資源描述:
《經(jīng)典線性回歸模型診斷和修正》由會(huì)員上傳分享,免費(fèi)在線閱讀,更多相關(guān)內(nèi)容在工程資料-天天文庫(kù)。
1、經(jīng)典線性回歸模型的診斷與修正下表為最近20年我國(guó)全社會(huì)固定資產(chǎn)投資與GDP的統(tǒng)計(jì)數(shù)據(jù):1年份國(guó)內(nèi)生產(chǎn)總值(億元)GDP全社會(huì)固定資產(chǎn)投資(億元)PI199671813.622913.519977971524941.1199885195.528406.2199990564.429854.72000100280.132917.72001110863.137213.492002121717.443499.91200313742255566.612004161840.270477.432005187318.988773.612006219438.5109998.162007270232.3137
2、323.942008319515.5172828.42009349081.4224598.772010413030.3251683.772011489300.6311485.132012540367.4374694.742013595244.4446294.091數(shù)據(jù)來(lái)源于國(guó)家統(tǒng)計(jì)局網(wǎng)站年度數(shù)據(jù)2014643974512020.652015689052.1561999.831.普通最小二乘法回歸結(jié)果如下:[=1Equation:EQ01Workfile:04::Untitled-nxIviewjprocObject]PrintNameFreezeEstimateForecastStat
3、sResidsDependentVariable:GDPMethod:LeastSquaresDate:12/06/17Time:14:50Sample:19962015Ineludedobservations.20VariableCoefficientStd.Errort-StatisticProb.C75906548945.063848585800000PI1.1753630.03633132.351180.0000R-squared0.983092Meandependentvar283798.3AdjustedR-squared0.982153S.D.dependentvar208
4、303.1S.E.ofregression27827.84Akaikeinfocriterion23.40010Sumsquaredresid1.39E+10Schwarzcriterion23.49967Loglikelihood-232.0010Hannan-Quinnenter.23.41954F-statistic1046599Durbin-Watsonstat0365276Prob(F-statistic)0000000方程初步估計(jì)為:GDP=75906.54+1.1754PI(32.351)R2=0.9822F=1046.599DW=0.36532、異方差的檢驗(yàn)與修正首先,用
5、圖示檢驗(yàn)法,生成殘差平方和與解釋變量PI的散點(diǎn)圖如下:Gjj]Graph:GRAPH01Workfile:04::Untitled-hx[viewProc
6、Object]PrintNameFreeze
7、OptionsUpdate
8、AddTextLine/ShadeRemove80,00060,00040,000Gj20,0000-20,000?40,000100,000300,000500,000PI從上圖可以看出,殘差平方和與解釋變量的散點(diǎn)圖主要分布在圖形的下半部分,有隨PI的變動(dòng)增大的趨勢(shì),因此,模型可能存在異方差。但是否確定存在異方差,還需作進(jìn)一步的驗(yàn)證。G?Q檢驗(yàn)如下:去除序列
9、中間約1/4的部分后,1996-2003年的OLS估計(jì)結(jié)果如下所示:1=]Equation:UNTITLEDWorkfile:04::Untitled-BX1ViewProcObjectPrintNameFreezeEstimateForecastStatsResidsDependentVariable:GDPMethod:LeastSquaresDate:01/04/18Time:20:59Sample:19962003Includedobservations:8VariableCoefficientStd.Errort-StatisticProb.C29637.515357.566
10、5.5318990.0015PI2.0357580.14935813.630050.0000R-squared0.968714Meandependentvar99696.39AdjustedR-squared0.963500S.D.dependentvar22372.04S上.of「egression4274.201Akaikeinfocriterion19.77090Sumsquaredresid1.10E+08Schwarzcr