異方差實驗報告Word版

1、附件二：實驗報告格式（首頁） 山東輕工業(yè)學(xué)院實驗報告 成績 課程名稱 計量經(jīng)濟(jì)學(xué) 指導(dǎo)教師 蘇衛(wèi)東 實驗日期 2013.5.18 院（系） 商學(xué)院會計系 專業(yè)班級 實驗地點 實驗樓二機(jī)房 學(xué)生姓名 學(xué)號 同組人 無 實驗項目名稱 異方差的檢驗 一、 實驗?zāi)康暮鸵?3、掌握異方差性問題出現(xiàn)的來源、后果、檢驗及修正的原理，以及相關(guān)的Eviews操 作方法 4、練習(xí)檢查和克服模型的異方差的操作方法。 6、用圖示法、斯皮爾曼法、戈德菲爾德、white驗證法，驗證該模型是否存在異方差 二、 實驗原理2、運用EVIEWS軟件及普通最小二乘法進(jìn)行模型估計3、檢驗?zāi)Ｐ偷漠惙讲钚圆ζ溥M(jìn)行調(diào)整三、 主要儀器設(shè)

2、備、試劑或材料Eviews軟件、課本教材、電腦 四、 實驗方法與步驟1、CREATE U 1 31 回車2、DATA Y X 回車 輸入數(shù)據(jù)obsYX126487772105921039099544131105085122109796107119127406127478503134999431142691058815522118981673012950176631377918575148191963515122221163161702228801715782412718165425604191400265002018292676021220028300222017274302321052956

3、024160028150252250321002624203250027257035250281720335002919003600030210036200312800382003、LS Y C X 回車用最小二乘法進(jìn)行估計出現(xiàn)Dependent Variable: YMethod: Least SquaresDate: 05/18/13 Time: 11:46Sample: 1 31Included observations: 31VariableCoefficientStd. Errort-StatisticProb. C-700.411116.6679-6.003460X0.087831

4、0.00482718.195750R-squared0.919464 Mean dependent var1266.452Adjusted R-squared0.916686 S.D. dependent var846.757S.E. of regression244.4088 Akaike info criterion13.8979Sum squared resid1732334 Schwarz criterion13.99042Log likelihood-213.418 F-statistic331.0852Durbin-Watson stat1.089829 Prob(F-statis

5、tic)0用普通最小二乘法進(jìn)行估計，估計結(jié)果如下=700.41+0.087831Xi R2=0.92 =0.92 F=335.82 t=(-6.0) (18.2) 括號內(nèi)為t統(tǒng)計量。(一).圖示檢驗法分別繪制X、Y坐標(biāo)系散點圖，命令如下：Scat x yGenr e2=resid2Scat x e2出現(xiàn)可以看出，隨著可支配收入x的增加，儲蓄y的離散程度增加，表明隨機(jī)誤差項ui存在異方差性。（二）斯皮爾曼等級相關(guān)系數(shù)檢驗命令scat x e2sort x data x dd1（輸入1-31）ls y c x 出現(xiàn)Dependent Variable: YMethod: Least Squares

6、Date: 05/18/13 Time: 11:34Sample: 1 31Included observations: 31VariableCoefficientStd. Errort-StatisticProb.C-700.4110116.6679-6.0034580.0000X0.0878310.00482718.195750.0000R-squared0.919464Mean dependent var1266.452Adjusted R-squared0.916686S.D. dependent var846.7570S.E. of regression244.4088Akaike

7、info criterion13.89790Sum squared resid1732334.Schwarz criterion13.99042Log likelihood-213.4175F-statistic331.0852Durbin-Watson stat1.943262Prob(F-statistic)0.000000sort x data x dd1ls y c x genr e1=abs(resid)sort e1 data e1 dd2genr r=1-6*sum(dd2-dd1)2)/(313-31)genr z=r*sqrt(30)出現(xiàn)3.326。R=0.607258 z=

8、3.326089 給定顯著性水平=0.05，查正態(tài)分布表，得,因為Z=3.331.96，所以拒絕H0,接受H1,即等級相關(guān)系數(shù)是顯著的，說明儲蓄計量模型的隨機(jī)誤差項存在異方差性。(三)、Goldfeld-Quant檢驗命令sort x smpl 1 11 ls y c x Dependent Variable: YMethod: Least SquaresDate: 05/18/13 Time: 11:37Sample: 1 11Included observations: 11VariableCoefficientStd. Errort-StatisticProb.C-744.6351195

