房地产影响因素分析.docx
《房地产影响因素分析.docx》由会员分享，可在线阅读，更多相关《房地产影响因素分析.docx（4页珍藏版）》请在冰豆网上搜索。
房地产影响因素分析
房地产影响因素分析
房地产影响因素分析（背景）xx年以来，我国商品房销售额大幅攀升?
带动了房地产开发和城市基础设施投资的新一轮高速增长。
通过产业链的传递，进而又拉动钢材、有色金属、建材、石化等生产资料价格的快速上涨，刺激这些生产资料部门产能投资的成倍扩张，最后导致全社会固定资产投资规模过大、增速过快情况的出现。
房价过快上涨在推动投资增长过快的同时，已经成为抑制消费的重要因素。
房地产价格本身呈自然上涨趋势，房价中长期趋势总是看涨。
随着我国经济发展，居民可支配收入提高，民间资金雄厚，大量资金需要寻找投资渠道，而股票市场等投资渠道目前又处于低迷状态，这是房地产投资需求不断扩大的经济背景。
强劲的CPI上涨说明当前的房价上涨并非孤立，是有其宏观经济背景的。
宏观调控能否有效防止局部行业过热出现反弹，其中的关键就是要继续加强和完善对房地产业的调控。
（引言）国际上关于房地产有一种普遍的观点：
人均收入超过1000美元，房地产市场呈现高速发展阶段。
欧美等发达国家基本都经历了这样一个阶段。
我们这篇论文，主要探讨房地产影响因素分析，主要从人均收入对房地产长期发展*阐述。
年份X1X2X3Y19902551.7361510.16222704.331919911111.2361700.6233.3786.19351992590.59982026.6253.4994.655519932897.0192577.4294.21291.45619943532.4713496.2367.81408.63919953983.0814282.95429.61590.86319964071.1814838.9467.41806.39919973527.5365160.3481.91997.16119982966.0575425.14792062.56919992818.8055854472.82052.620002674.2646279.98476.62111.617xx2830.6886859.6479.92169.719xx2906.167702.8475.12250.177xx3011.4248472.2479.42359.499xx3441.629421.6495.22713.878
X1=建材成本（元/平方米）X2=居民人均收入（元）X3=物价指数Y=房地产价格（元/平方米）初定模型：
Y=c+a1*x1+a2*x2+a3*x3+etDependentVariable:
YMethod:
LeastSquaresDate:
06/05/05Time:
23:
04Sample:
1990xxIncludedobservations:
15VariableCoefficientStd.Errort-StatisticProb.X32.5375780.5904224.2979080.0013X20.1464950.0209686.9865680.0000X1-0.0180160.035019-0.5144470.6171C33.20929118.27470.2807810.7841R-squared0.983094Meandependentvar1753.317AdjustedR-squared0.978483S.D.dependentvar600.9536S.E.ofregression88.15143Akaikeinfocriterion12.01917Sumsquaredresid85477.42Schwarzcriterion12.20798Loglikelihood-86.14376F-statistic213.2186Durbin-Watsonstat1.504263Prob（F-statistic）0.000000
一：
多元线性回归DependentVariable:
YMethod:
LeastSquaresDate:
06/05/05Time:
23:
05Sample:
1990xxIncludedobservations:
15VariableCoefficientStd.Errort-StatisticProb.X10.3360100.1510842.2239990.0445C792.0169453.44601.7466620.1043R-squared0.275612Meandependentvar1753.317AdjustedR-squared0.219889S.D.dependentvar600.9536S.E.ofregression530.7855Akaikeinfocriterion15.51016Sumsquaredresid3662533.Schwarzcriterion15.60457Loglikelihood-114.3262F-statistic4.946171Durbin-Watsonstat0.275870Prob（F-statistic）0.044490
DependentVariable:
YMethod:
LeastSquaresDate:
06/05/05Time:
23:
09Sample:
1990xxIncludedobservations:
15VariableCoefficientStd.Errort-StatisticProb.X35.5017790.52507510.478090.0000C-486.8605220.1227-2.2117690.0455R-squared0.894128Meandependentvar1753.317AdjustedR-squared0.885984S.D.dependentvar600.9536S.E.ofregression202.9191Akaikeinfocriterion13.58706Sumsquaredresid535290.2Schwarzcriterion13.68146Loglikelihood-99.90293F-statistic109.7903Durbin-Watsonstat0.440527Prob（F-statistic）0.000000
DependentVariable:
YMethod:
LeastSquaresDate:
06/05/05Time:
23:
10Sample:
1990xxIncludedobservations:
15VariableCoefficientStd.Errort-StatisticProb.X20.2363470.01587914.884170.0000C561.997588.563336.3457130.0000R-squared0.944572Meandependentvar1753.317AdjustedR-squared0.940308S.D.dependentvar600.9536S.E.ofregression146.8243Akaikeinfocriterion12.93992Sumsquaredresid280245.9Schwarzcriterion13.03432Loglikelihood-95.04937F-statistic221.5384Durbin-Watsonstat0.475648Prob（F-statistic）0.000000
