完整版)我國私人汽車擁有量分析情況畢業(yè)論文

1、我國私人汽車擁有量分析E3UEE1LI我國私人汽車擁有量分析前言:國家統(tǒng)計局最新公布的數(shù)據(jù)顯示，國內(nèi)大城市的私家車擁有量繼續(xù)保持大幅增長的趨勢。截止到2001年底， 在全國十大城市的私家車擁有量排名中， 北京私家車的 擁有量以多出第二名近40萬輛的絕對優(yōu)勢排在了第一位。這十個城市的具體排名分別是:有關(guān)統(tǒng)計資料表明，我國城鎮(zhèn)居民中有 3800萬戶（占城鎮(zhèn)居民總戶數(shù)的 24.8 %）,有能力承受10萬元左右的汽車消費(fèi)。從近幾年我國汽車消費(fèi)的發(fā)展變化來看，汽車 消費(fèi)將成為消費(fèi)熱點(diǎn)。從1990年到2000年的10年間，我國民用汽車的保有量由551.36萬輛增加到1608.91萬輛，平均每年增長 11.

2、3 %。其中私人汽車擁有量 由1990年的81.62萬輛增加到2000年的625.73萬輛，平均每年增長 22.6 %。私人 汽車擁有量占民用汽車的保有量比重從1990年的14.8 %, 上升到2000年的38.9 %,平均每年上升2.4個百分點(diǎn)。1996年以來，民用汽車擁有量的增加量中，私人汽車 增加量的比重均高于 57.7 %，其中最高的是1999年，私人汽車增加量占全部民用汽 車增加量的82.5 %。這說明我國汽車市場結(jié)構(gòu)發(fā)生了根本性的變化，居民個人已經(jīng) 成為我國汽車市場的消費(fèi)主體。隨著我國經(jīng)濟(jì)突飛猛進(jìn)的發(fā)展，人民群眾的收入水平不斷提高，特別是城鎮(zhèn)居民的收入不斷提高，私人汽車擁有量不斷增

3、加，同時銀行的按揭貸款買車等等的一系列推 動措施，也促進(jìn)了私人汽車擁有倆的增加。單從經(jīng)濟(jì)方面來說，私人汽車擁有數(shù)量是評判一個國家人民生活水平的重要指標(biāo)， 對它的研究分析是有比較現(xiàn)實(shí)的意義的。我國私人汽車擁有量隨時間變化圖如下：數(shù)據(jù)收集：Y: 我國私人汽車擁有量X1：城鎮(zhèn)居民可支配收入X2:貸款利率X3:燃料、動力類價格指數(shù)（以1990年價格為10 0的定比指數(shù)序列）具體數(shù)據(jù)如下obs Y X1 X2（）X31990 816200 1510.2 9.72 10019919604001700.68.64101.9874 普通的多元線性方程形式:3 0+ 3 1x1+ 3 2x2+ 3 3x3先對各

4、個變量做平穩(wěn)性檢驗(yàn) : 對 YADF Test Statistic1.0821631% Critical Value*-4.32605%Critical Value-3.219510% Critical Value-2.7557*MacKinnon critical values for rejection ofDependent Variable: D(ADFY)Method: Least SquaresDate: 061405 Time: 09:21Sample(adjusted): 1994 2003Included observations: 10 after adjusting en

5、dpointsVariable Coefficient Std. Error t-Statistic Prob.ADFY(-1) 0.334153 0.308782 1.082163 0.3286Adjusted R-squared 0.907058S.D. dependent varS.E. of regression 216741.3Akaike info criterionSum squared resid 2.35E+11Schwarz criterion710945.927.7176527.86894Log likelihood-133.5882F-statistic22.95874

6、D(ADFY(-1)-0.1210600.697271-0.1736200.8690D(ADFY(-2)-0.0546060.945213-0.0577720.9562D(ADFY(-3)-0.4094070.879632-0.4654300.6612Durbin-Watson stat2.080638Prob(F-statistic)0.002042對 X1ADF Test Statistic-0.1589121%Critical Value-4.32605%Critical Value-3.219510% Critical Value-2.7557*MacKinnon critical v

