主要内容

sbionlmefit

估计使用非线性混合效应Simbiologymodels (requires统计和机器学习工具箱software)

sbionlmefit将来的版本将被删除。利用sbiofitmixedinstead.

Syntax

results= sbionlmefit(modelObj,pkModelMapObject,pkdataObject,InitEstimates)
results= sbionlmefit(modelObj,pkModelMapObject,pkdataObject,CovModelObj)
results= sbionlmefit(...,名称,价值)
results= sbionlmefit(...,选项结构)
[results,Simdatai,simdatap] = sbionlmefit(...)

描述

results= sbionlmefit(modelObj,pkModelMapObject,pkdataObject,InitEstimates)performs nonlinear mixed-effects estimation using the SimBiology®model,modelObj,并回报估计的结果resultsstructure.

results= sbionlmefit(modelObj,pkModelMapObject,pkdataObject,CovModelObj)使用参数和协变量之间的关系CovModelObj, 一个CovariateModel目的。TheCovariateModelobject also provides the parameter transformation.

results= sbionlmefit(...,名称,价值)执行非线性混合效应估计,其中一个或多个指定的其他选项名称,价值配对参数。

Following is an alternative to the previous syntax:

results= sbionlmefit(...,选项结构)指定选项结构,一个包含字段和值的结构,是由名称值对参数接受的nlmefit。默认值选项结构are the same as the defaults for the arguments used bynlmefit,例外解释了输入参数

[results,Simdatai,simdatap] = sbionlmefit(...)返回Simbiology模型的仿真数据,modelObj,使用参数的估计值。

输入参数

modelObject

Simbiology模型对象用于拟合观察到的数据。

Note

如果使用包含活性剂量的模型对象(即包含使用剂量对象创建的剂量对象adddosemethod, and specified as active using the积极的剂量对象的属性)请注意,这些活性剂量被忽略sbionlmefit功能。

pkModelMapObject

pkmodelmapobject that defines the roles of the model components used for estimation. For details, seepkmodelmap目的。

Note

If using apkmodelmapobject that specifies multiple doses, ensure each element in theDosedproperty is unique.

pkdataObject

PKDataobject that defines the data to use in fitting, and the roles of the columns used for estimation.pkdataObject必须为至少两组定义目标数据。有关详细信息,请参阅PKData object

Note

对于属于单个组的数据的每个子集(如在数据列中定义的GroupLabel属性),该软件允许同时进行多次观察。如果您的数据是正确的,请注意:

  • These data points are not averaged, but fitted individually.

  • 不同时间的不同观测值会导致一些时间点加权。

InitEstimates

固定效应的初始估计值的向量。首先P要点InitEstimatescorrespond to the fixed effects for eachP元素pkModelMapObjectEstimated。其他元素对应于协变量因子的固定效应。首先P要点InitEstimates按照由paramtransformname-value pairs (log transformed by default).

CovModelObj

CovariateModel定义参数与协变量之间关系的对象。有关详细信息,请参阅CovariateModel object

Tip

要同时拟合来自多个剂量水平的数据,请省略随机效应(eta) from the expressions in theCovariateModel目的。

选项结构

包含字段和值th结构e name-value pairs accepted by thenlmefit功能。默认值选项结构are the same as the defaults for the arguments used bynlmefit, with the exceptions noted in名称值对参数

如果您具有并行计算Toolbox™,则可以通过设置名称值对参数启用并行计算,以使数据拟合更快拟合'UseParallel'to真的在里面Statset选项结构如下:

Parpool;%打开平行计算的Parpool opt = statset(...,'useParallear',true);%启用并行计算结果= sbionlmefit(...,'options',opt);%执行数据拟合

Tip

Simbiologysoftware includes theSBIOFITSTATUSPLOT功能,您可以在outputfcnfield of theOptions场地。此功能使您可以监视拟合状态。

Tip

要同时拟合来自多个剂量级别的数据,请使用InitEstimates输入参数并设置reparamsselectfield to a 1-by-nlogical vector, with all entries set tofalse, 在哪里n等于固定效果的数量。

Name-Value Arguments

将可选的参数对Name1=Value1,...,NameN=ValueN, 在哪里Name是the argument name and价值是相应的值。名称值参数必须在其他参数之后出现,但是对的顺序并不重要。

Before R2021a, use commas to separate each name and value, and encloseNamein quotes.