DependentVariable:
YMethod:
LeastSquaresDate:
06/07/05Time:
21:
42Sample:
1990xxIncludedobservations:
15VariableCoefficientStd.Errort-StatisticProb.X32.3558330.4583405.1399230.0002X20.1500860.0191577.8347140.0000C37.56794114.29910.3286810.7481R-squared0.982687Meandependentvar1753.317AdjustedR-squared0.979802S.D.dependentvar600.9536S.E.ofregression85.40783Akaikeinfocriterion11.90961Sumsquaredresid87533.98Schwarzcriterion12.05122Loglikelihood-86.32207F-statistic340.5649Durbin-Watsonstat1.408298Prob（F-statistic）0.000000
得到结果发现，ｘ１的系数小，然后对ｙ与ｘ１回归可决系数小，相关性差，剔出这个因素。
因为价格更多取决于供需关系。
修正之后为：
Y＝c+a2*x2+a3*x3＋et二：
多重线性分析：
三个表如上：
X2与X3存在多重共线性，1.0000000.8760730.8760731.000000
DependentVariable:
YMethod:
LeastSquaresDate:
06/05/05Time:
23:
09Sample:
1990xxIncludedobservations:
15VariableCoefficientStd.Errort-StatisticProb.X35.5017790.52507510.478090.0000C-486.8605220.1227-2.2117690.0455R-squared0.894128Meandependentvar1753.317AdjustedR-squared0.885984S.D.dependentvar600.9536S.E.ofregression202.9191Akaikeinfocriterion13.58706Sumsquaredresid535290.2Schwarzcriterion13.68146Loglikelihood-99.90293F-statistic109.7903Durbin-Watsonstat0.440527Prob（F-statistic）0.000000
Sample:
1990xxIncludedobservations:
15VariableCoefficientStd.Errort-StatisticProb.X20.2363470.01587914.884170.0000C561.997588.563336.3457130.0000R-squared0.944572Meandependentvar1753.317AdjustedR-squared0.940308S.D.dependentvar600.9536S.E.ofregression146.8243Akaikeinfocriterion12.93992Sumsquaredresid280245.9Schwarzcriterion13.03432Loglikelihood-95.04937F-statistic221.5384Durbin-Watsonstat0.475648Prob（F-statistic）0.000000
由于引入物价指数改善小，所以模型仅一步改进为：
Y＝c+a2*x2＋et
三：
异方差检验：
ARCHTest:
F-statistic1.315031Probability0.335173Obs*R-squared3.963227Probability0.265462TestEquation:
DependentVariable:
RESID^2Method:
LeastSquaresDate:
06/05/05Time:
23:
46Sample（adjusted）:
1993xxIncludedobservations:
12afteradjustingendpointsVariableCoefficientStd.Errort-StatisticProb.C22737.9410296.612.2082950.0582RESID^2（-1）0.2419520.3831440.6314930.5453RESID^2（-2）-0.3277690.404787-0.8097340.4415RESID^2（-3）-0.2737200.378355-0.7234490.4900R-squared0.330269Meandependentvar16705.23AdjustedR-squared0.079120S.D.dependentvar18205.33S.E.ofregression17470.29Akaikeinfocriterion22.63559Sumsquaredresid2.44E+09Schwarzcriterion22.79723Loglikelihood-131.8136F-statistic1.315031Durbin-Watsonstat1.842435Prob（F-statistic）0.335173
ＡＲＣＨ＝３．９６３＜临界值７．８１４７３所以无异方差WhiteHeteroskedasticityTest:
F-statistic0.159291Probability0.854522Obs*R-squared0.387928Probability0.823687TestEquation:
DependentVariable:
RESID^2Method:
LeastSquaresDate:
06/05/05Time:
23:
46Sample:
1990xxIncludedobservations:
