《我國(guó)財(cái)政收入影響因素分析》 計(jì)量經(jīng)濟(jì)學(xué)論文(eviews分析)

1、我國(guó)財(cái)政收入影響因素分析班級(jí)： 姓名： 學(xué)號(hào)：指導(dǎo)教師： 完成時(shí)間： 摘要：對(duì)我國(guó)財(cái)政收入影響因素進(jìn)行了定量分析，建立了數(shù)學(xué)模型，并提出了提高我國(guó)財(cái)政收入質(zhì)量的政策建議。關(guān)鍵詞：財(cái)政收入 實(shí)證分析 影響因素一、 引言財(cái)政收入對(duì)于國(guó)民經(jīng)濟(jì)的運(yùn)行及社會(huì)發(fā)展具有重要影響。首先，它是一個(gè)國(guó)家各項(xiàng)收入得以實(shí)現(xiàn)的物質(zhì)保證。一個(gè)國(guó)家財(cái)政收入規(guī)模大小往往是衡量其經(jīng)濟(jì)實(shí)力的重要標(biāo)志。其次，財(cái)政收入是國(guó)家對(duì)經(jīng)濟(jì)實(shí)行宏觀調(diào)控的重要經(jīng)濟(jì)杠桿。宏觀調(diào)控的首要問(wèn)題是社會(huì)總需求與總供給的平衡問(wèn)題，實(shí)現(xiàn)社會(huì)總需求與總供給的平衡，包括總量上的平衡和結(jié)構(gòu)上的平衡兩個(gè)層次的內(nèi)容。財(cái)政收入的杠桿既可通過(guò)增收和減收來(lái)發(fā)揮總量調(diào)控作用，

2、也可通過(guò)對(duì)不同財(cái)政資金繳納者的財(cái)政負(fù)擔(dān)大小的調(diào)整，來(lái)發(fā)揮結(jié)構(gòu)調(diào)整的作用。此外，財(cái)政收入分配也是調(diào)整國(guó)民收入初次分配格局，實(shí)現(xiàn)社會(huì)財(cái)富公平合理分配的主要工具。在我國(guó)，財(cái)政收入的主體是稅收收入。因此，在稅收體制及政策不變的情況下，財(cái)政收入會(huì)隨著經(jīng)濟(jì)繁榮而增加，隨著經(jīng)濟(jì)衰退而下降。我國(guó)的財(cái)政收入主要包括稅收、國(guó)有經(jīng)濟(jì)收入、債務(wù)收入以及其他收入四種形式，因此，財(cái)政收入會(huì)受到不同因素的影響。從國(guó)民經(jīng)濟(jì)部門(mén)結(jié)構(gòu)看，財(cái)政收入又表現(xiàn)為來(lái)自各經(jīng)濟(jì)部門(mén)的收入。財(cái)政收入的部門(mén)構(gòu)成就是在財(cái)政收入中，由來(lái)自國(guó)民經(jīng)濟(jì)各部門(mén)的收入所占的不同比例來(lái)表現(xiàn)財(cái)政收入來(lái)源的結(jié)構(gòu)，它體現(xiàn)國(guó)民經(jīng)濟(jì)各部門(mén)與財(cái)政收入的關(guān)系。我國(guó)財(cái)政收入主要

3、來(lái)自于工業(yè)、農(nóng)業(yè)、商業(yè)、交通運(yùn)輸和服務(wù)業(yè)等部門(mén)。因此，本文認(rèn)為財(cái)政收入主要受到總稅收收入、國(guó)內(nèi)生產(chǎn)總值、其他收入和就業(yè)人口總數(shù)的影響。二、預(yù)設(shè)模型令財(cái)政收入Y（億元）為被解釋變量，總稅收收入X1（億元）、國(guó)內(nèi)生產(chǎn)總值X2（億元）、其他收入X3（億元）、就業(yè)人口總數(shù)為X4（萬(wàn)人）為解釋變量，據(jù)此建立回歸模型。二、 數(shù)據(jù)收集從2010中國(guó)統(tǒng)計(jì)年鑒得到1990-2009年每年的財(cái)政收入、總稅收收入、國(guó)內(nèi)生產(chǎn)總值工、其他收入和就業(yè)人口總數(shù)的統(tǒng)計(jì)數(shù)據(jù)如下：obs財(cái)政收入Y總稅收收入X1國(guó)內(nèi)生產(chǎn)總值X2其他收入X3就業(yè)人口總數(shù)X419902937.12821.8618667.8299.5364749199