9、.4108-3.8106140.0041X0.0882580.0157055.6196190.0003R-squared0.778216Mean dependent var331.3636Adjusted R-squared0.753574S.D. dependent var260.8157S.E. of regression129.4724Akaike info criterion12.72778Sum squared resid150867.9Schwarz criterion12.80012Log likelihood-68.00278F-statistic31.58011Durbin-

10、Watson stat1.142088Prob(F-statistic)0.000326smpl 21 31 ls y c x Dependent Variable: YMethod: Least SquaresDate: 05/18/13 Time: 11:38Sample: 21 31Included observations: 11VariableCoefficientStd. Errort-StatisticProb.C666.3811911.25850.7312760.4832X0.0457790.0278981.6409710.1352R-squared0.230295Mean d

11、ependent var2152.909Adjusted R-squared0.144772S.D. dependent var354.4462S.E. of regression327.7867Akaike info criterion14.58557Sum squared resid966997.0Schwarz criterion14.65791Log likelihood-78.22063F-statistic2.692786Durbin-Watson stat2.743586Prob(F-statistic)0.135222.記下第一個殘差平方和：150867.9 記下第二個殘差平方

12、和：966997.0。計算F=6.41，給定顯著性水平=0.05，查F分布表V1=V2=11-2=9,F0.05(9,9)=3.18,因為F=6.413.18，所以接受備擇假設(shè)，即儲蓄計量模型的隨機(jī)誤差項存在異方差性。(四).White檢驗命令smpl 21 31 ls y c x smpl 1 31 ls y c x出現(xiàn)Dependent Variable: YMethod: Least SquaresDate: 05/18/13 Time: 11:41Sample: 1 31Included observations: 31VariableCoefficientStd. Errort-St

13、atisticProb.C-700.4110116.6679-6.0034580.0000X0.0878310.00482718.195750.0000R-squared0.919464Mean dependent var1266.452Adjusted R-squared0.916686S.D. dependent var846.7570S.E. of regression244.4088Akaike info criterion13.89790Sum squared resid1732334.Schwarz criterion13.99042Log likelihood-213.4175F

14、-statistic331.0852Durbin-Watson stat1.943262Prob(F-statistic)0.000000White Heteroskedasticity Test:F-statistic5.819690Probability0.007699Obs*R-squared9.102584Probability0.010554Test Equation:smpl 1 31 ls y c xDependent Variable: RESID2Method: Least SquaresDate: 05/18/13 Time: 11:44Sample: 1 31Includ

15、ed observations: 31VariableCoefficientStd. Errort-StatisticProb.C19975.9882774.930.2413290.8111X-2.1986328.094419-0.2716230.7879X20.0001460.0001760.8300460.4135R-squared0.293632Mean dependent var55881.73Adjusted R-squared0.243177S.D. dependent var77875.67S.E. of regression67748.39Akaike info criteri

16、on25.17675Sum squared resid1.29E+11Schwarz criterion25.31553Log likelihood-387.2397F-statistic5.819690Durbin-Watson stat2.580140Prob(F-statistic)0.007699因為TR2=310.2936=9.1，所以結(jié)論是該回歸模型中存在異方差.其中obs*R-squared等于9.102584表示的就是統(tǒng)計量TR2的值。(五)克服異方差命令smpl 1 31 ls y c x Dependent Variable: YMethod: Least SquaresD

17、ate: 05/18/13 Time: 11:51Sample: 1 31Included observations: 31VariableCoefficientStd. Errort-StatisticProb.C-700.4110116.6679-6.0034580.0000X0.0878310.00482718.195750.0000R-squared0.919464Mean dependent var1266.452Adjusted R-squared0.916686S.D. dependent var846.7570S.E. of regression244.4088Akaike i

18、nfo criterion13.89790Sum squared resid1732334.Schwarz criterion13.99042Log likelihood-213.4175F-statistic331.0852Durbin-Watson stat1.943262Prob(F-statistic)0.000000genr ww=1/abs(resid)ls (w=1/x) y c xDependent Variable: YMethod: Least SquaresDate: 05/18/13 Time: 12:01Sample: 1 31Included observations: 31VariableCoefficientStd. Errort-Stat