15VariableCoefficientStd.Errort-StatisticProb.C31063.2822612.201.3737400.1946X2-5.0557549.640127-0.5244490.6095X2^20.0004210.0009070.4646050.6505R-squared0.025862Meandependentvar18683.06AdjustedR-squared-0.136494S.D.dependentvar18673.13S.E.ofregression19906.77Akaikeinfocriterion22.81236Sumsquaredresid4.76E+09Schwarzcriterion22.95397Loglikelihood-168.0927F-statistic0.159291Durbin-Watsonstat1.357657Prob（F-statistic）0.854522
ＷＨＩＴＥ＝０．３８７９＜临界值７．８１４７３无异方差。
四：
自相关分析：
ＤＷ＝０．４７５６查表的ｄｌ＝１．０７７ｄｕ＝１．３６１存在自相关广义差分法修正：
ρ＝１－０．４７５６／２＝０．７６２２DependentVariable:
DYMethod:
LeastSquaresDate:
06/06/05Time:
00:
18Sample（adjusted）:
1991xxIncludedobservations:
14afteradjustingendpointsVariableCoefficientStd.Errort-StatisticProb.DX20.1820860.0349185.2146550.0002C236.558963.273883.7386500.0028R-squared0.693820Meandependentvar544.1620AdjustedR-squared0.668305S.D.dependentvar148.7133S.E.ofregression85.64840Akaikeinfocriterion11.86994Sumsquaredresid88027.77Schwarzcriterion11.96124Loglikelihood-81.08959F-statistic27.19263Durbin-Watsonstat1.584278Prob（F-statistic）0.000217
得出：
回归后可决系数降低，考虑其他方法。
1．迭代法：
表：
发现可决系数提高，Ｆ统计量提高，ＤＷ＝１．５５４７〉１．３６１已经无自相关。
结论：
Y－bY（－１）＝ｃ*（１－ｂ）＋a2*（x2－b*x2（－１））+et
由下表的b=0.681C=561.9975a2=0.236347179.2772Y*=Y－0.681Y（－１）X*=x2－0.681*x2（－１）Y*=179.2272+0.2363X*+et
Method:
LeastSquaresDate:
06/07/05Time:
20:
57Sample（adjusted）:
1991xxIncludedobservations:
14afteradjustingendpointsVariableCoefficientStd.Errort-StatisticProb.E20.6805090.1776963.8296240.0024C11.6877324.888250.4696080.6471R-squared0.549989Meandependentvar15.32764AdjustedR-squared0.512488S.D.dependentvar133.2751S.E.ofregression93.05539Akaikeinfocriterion12.03583Sumsquaredresid103911.7Schwarzcriterion12.12712Loglikelihood-82.25081F-statistic14.66602Durbin-Watsonstat1.313042Prob（F-statistic）0.002397
2．改进模型方程（对数法，然后用迭代法）：
Lｙ－ｂLｙ（－１）＝ｃ＊（１－ｂ）＋ａ２＊（Lｘ２－ｂ＊Lｘ２（－１）可决系数很高，F统计量相对1中也有提高，DW=1.81>1.361无自相关。
DependentVariable:
LYMethod:
LeastSquaresDate:
06/06/05Time:
10:
24Sample（adjusted）:
1991xxIncludedobservations:
14afteradjustingendpointsConvergenceachievedafter7iterationsVariableCoefficientStd.Errort-StatisticProb.LX20.5862030.1002435.8477990.0001C2.5258100.8823502.8625940.0154AR
（1）0.5671440.2204572.5725890.0259R-squared0.980054Meandependentvar7.460096AdjustedR-squared0.976428S.D.dependentvar0.351331S.E.ofregression0.053941Akaikeinfocriterion-2.814442Sumsquaredresid0.03xxSchwarzcriterion-2.677501Loglikelihood22.70109F-statistic270.2458Durbin-Watsonstat1.810100Prob（F-statistic）0.000000InvertedARRoots.57
DependentVariable:
E1Method:
LeastSquaresDate:
06/07/05Time:
21:
00Sample（adjusted）:
1991xxIncludedobservations:
14afteradjustingendpointsVariableCoefficientStd.Errort-StatisticProb.E20.5017840.2195612.2853940.0413C0.0066390.0150690.4406000.6673R-squared0.303258Meandependentvar0.007495AdjustedR-squared0.245197S.D.dependentvar0.064877S.E.ofregression0.056365Akaikeinfocriterion-2.782368Sumsquaredresid0.038124Schwarzcriterion-2.691074Loglikelihood21.47658F-statistic5.223026Durbin-Watsonstat1.517853Prob（F-statistic）0.041274
用1，2两种修正，两种效果都很好，都消除了自相关，相比较2更好。
所以，方程：
b=0.502Y*=Lｙ－o.502*Lｙ（－１）X*=Lx2－0.502*Lx2（－１）Y*=1.2579+0.5862X*+et
以上就是通过分析和检验得到的回归方程。
所以，人均收入水平的高低在一定程度上影响房地产价格。
当前的房地产价格增长背后收入是不可忽略的因素。
：
中经网，国家*网站，
内容仅供参考
升级会员 