4、13149.482990.1721781.5240.16549119923483.373296.9126923.5265.156615219934348.954255.335333.9191.046680819945218.15126.8848197.9280.186745519956242.26038.0460793.7396.196806519967407.996909.8271176.6724.666895019978651.148234.0478973682.36982019989875.959262.884402.3833.370637199911444.0810682.588967

5、7.1925.4371394200013395.2312581.5199214.6944.9872085200116386.0415301.38109655.21218.173025200218903.6417636.45120332.71328.7473740200321715.2520017.31135822.81691.9374432200426396.4724165.68159878.32148.3275200200531649.2928778.54184937.42707.8375825200638760.234804.35216314.43683.8576400200751321.

6、7845621.97265810.34457.9676990200861330.3554223.79314045.45552.4677480200968518.359521.59340506.97215.7277995三、 模型建立1、 散點(diǎn)圖分析2、 單因素或多變量間關(guān)系分析YX1X2X3X4Y10.9989134611478530.9934790452908040.8770144886795640.983602719841508X10.99891346114785310.9937402677184690.8556377347447820.984935296593492X20.9934790

7、452908040.99374026771846910.8561835802284710.986241165680459X30.8770144886795640.8556377347447820.85618358022847110.810940334650381X40.9836027198415080.9849352965934920.9862411656804590.8109403346503811由散點(diǎn)圖分析和變量間關(guān)系分析可以看出被解釋變量財(cái)政收入Y與解釋變量總稅收收入X1、國(guó)內(nèi)生產(chǎn)總值X2、其他收入X3、就業(yè)人口總數(shù)X4呈線性關(guān)系，因此該回歸模型設(shè)為：3、 模型預(yù)模擬由eviews做o

8、ls回歸得到結(jié)果：Dependent Variable: YMethod: Least SquaresDate: 11/14/11 Time: 17:51Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C7299.5231691.8144.3146140.0006X11.0628020.02110850.349720.0000X20.0017700.0045280.3910070.7013X30.8733690.1198067.2898520.0000X4-0.1159

9、750.026580-4.3631600.0006R-squared0.999978Mean dependent var20556.75Adjusted R-squared0.999972S.D. dependent var19987.03S.E. of regression106.6264Akaike info criterion12.38886Sum squared resid170537.9Schwarz criterion12.63779Log likelihood-118.8886F-statistic166897.9Durbin-Watson stat1.496517Prob(F-

10、statistic)0.000000 (4.314614) ( 50.34972 ) ( 0.391007) ( 7.289852) ( -4.363160) 四、 模型檢驗(yàn)1.計(jì)量經(jīng)濟(jì)學(xué)意義檢驗(yàn)多重共線性檢驗(yàn)與解決求相關(guān)系數(shù)矩陣，得到：Correlation MatrixYX1X2X3X410.9989134611478530.9934790452908040.8770144886795640.9836027198415080.99891346114785310.9937402677184690.8556377347447820.9849352965934920.99347904529080

11、40.99374026771846910.8561835802284710.9862411656804590.8770144886795640.8556377347447820.85618358022847110.8109403346503810.9836027198415080.9849352965934920.9862411656804590.8109403346503811發(fā)現(xiàn)模型存在多重共線性。接下來(lái)運(yùn)用逐步回歸法對(duì)模型進(jìn)行修正:將各個(gè)解釋變量分別加入模型,進(jìn)行一元回歸: 作Y與X1的回歸，結(jié)果如下:Dependent Variable: YMethod: Least SquaresD

12、ate: 11/22/11 Time: 23:02Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C-755.6610145.2330-5.2030940.0001X11.1449940.005760198.79310.0000R-squared0.999545Mean dependent var20556.75Adjusted R-squared0.999519S.D. dependent var19987.03S.E. of regression438.1521Ak

13、aike info criterion15.09765Sum squared resid3455590.Schwarz criterion15.19722Log likelihood-148.9765F-statistic39518.70Durbin-Watson stat0.475046Prob(F-statistic)0.000000作Y與X2的回歸，結(jié)果如下:Dependent Variable: YMethod: Least SquaresDate: 11/22/11 Time: 23:06Sample: 1990 2009Included observations: 20Variab

