学科分类
/ 1
1 个结果
  • 简介:Inthisstudy,thesampledatawasbasedon2190branchlengthandanglesamplesof30treesfromdahurianlarch(Larixgmeiinii)plantationslocatedinWuyingForestBureauinHeilongjiangProvince.Thestepwiseregressiontechniqueswereusedtodevelopbranchlengthandbranchanglemodels:BL=b1+b2DINC+b3DINC2+b4DBH·DINC2,BA=b1+b2DINC+b3DINC2+b4DBH·DINC.Then,thedevelopedmodelswerefittedusinglinearmixed-effectsmodelingapproachbasedonLMEprocedureofS-PLUSsoftware.Evaluationstatistics,suchasAIC,BIC,LogLikelihoodandLikelihoodratiotestwereusedformodelcomparisons.Theresultsshowedthatthebranchlengthandbranchanglemodelswithparametersb1,b2,b3asmixedeffectsshowedthebestperformance.Exponentialandpowerfunctionswereincorporatedintomixedbranchlengthandbranchanglemodel.Theadditionoftheexponentialandpowerfunctionssignificantlyimprovedthemixed-effectsmodel.Theplotsofstandardizedresidualsindicatedthatthemixed-effectmodelwithexponentialandpowerfunctionsshowedmorehomogeneousresidualvariancethanthemixed-effectsmodel.Validationconfirmedthatthemixedmodelwithcalibrationofrandomparameterscouldprovidemoreaccurateandpreciseprediction.Therefore,theapplicationofmixedmodelnotonlyshowedthemeantrendsofbranchlengthandbranchangle,butalsoshowedtheindividualdifferencebasedonvariance-covariancestructure.

  • 标签: branch LENGTH branch ANGLE LINEAR MIXED