第六讲 计量经济学ppt课件.ppt

《第六讲 计量经济学ppt课件.ppt》由会员上传分享，免费在线阅读，更多相关内容在教育资源-天天文库。

1、MultipleRegressionAnalysis多元回归分析y=b0+b1x1+b2x2+...bkxk+u4.FurtherIssues进一步的问题1IntermediateEconometrics,YanShenChapterOutline本章大纲EffectsofDataScalingonOLSStatistics数据的测度单位换算对OLS统计量的影响MoreonFunctionalForm对函数形式的进一步讨论MoreonGoodness-of-FitandSelectionofRegressors拟合优度和回归元选择的进一步探讨PredictionandResidual

2、Analysis预测和残差分析2IntermediateEconometrics,YanShenLectureNotes课堂笔记EffectsofRedefiningvariables重新定义变量的影响Estimatedcoefficients估计系数RsquaredR平方tstatisticst统计量Functionalform函数形式Logarithmicform对数函数形式ModelswithQuadratics含二次式的模型Modelswithinteractionterms含交叉项的模型3IntermediateEconometrics,YanShenRedefiningV

3、ariables重新定义变量Whywouldwewanttodoso?为什么我们想这样做？Often,datascalingisusedtoreducethenumberofzerosafteradecimalpointinanestimatedcoefficient,sothattheresultsappearprettier.数据测度单位变换经常被用于减少被估参数小数点后的零的个数，这样结果更好看一些。Sincethisismainlyanactionofdecoration,weexpectnothingessentialshouldchange.既然这样做主要为了好看，我们希

4、望本质的东西不改变。4IntermediateEconometrics,YanShenRedefiningVariables:Anexample重新定义变量：一个例子Consideramodelrelatinginfantbirthweighttocigarettesmokingandfamilyincome:以下模型反映了婴儿出生体重与孕妇吸烟量和家庭收入之间的关系：(1)Considerthefollowingrescaling:考虑如下单位变换：(2)Birthweightischangedfromouncestopounds出生体重单位由盎司变为磅(3)Numberofcig

5、arettesischangedtopacksofcigrattes香烟的支数变为包数Theestimationresultsispresentedinthefollowingtable.估计结果列于下表5IntermediateEconometrics,YanShenTable6.1Y(column)(1)bwght(2)bwghtlbs(3)bwghtX(rows)Cigs-0.4634(0.0916)-0.0289(0.0057)--Packs-----9.268(1.832)Faminc0.0927(0.0292)0.0058(0.0018)0.0927(0.0292)Int

6、ercept116.794(1.049)7.3109(0.0656)116.974(1.049)Observations138813881388R-squared0.02980.02980.0298SSR557,485.512177.5778557.485.51SER20.0631.253920.0636IntermediateEconometrics,YanShenImpactofchangingthescaleofthedependentvariable改变被解释变量测度单位的影响Since1lbs=16oz,thedependentvariableistransformedby

7、dividing16.因为1磅＝16盎司，被解释变量被除以16。Wecomparecolumns(1)and(2).比较第1列与第2列。Theestimatedcoefficientsin(1)/16=thosein(2).(1)中被估参数/16＝(2)中被估参数Thestandarderrorsofestimatedcoefficientsin(1)/16=thosein(2)(1)中被估参数的标准差/16＝(2)中被估参数的标准差7Intermedia