14、leCoefficientStd. Errort-StatisticProb.C-5222.077861.2067-6.0636740.0000X20.2076890.00554837.432670.0000R-squared0.987317Mean dependent var20556.75Adjusted R-squared0.986612S.D. dependent var19987.03S.E. of regression2312.610Akaike info criterion18.42478Sum squared resid96267005Schwarz criterion18.5

15、2435Log likelihood-182.2478F-statistic1401.205Durbin-Watson stat0.188013Prob(F-statistic)0.000000作Y與X3的回歸，結(jié)果如下:Dependent Variable: YMethod: Least SquaresDate: 11/22/11 Time: 23:08Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C2607.879773.99883.3693580.0034X31

16、0.030730.29431134.082090.0000R-squared0.984740Mean dependent var20556.75Adjusted R-squared0.983893S.D. dependent var19987.03S.E. of regression2536.645Akaike info criterion18.60971Sum squared resid1.16E+08Schwarz criterion18.70929Log likelihood-184.0971F-statistic1161.589Durbin-Watson stat1.194389Pro

17、b(F-statistic)0.000000作Y與X4的回歸，結(jié)果如下:Dependent Variable: YMethod: Least SquaresDate: 11/22/11 Time: 23:08Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C-272959.337203.65-7.3368940.0000X44.0974030.5184677.9029180.0000R-squared0.776276Mean dependent var20556.75A

18、djusted R-squared0.763846S.D. dependent var19987.03S.E. of regression9712.824Akaike info criterion21.29492Sum squared resid1.70E+09Schwarz criterion21.39449Log likelihood-210.9492F-statistic62.45611Durbin-Watson stat0.157356Prob(F-statistic)0.000000依據(jù)可決系數(shù)最大的原則選取X1作為進(jìn)入回歸模型的第一個(gè)解釋變量,再依次將其余變量分別代入回歸得:作Y與

19、X1、X2的回歸，結(jié)果如下Dependent Variable: YMethod: Least SquaresDate: 11/22/11 Time: 23:09Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C-188.4285239.0743-0.7881590.4415X11.2815940.04947225.905680.0000X2-0.0250550.009029-2.7749080.0130R-squared0.999687Mean dependent v

20、ar20556.75Adjusted R-squared0.999650S.D. dependent var19987.03S.E. of regression374.0345Akaike info criterion14.82405Sum squared resid2378330.Schwarz criterion14.97341Log likelihood-145.2405F-statistic27118.20Durbin-Watson stat0.683510Prob(F-statistic)0.000000作Y與X1、X3的回歸，結(jié)果如下Dependent Variable: YMet

21、hod: Least SquaresDate: 11/22/11 Time: 23:10Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C-351.105483.15053-4.2225270.0006X10.9928130.01870753.071960.0000X31.3569360.1651098.2184100.0000R-squared0.999908Mean dependent var20556.75Adjusted R-squared0.999898S.D

22、. dependent var19987.03S.E. of regression202.1735Akaike info criterion13.59361Sum squared resid694859.9Schwarz criterion13.74297Log likelihood-132.9361F-statistic92839.33Durbin-Watson stat1.177765Prob(F-statistic)0.000000作Y與X1、X4的回歸，結(jié)果如下Dependent Variable: YMethod: Least SquaresDate: 11/22/11 Time:

23、23:10Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C11853.461824.5226.4967480.0000X11.1858860.006645178.46080.0000X4-0.1866450.026984-6.9170030.0000R-squared0.999881Mean dependent var20556.75Adjusted R-squared0.999867S.D. dependent var19987.03S.E. of regressi

24、on230.8464Akaike info criterion13.85886Sum squared resid905931.0Schwarz criterion14.00822Log likelihood-135.5886F-statistic71206.90Durbin-Watson stat1.459938Prob(F-statistic)0.000000在滿足經(jīng)濟(jì)意義和可決系數(shù)的條件下選取X3作為進(jìn)入模型的第二個(gè)解釋變量,再次進(jìn)行回歸則:作Y與X1、X3、X2的回歸，結(jié)果如下Dependent Variable: YMethod: Least SquaresDate: 11/22/11

