1、經(jīng)濟計量分析實驗報告一、實驗項目異方差的檢驗及修正二、實驗日期2015.12.06三、實驗?zāi)康膶τ趪鴥?nèi)旅游總花費的有關(guān)影響因素建立多元線性回歸模型，對變量進行多重共線性的檢驗及修正后，進行異方差的檢驗和補救。四、實驗內(nèi)容建立模型，對模型進行參數(shù)估計，對樣本回歸函數(shù)進行統(tǒng)計檢驗，以判定估計的可靠程度，包括擬合優(yōu)度檢驗、方程總體線性的顯著性檢驗、變量的顯著性檢驗，以及參數(shù)的置信區(qū)間估計。檢驗變量是否具有多重共線性并修正。檢驗是否存在異方差并補救。五、實驗步驟1、建立模型。以國內(nèi)旅游總花費Y作為被解釋變量，以年底總?cè)丝诒硎救丝谠鲩L水平，以旅行社數(shù)量表示旅行社的發(fā)展情況，以城市公共交通運營數(shù)表示城市公

2、共交通運行狀況，以城鄉(xiāng)居民儲蓄存款年末增加值表示城鄉(xiāng)居民儲蓄存款增長水平。2、模型設(shè)定為:y=B+Bx+Bx+Bx+Bx+卩t011t22t33t44tt其中：y國內(nèi)旅游總花費（億元）tx年底總?cè)丝冢ㄈf人）1tx旅行社數(shù)量（個）2tx城市公共交通運營數(shù)（輛）3tx城鄉(xiāng)居民儲蓄存款年末增加值（億元）4t3、對模型進行多重共線性檢驗。4、檢驗異方差是否存在。六、實驗結(jié)果（一）、消除多重共線性之后的模型Sample(adjusted):19942008Sample(adjusted):19942008Includedobservations:15afteradjustmentsVariableCoe

3、fficientStd.Errort-StatisticProb.C81113.9926581.733.0514940.0122PEOPLE-0.7200760.230790-3.1200460.0109AGENT0.1519240.1082231.4038050.1907TRANSIT0.0533290.0138343.8549880.0032SAVE0.0007790.0205020.0380200.9704R-squared0.969693Meandependentvar3875.880AdjustedR-squared0.957571S.D.dependentvar2295.093S.

4、E.ofregression472.7528Akaikeinfocriterion15.41622Sumsquaredresid2234952.Schwarzcriterion15.65224Loglikelihood-110.6217Hannan-Quinncriter.15.41371F-statistic79.98987Durbin-Watsonstat2.028677Prob(F-statistic)0.000000多元線性回歸模型估計結(jié)果如下：勺=8111399-0.720076K+0.15192軟+0.053329K+0.000779Ki1234SE=(26581.73)(0.23

5、0790)(0.108223)(0.013834)(0.020502)t=(3.051494)(-3.120046)(1.403805)(3.854988)(0.038020)R2=0.969693不2=0.957571f=79.98987(1)擬合優(yōu)度檢驗：可決系數(shù)R2=0.969693較高，修正的可決系數(shù)不2=0.957571也較高，表明模型擬合較好。方程總體線性的顯著性檢驗(F)：針對H:卩=卩=卩=卩=0，取a=0.05，查自由度為k=4和n-k-1=1001234的臨界值F(4,10)。由于F=79.98987F(4,10)=3.48,p值(n-p)R2p值0.05接受原假設(shè)，即不存

6、在異方差2.White檢驗HeteroskedasticityTest:WhiteF-statistic3.066639Prob.F(2,12)0.0840Obs*R-squared5.073500Prob.Chi-Square(2)0.0791ScaledexplainedSS3.901442Prob.Chi-Square(2)0.1422TestEquation:DependentVariable:RESIDA2Method:LeastSquaresDate:12/06/15Time:19:01Sample:1226Includedobservations:15VariableCoeffi

7、cientStd.Errort-StatisticProb.C159495.6683418.60.2333790.8194AGENTS0.0039100.0059660.6554590.5245AGENT-30.28092140.0834-0.2161640.8325R-squared0.338233Meandependentvar414537.9AdjustedR-squared0.227939S.D.dependentvar613998.8S.E.ofregression539502.4Akaikeinfocriterion29.41154Sumsquaredresid3.49E+12Sc

8、hwarzcriterion29.55315Loglikelihood-217.5865Hannan-Quinncriter.29.41003F-statistic3.066639Durbin-Watsonstat1.930390Prob(F-statistic)0.083990p值0.05X（22）=5.99nR2，接受原假設(shè)，表示不存在異方差。3.G-D檢驗DependentVariable:COSTMethod:LeastSquaresDate:12/06/15Time:18:01Sample:1217Includedobservations:6VariableCoefficientSt

9、d.Errort-StatisticProb.C-464.5026552.0770-0.8413730.4475AGENT0.4565810.1039264.3933230.0118R-squared0.828336Meandependentvar1895.567AdjustedR-squared0.785420S.D.dependentvar673.2631S.E.ofregression311.8745Akaikeinfocriterion14.58428Sumsquaredresid389062.8Schwarzcriterion14.51487Loglikelihood-41.7528

10、4Hannan-Quinncriter.14.30641F-statistic19.30128Durbin-Watsonstat3.104838Prob(F-statistic)0.011752&2/出-&2/出-k22&2/凹-ki2HF(k，寫-k)1Method:LeastSquaresDate:12/06/15Time:18:03Sample:2126Includedobservations:6VariableCoefficientStd.Errort-StatisticProb.C-6878.2701141.633-6.0249400.0038AGENT0.7628110.06682

11、911.414310.0003R-squared0.970213Meandependentvar6031.417AdjustedR-squared0.962766S.D.dependentvar1972.540S.E.ofregression380.6227Akaikeinfocriterion14.98270Sumsquaredresid579494.4Schwarzcriterion14.91328Loglikelihood-42.94809Hannan-Quinncriter.14.70483F-statistic130.2866Durbin-Watsonstat1.642188Prob

12、(F-statistic)0.000336F=579494.4/389062.8=1.4894624F(5,5)=5.05F,所以接受原假設(shè)，不存在異方差性。所以回歸模型為Y=-301.8388+0.382963X2，說明旅行社數(shù)量每增加1個,平均說來國內(nèi)旅游總花費將增加3829.63萬元。Breusch-GodfreySerialCorrelationLMTest:F-statistic882.2612Prob.F(1,12)0.0000Obs*R-squared14.79872Prob.Chi-Square(1)0.0001TestEquation:DependentVariable:RE

13、SIDMethod:LeastSquaresDate:12/06/15Time:18:26Sample:1226Includedobservations:15Presamplemissingvaluelaggedresidualssettozero.Weightseries:WVariableCoefficientStd.Errort-StatisticProb.C-29.6860949.99510-0.5937800.5637AGENT-0.0086400.005743-1.5044670.1583RESID(-1)0.4903760.0893625.4874970.0001Weighted

14、StatisticsR-squared0.986581Meandependentvar-6.540864AdjustedR-squared0.984345S.D.dependentvar30.39880S.E.ofregression3.896737Akaikeinfocriterion5.735013Sumsquaredresid182.2148Schwarzcriterion5.876623Loglikelihood-40.01260Hannan-Quinncriter.5.733504F-statistic441.1306Durbin-Watsonstat2.501422Prob(F-sta