7、alues for rejection ofDependent Variable: D(ADFX1)Method: Least SquaresDate: 061405Time: 09:26Sample(adjusted): 1994 2003Included observations: 10 after adjusting endpointsVariable Coefficient Std. Error t-Statistic Prob.ADFX1(-1) -0.005477 0.034465 -0.158912 0.8800D(ADFX1(-1) 0.664445 0.406596 1.63

8、4162 0.1632D(ADFX1(-2) -0.331605 0.522131 -0.635100 0.5533D(ADFX1(-3) -0.414658 0.416042 -0.996674 0.3647C 609.9278 275.2910 2.215575 0.0776R-squared 0.746497Mean dependent var589.4800Adjusted R-squared0.543694S.D. dependent var229.7711S.E. of regression155.2114Akaike info criterion13.23431Sum squar

9、ed resid120452.9Schwarz criterion13.38560Log likelihood-61.17153F-statistic3.680899Durbin-Watson stat2.031160Prob(F-statistic)0.092741對 X2ADF Test Statistic-0.5291981%Critical Value*-4.32605%Critical Value-3.219510% Critical Value-2.7557*MacKinnon critical values for rejection ofDependent Variable:

10、D(ADFX2)Method: Least SquaresDate: 061405 Time: 09:27Sample(adjusted): 1994 2003Included observations: 10 after adjusting endpointsVariable CoefficientStd. Error t-StatisticProb.0.6193ADFX2(-1) -0.069982 0.132242 -0.529198D(ADFX2(-1)0.5434260.3211591.6920750.1514D(ADFX2(-2)0.1405350.3683640.3815100.

11、7185D(ADFX2(-3)-0.3913870.347038-1.1277940.3106C 0.1550181.2198420.1270800.9038R-squared 0.768917Mean dependent var -0.486000Adjusted R-squared 0.584050S.D. dependent var0.905296S.E. of regression 0.583863Akaike info criterion2.068551Sum squared resid 1.704478Schwarz criterion 2.219843Log likelihood

12、 -5.342754F-statistic 4.159310Durbin-Watson stat2.443814Prob(F-statistic) 0.075014對 X3ADF Test Statistic-2.5015581% Critical Value* -4.32605%Critical Value-3.219510% Critical Value-2.7557*MacKinnon critical values for rejection ofDependent Variable: D(ADFX3)Method: Least SquaresDate: 061405Time: 09:

13、27Sample(adjusted): 1994 2003Included observations: 10 after adjusting endpointsVariable Coefficient Std. Error t-Statistic Prob.ADFX3(-1) -0.296326 0.118457 -2.501558 0.0544D(ADFX3(-1)-0.3320830.323046-1.0279730.3511D(ADFX3(-2)-0.5925950.256861-2.3070660.0692D(ADFX3(-3)0.0791950.2904280.2726840.796

14、0C 101.695638.342962.6522620.045314.01521R-squared 0.684768 Mean dependent var 14.93622Adjusted R-squared 0.432582 S.D. dependent varS.E. of regression10.55726Akaike info criterion7.858358Sum squared resid557.2788Schwarz criterion8.009650Log likelihood-34.29179 F-statistic 2.715332Durbin-Watson stat

15、 1.902782 Prob(F-statistic) 0.151305 由此可見，各個變量的隨時間變化是平穩(wěn)的，可以對其直接進(jìn)行最小二乘估計。 對其作普通最小二乘估計：Dependent Variable: YMethod: Least SquaresDate: 060305Time: 16:43Sample: 1990 2003Included observations: 14Variable Coefficient Std. Error t-Statistic Prob.X1 2922.028 515.0624 5.673154 0.0002X3 -50492.48 14255.54 -

16、3.541955 0.0053S.E. of regression 750961.7 Akaike info criterion 30.13105Sum squared resid5.64E+12 Schwarz criterion 30.31364Log likelihood-206.9174F-statistic90.71108Durbin-Watson stat1.514620Prob(F-statistic)0.000000t=(1.883529) (5.673154) (-1.379442) (-3.541955)Adjusted R2-=0.953922 F=90.71108 經(jīng)觀