25、 Time: 23:13Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C-76.04458100.1724-0.7591370.4588X11.0859240.02980136.438810.0000X31.2108530.1334449.0738770.0000X2-0.0140730.003944-3.5679010.0026R-squared0.999949Mean dependent var20556.75Adjusted R-squared0.999939S

26、.D. dependent var19987.03S.E. of regression155.5183Akaike info criterion13.10826Sum squared resid386975.0Schwarz criterion13.30741Log likelihood-127.0826F-statistic104602.9Durbin-Watson stat1.196933Prob(F-statistic)0.000000作Y與X1、X3、X4的回歸，結(jié)果如下Dependent Variable: YMethod: Least SquaresDate: 11/22/11 T

27、ime: 23:13Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C6781.7641024.7456.6180030.0000X11.0686420.01451473.627640.0000X30.8910690.1079498.2545510.0000X4-0.1076390.015451-6.9666750.0000R-squared0.999977Mean dependent var20556.75Adjusted R-squared0.999973S.D.

28、dependent var19987.03S.E. of regression103.7654Akaike info criterion12.29900Sum squared resid172276.1Schwarz criterion12.49814Log likelihood-118.9900F-statistic234970.9Durbin-Watson stat1.451447Prob(F-statistic)0.000000可見(jiàn)加入其余任何一個(gè)變量都會(huì)導(dǎo)致系數(shù)符號(hào)與經(jīng)濟(jì)意義不符,故最終修正后的回歸模型為:Dependent Variable: YMethod: Least Squar

29、esDate: 11/30/11 Time: 12:18Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C-351.105483.15053-4.2225270.0006X10.9928130.01870753.071960.0000X31.3569360.1651098.2184100.0000R-squared0.999908Mean dependent var20556.75Adjusted R-squared0.999898S.D. dependent var1

30、9987.03S.E. of regression202.1735Akaike info criterion13.59361Sum squared resid694859.9Schwarz criterion13.74297Log likelihood-132.9361F-statistic92839.33Durbin-Watson stat1.177765Prob(F-statistic)0.000000(-4.222527) ( 53.07196) ( 8.218410) 異方差檢驗(yàn)與修正 圖示法ee與X1的散點(diǎn)圖如下：說(shuō)明ee與X1存在單調(diào)遞增型異方差性。ee與X3的散點(diǎn)圖如下：說(shuō)明ee

31、與X3存在單調(diào)遞增型異方差性。G-Q檢驗(yàn)對(duì)20組數(shù)據(jù)剔除掉中間四組剩下的進(jìn)行分組后，第一組（1990-1997）數(shù)據(jù)的回歸結(jié)果：Dependent Variable: YMethod: Least SquaresDate: 11/30/11 Time: 12:54Sample: 1990 1997Included observations: 8VariableCoefficientStd. Errort-StatisticProb.X10.9841230.01625560.543200.0000X30.8515180.1566885.4344720.0029C-28.3427545.36993

32、-0.6247030.5596R-squared0.999686Mean dependent var5179.791Adjusted R-squared0.999560S.D. dependent var2099.840S.E. of regression44.05899Akaike info criterion10.68893Sum squared resid9705.972Schwarz criterion10.71872Log likelihood-39.75573F-statistic7947.575Durbin-Watson stat1.663630Prob(F-statistic)

33、0.000000殘差平方和RSS1=9705.972第二組（2002-2009）數(shù)據(jù)的回歸結(jié)果：Dependent Variable: YMethod: Least SquaresDate: 11/30/11 Time: 12:55Sample: 2002 2009Included observations: 8VariableCoefficientStd. Errort-StatisticProb.X11.0664040.02774738.433210.0000X30.8472280.2151143.9385030.0110C-1184.159261.8258-4.5226980.0063R

34、-squared0.999932Mean dependent var39824.41Adjusted R-squared0.999905S.D. dependent var18639.16S.E. of regression182.0047Akaike info criterion13.52594Sum squared resid165628.5Schwarz criterion13.55573Log likelihood-51.10375F-statistic36705.08Durbin-Watson stat1.326122Prob(F-statistic)0.000000殘差平方和RSS

35、2= 165628.5所以F= RSS2/RSS1= 165628.5/9705.972=17.0646在給定a=5%下查得臨界值 ，因此否定兩組子樣方差相同的假設(shè)，從而該總體隨機(jī)項(xiàng)存在遞增異方差性。White 方法檢驗(yàn)White Heteroskedasticity Test:F-statistic6.142010Probability0.003919Obs*R-squared12.41812Probability0.014498Test Equation:Dependent Variable: RESID2Method: Least SquaresDate: 11/30/11 Time:

36、13:21Sample: 1990 2009Included observations: 20VariableCoefficientStd. Errort-StatisticProb.C24856.5019211.301.2938480.2153X1-20.573277.549127-2.7252520.0156X120.0002128.04E-052.6399820.0186X3237.181378.613233.0170670.0087X32-0.0240730.006568-3.6652300.0023R-squared0.620906Mean dependent var34743.00

37、Adjusted R-squared0.519815S.D. dependent var49156.00S.E. of regression34062.86Akaike info criterion23.92212Sum squared resid1.74E+10Schwarz criterion24.17105Log likelihood-234.2212F-statistic6.142010Durbin-Watson stat1.560937Prob(F-statistic)0.003919a=5%下，臨界值拒絕同方差性 修正Dependent Variable: YMethod: Lea

38、st SquaresDate: 11/30/11 Time: 14:29Sample: 1990 2009Included observations: 20Weighting series: 1/E1VariableCoefficientStd. Errort-StatisticProb.C-314.207443.68550-7.1924860.0000X10.9797580.008622113.63360.0000X31.4572910.06592222.106290.0000Weighted StatisticsR-squared0.999999Mean dependent var2724

39、6.27Adjusted R-squared0.999999S.D. dependent var74471.17S.E. of regression73.91795Akaike info criterion11.58127Sum squared resid92885.67Schwarz criterion11.73063Log likelihood-112.8127F-statistic3138195.Durbin-Watson stat0.956075Prob(F-statistic)0.000000Unweighted StatisticsR-squared0.999902Mean dep

40、endent var20556.75Adjusted R-squared0.999891S.D. dependent var19987.03S.E. of regression209.0283Sum squared resid742778.2Durbin-Watson stat1.365483(-7.192486) ( 113.6336) ( 22.10629) 序列相關(guān)性檢驗(yàn)從殘差項(xiàng)e2與e2(-1)及e與時(shí)間t的關(guān)系圖（如下）看，隨機(jī)項(xiàng)呈現(xiàn)正序列相關(guān)性。Q統(tǒng)計(jì)量檢驗(yàn)由圖可以看出，存在一階序列相關(guān)回歸檢驗(yàn)殘差e2與e2（-1）做回歸得：Dependent Variable: EMethod:

41、 Least SquaresDate: 12/04/11 Time: 15:21Sample (adjusted): 1991 2009Included observations: 19 after adjustmentsVariableCoefficientStd. Errort-StatisticProb.C16.8152545.696110.3679800.7174E(-1)0.3035700.2311141.3135080.2065R-squared0.092138Mean dependent var25.28519Adjusted R-squared0.038734S.D. depe

42、ndent var201.1252S.E. of regression197.1916Akaike info criterion13.50553Sum squared resid661036.6Schwarz criterion13.60494Log likelihood-126.3025F-statistic1.725303Durbin-Watson stat1.776498Prob(F-statistic)0.206464e與e(-1)、e(-2)做回歸得：Dependent Variable: EMethod: Least SquaresDate: 12/04/11 Time: 15:2

43、4Sample (adjusted): 1992 2009Included observations: 18 after adjustmentsVariableCoefficientStd. Errort-StatisticProb.C7.44976046.209120.1612180.8741E(-1)0.4195640.2444751.7161870.1067E(-2)-0.3798940.278641-1.3633800.1929R-squared0.192570Mean dependent var16.45940Adjusted R-squared0.084912S.D. depend

44、ent var203.1349S.E. of regression194.3193Akaike info criterion13.52789Sum squared resid566399.7Schwarz criterion13.67629Log likelihood-118.7510F-statistic1.788727Durbin-Watson stat2.055382Prob(F-statistic)0.201043由上表明不存在序列相關(guān)性。D.W檢驗(yàn)由異方差檢驗(yàn)修正后的結(jié)果： 得D.W=1.365483取a=5%，由于n=20，k=3(包含常數(shù)項(xiàng))，查表得： dl=1.10， du=1.54由于dlDW=1.365483 du ，故: 序列相關(guān)性不確定。拉格朗日