《综合性设计性报告》由会员分享，可在线阅读，更多相关《综合性设计性报告（6页珍藏版）》请在金锄头文库上搜索。
1、数学与计算机科学系综合性、设计性项目实验报告课程名称时间序列分析开课学期2013-2014 （2）专业统计学班级11级统计一班实验地点博弈北301实验时间2014-5-29项目名称ARIMA模型项目类型综合性项目成员（姓名+学号）陈强 110314102刘刚 110314111王锐 110314119 李成飞110314108教师 评 语成绩教师签名实验报告一、实验目的通过建立 ARIMA 模型，分析研究 1880-1985 年全球地表平均温度改变值序列并利用模 型做出相应预测。二、实验仪器或设备Eviews7.2 &PC三、总体设计（设计原理、设计方案及流程等）ARIMA 模型的基本思想是：
2、将预测对象随时间推移而形成的数据序列视为一个随机序 列，用一定的数学模型来近似描述这个序列。这个模型一旦被识别后就可以从时间序列的 过去值及现在值来预测未来值。ARIMA （p, d, q）称为差分自回归移动平均模型，AR是自回归，p为自回归项；MA为 移动平均， q 为移动平均项数， d 为时间序列成为平稳时所做的差分次数。分 析 结 束四、实验步骤（包括主要步骤、代码分析等）步骤一.创建工作文件&导入数据打开 Eviews7.2 工作系统file open foreign data work file f 命名为 year ,x步骤二. 数据预处理-作出时序图Quick步骤三.模型识别&定
3、阶-作出一阶差分时序图&相关图命令：genrDate: 05/28/14 Time: 09:01Sample: 1880 1985Included! observations: 105AutocorrelationPartial CorrelationACFACQ-StatProb匚i匚i1-0.253-0.2536.90910.009i匚i匚i2-0.114-0.1908.31530.016匚i匚i3-0.158-0.26711.0810.011i】ii匚i40.045-0.13011.3010.023i匸i匸i5-0.099-0.24112.4100.030iZlii60.2150.056
4、17.6680.007匚i匚i7-0.202-0.23022.3560.002iJii80.105-0.03123.6300.003i匸i匚ig-0.106-0.16024.9370.003iii100.103-0.04926.1920.003iiii11-0.012-0.01526.2080.006iiii120.043-0.05326.4330.009i iii13-0.077-0.00427.1640.012iJiii140.1090.04428.6430.012i iii15-0.0680.04629.2280.015i| iiI i160.0350.03229.3830.021i i
5、ii17-0.0680.00829.9670.027iii |i18-0.004-0.02629.9690.038i匸ii匚i19-0.105-0.13731.4010.036iii200.135-0.00633.8270.027iii |i21-0.012-0.03733.8470.039iiii220.044-0.01634.1050.048i| iiZU230.0370.10534.2900.061匚i匸i24-0.192-0.23239.3920.025iii |i250.018-0.04539.4390.033ii260.2130.09845.8790.009i Iiii27-0.0
6、340.05046.0500.013i Lii |i28-0.094-0.03747.3270.013i| iii290.0290.05347.4470.017i匸ii |i30-0.111-0.03849.3060.015iiIEi310.020-0.09949.3680.019i丁i320.1200.08751.5950.016iiii330.0020.02451.5950.021i iii34-0.052-0.01252.0280.025iiii350.0180.04352.0800.032i匸ii匚i36-0.099-0.13453.6890.029Date: 05/28/14 Tim
7、e: 09:03Sample: 1881 1985Included observations: 105Q-statistic probabilities adjusted!for 1 ARMAterm(s)结果命名为 Eq01步骤 四. 参数 估计 &模 型检 验QuickfEstimate Equat ionf 输入 【x c MA(1 )】fAutocorrelationPartial CorrelationACFACQ-StatProbi二i二10.2380.2386.1039ii匚i2-0.084-0.1486.86490.009匚ii匚i3-0.214-0.16911.9120.00
8、3i匚ii Ii4-0.120-0.03913.5070.004i Lii Li5-0.090-0.09814.4150.006iiii60.0810.08315.1550.010ii匚i7-0.096-0.20016.2150.013iI iii80.0270.08716.3020.022i |ii 1i9-0.027-0.07716.3870.037iiii100.0890.08817.3210.044iii| i110.0610.02517.7700.059iiii120.0560.00618.1540.078iiii13-0.0060.07518.1590.111iii| iu0.06
9、30.04018.6510.134i【iii15-0.052-0.01318.9880.165i【ii |i16-0.056-0.04219.3820.197i匚ii 1i17-0.126-0.07021.3930.164i匚ii i18-0.102-0.07822.7320.158i ii 1i19-0.080-0.07423.5650.170ii】i200.0930.06524.7190.170iii |i210.053-0.04725.0940.198iI iii220.038-0.01725.2900.235iiii23-0.022-0.01825.3570.280IEi匚i24-0.
10、140-0.18628.0670.213iI ii250.0360.17128.2490.250iii260.1790.07032.8190.136iii 1i270.009-0.06032.8300.167i匸ii 1i28-0.105-0.05934.4480.153i iii29 0.0790.02435.3700.159i匚ii Li30-0.125-0.08637.7180.129iiii310.003-0.01037.7190.157iJiii320.1030.09539.3600.144iI ii 1i330.032-0.08039.5210.169i【ii 1i34-0.052
11、-0.06439.9480.189i ii |i35-0.061-0.04940.5420.204i匸ii匚i36-0.107-0.14542.4080.182Dependent Variable: D(XMethod: Least SquaresDate: 05/28/14 Time: 03:57Sample (adjusted): 1831 1935Included! observations: 105 after adjustmentsConvergence achieved after 9 iterations MA Backcast: 1330R-squared0.146492Mean dependent va.r0.004236Adjusted R-square