17、察：各個系數(shù)符合經(jīng)濟(jì)意義 ;從可決系數(shù)看擬合優(yōu)度較好 ;X2的T檢驗(yàn)不顯著，而 F統(tǒng)計量顯著，效果很好，可以推斷解釋變量可能存在多重共線性。一、多重共線性的檢驗(yàn)與修正： 下面是 x1 x2 x3 的簡單相關(guān)系數(shù)矩陣 :x1 x2 x3x1 1 -0.73851 0.975673x2 -0.73851 1 -0.66181x3 0.975673 -0.66181 1可見 , 各個變量相關(guān)系數(shù)很高 , x1 x3 尤為突出 . 我們采用逐步回歸法進(jìn)行修正：(1) 運(yùn)用OLS方法逐一求Y對各個解釋變量的回歸，結(jié)合經(jīng)濟(jì)意義和統(tǒng)計檢驗(yàn)出擬 合效果最好的一個一元線性回歸方程：方程 1：Dependent

18、Variable: YMethod: Least SquaresDate: 060305 Time: 17:08Sample: 1990 2003Included observations: 14Variable Coefficient Std. Error t-Statistic Prob.X1 1474.612 151.6332 9.724864 0.0000Sum squared resid 1.79E+13Schwarz criterion31.09250Log likelihood -215.0085F-statistic 94.57299Durbin-Watson stat 0.2

19、73300Prob(F-statistic)0.000000方程 2：Dependent Variable: YMethod: Least SquaresDate: 060305 Time: 17:08Sample: 1990 2003Included observations: 14Variable Coefficient Std. Errort-StatisticProb.Sum squared resid5.28E+13Schwarz criterion32.17243Log likelihood-222.5679F-statistic24.19456Durbin-Watson stat

20、 0.583287Prob(F-statistic)0.000355方程 3:Dependent Variable: YMethod: Least SquaresDate: 060305Time: 17:09Sample: 1990 2003Included observations: 14Variable Coefficient Std. Errort-StatisticProb.X3 41472.90 7074.333 5.8624470.0001Sum squared resid4.12E+13Schwarz criterion31.92472Log likelihood-220.834

21、0F-statistic34.36829Durbin-Watson stat 0.332537Prob(F-statistic)0.000077(2) 對比分析， 依據(jù)調(diào)整后可決系數(shù)最大原則， 選取 X1 進(jìn)入回歸模型的第一個解釋變 量，形成一元回歸模型 : (787741.3) (151.6332)t=(-3.321533) (9.724864)Adjusted R-squared=0.878018 F=94.57299(3) 逐步回歸，將其余變量分別加入模型：Dependent Variable: YMethod: Least SquaresDate: 060305 Time: 17:13

22、Sample: 1990 2003Included observations: 14Prob.Variable Coefficient Std. Error t-StatisticX1 1164.618 197.8825 5.885402 0.0001Sum squared resid 1.27E+13Schwarz criterion30.93808Log likelihood -212.6080F-statistic 63.32690Durbin-Watson stat0.449924Prob(F-statistic)0.000001Dependent Variable: YMethod:

23、 Least SquaresDate: 060305Time: 17:13Sample: 1990 2003Included observations: 14Variable CoefficientStd. Errort-StatisticProb.X1 3323.203 442.20237.5151190.0000X3 -58306.1613608.15-4.2846500.0013S.E. of regression781172.8Akaike info criterion30.16239Sum squared resid6.71E+12Schwarz criterion30.29933L

24、og likelihood-208.1367F-statistic124.8664Durbin-Watson stat1.457294Prob(F-statistic)0.000000由上表可以看出，X3和X1構(gòu)建的模型的擬合值優(yōu)于X2和X1構(gòu)建的方程的擬合值,且比起 t=(1.257573) (7.515119) (-4.284665)Adjusted R-squared=0.950141 F=124.8664二、異方差的檢驗(yàn)與修正Dependent Variable: E2Method: Least SquaresDate: 060305 Time: 18:31Sample(adjuste

25、d): 1993 2003Included observations: 11 after adjusting endpointsVariable Coefficient Std. Error t-Statistic Prob.C 4.33E+11 1.37E+12 0.314942 0.7620E2(-1)3.4755720.8320874.1769320.0042E2(-2)-3.8674531.376776-2.8090650.0262E2(-3)1.4041651.1176241.2563840.2493R-squared 0.827082Mean dependent var 2.96E+12Adjusted R-squared 0.752974S.D. dependent var 3.55E+12S.E. of regression 1.76E+12Akaike info criterion59.51134Sum squared resid 2.18E+25Schwarz criterion 59.65603Log likeli