数理统计、回归分析等数学方法及计算机技术进行量化和模拟处理，建立了相应的数学模型。
Simultaneity, the methods of numerical value calculating, regression analysis and computer embedded the studies too. Some mathematical models were established.
针对具有频繁场景切换的视频流，用马尔可夫链来模拟视频场景之间的切换，场景内部用自回归模型来建模。
For the frequently scene switching video traffic, it USES Markovian to simulate the switching among the scenes, and USES self-regression model to modeling inside the scene.
同时考虑样地的随机效应、观测数据的时间序列相关性及不同初植密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。
The precision of mixed model considering plot random effects, time series error autocorrelation and different plantation density at one time is better than that of ordinary regression analysis method.
本文应用带单位根的门限自回归模型，对我国1990年来以来通货膨胀率的动态路径进行了模拟分析。
The paper builds up a TAR model with unit root to make an analysis of China's inflation rate since 1990.
本文应用带单位根的门限自回归模型，对我国1990年来以来通货膨胀率的动态路径进行了模拟分析。
The paper builds up a TAR model with unit root to make an analysis of China's inflation rate since 1990.
应用推荐