Thesbionlmefit函数使用姓名值对参数万博1manbetxnlmefit功能。

Thesenlmefitname-value pairs are hard-coded insbionlmefit, 和therefore, you cannot set them:

  • FEParamsSelect

  • FEConstDesign

  • FEGroupDesign

  • FEObsDesign

  • REConstDesign

  • REGroupDesign

  • REObsDesign

  • 矢量化

If you provide aCovariateModel对象作为输入sbionlmefit,然后这些nlmefitname-value pairs are computed from the covariate model, and therefore, you cannot set them:

  • FEGroupDesign

  • paramtransform

  • reparamsselect

You can set all othernlmefitname-value pairs. For details, see thenlmefit(Statistics and Machine Learning Toolbox)reference page.

Be aware that the defaults for thesenlmefit名称值对在使用时有所不同sbionlmefit:

FEGroupDesign

数字阵列为每个组指定设计矩阵。

Default:repmat(眼睛(P),[1 1 ngroups]), 在哪里P= the number of estimated parameters, andngroups= the number of groups in the observed data.

paramtransform

Vector of integers specifying how the parameters are distributed.

Note

Do not use theparamtransformoption to specify parameter transformations when providing aCovariateModelobject to a fitting function. TheCovariateModel对象提供参数转换。

Default:Vector of ones, which specifies all parameters are log transformed.

OptimFun

Character vector specifying the optimization function used in maximizing the likelihood.

Default:fminunc, if you have Optimization Toolbox™ installed. Otherwise, the default isfminsearch

Options

Structure containing multiple fields, includingDerivStep, 一个scalar or vector specifying the relative difference used in the finite difference gradient calculation, andFunValCheck, 一个logical specifying whether to check for invalid values, such asNaN或者inf, frommodelfun

Default:默认值DerivStep是the lesser of1e-4, or the value of the求解与之关联的配置集的属性modelObj,最少EPS^(1/3)。默认值FunValCheck离开

Tip

Simbiologysoftware includes theSBIOFITSTATUSPLOT功能,您可以在outputfcnfield of theOptions名称值对输入参数。此功能使您可以监视拟合状态。

Tip

要同时拟合来自多个剂量级别的数据,请使用InitEstimates输入参数并设置reparamsselectname-value pair input argument to a 1-by-nlogical vector, with all entries set tofalse, 在哪里n等于固定效果的数量。

Output Arguments

results

包含这些字段的结构:

  • FixedEffects- 一个dataset(Statistics and Machine Learning Toolbox)array containing estimated fixed effects, including standard errors.

  • randomeffects- 一个datasetarray containing sampled random effects for each group in the observed data inpkdataObject

  • 个人参数估计- 一个datasetarray containing estimated parameter values for individuals, including random effects.

  • 人群估计- 一个datasetarray containing estimated parameter values for the population, without random effects.

  • randomeffectcovariancematrix- 一个datasetarray containing the estimated covariance matrix of the random effects.

  • 估计的参数- 字符矢量的单元格数组指定估计参数的名称。

  • CovariateNames- 字符矢量的单元格数组,指定协变量的名称CovModelObj

  • FixedEffectsStruct- 包含估计固定效应值的结构。

  • stats- 包含信息的结构AIC,BIC, 和weighted residuals. For details on the fields in this structure, see thestatsstructure innlmefit(Statistics and Machine Learning Toolbox)在里面统计和机器学习工具箱™ documentation. However, the fields in thestats返回的结构sbionlmefit与返回的人略有不同nlmefit,即:

    • 国税局,总统,iwres,PWRES, 和cwres每一个标题都包含一个矩阵的生或加权residuals, with the number of columns equal to the number of responses in the model.

    • Thestats返回的结构sbionlmefitincludes an additional field,Observed。This field contains a character vector or cell array of character vectors specifying the measured responses that correspond to the columns in the matrices of the国税局,总统,iwres,PWRES, 和cwresfields. TheObservedfield is the same as theObserved属性pkmodelmap输入参数。

Simdatai

simdata对象包含使用个体的估计参数值模拟模型的数据。该对象包括观察到的状态和记录状态。

simdatap

simdata对象containing data from simulating the model using the estimated parameter values for the population. This object includes observed states and logged states.

Version History

Introduced in R2009a