您好,欢迎访问三七文档
当前位置:首页 > 电子/通信 > 综合/其它 > 数学建模作业多元统计
数学建模作业:多元统计作业Ⅳ-1回归分析某种水泥在凝固时放出的热量y(k/g)与水泥中的3CaOAl2O3的成分(%),3CaOSiO2的成分x2(%),4CaOAl2O3Fe2O3的成分x3(%),2CaOSiO2的成分x4(%)的观测值如下表,试以y为因变量,以x1,x2,x3,x4为自变量建立多元回归方程并作显著性检验。样本点x1x2x3x4y172666078.52129155274.331156820104.34113184787.6575263395.961155922109.27371176102.78131224472.59254182293.1102147426115.911140233483.8121166912113.3131068812109.4解:编写程序如下:datashuini;inputx1-x4y@@;cards;72666078.5129155274.31156820104.3113184787.675263395.91155922109.2371176102.7131224472.5254182293.12147426115.9140233483.81166912113.31068812109.4;procreg;modely=x1x2x3x4/selection=stepwise;run;运行结果如下:(1)回归方程显著性检验:AnalysisofVarianceSumofMeanSourceDFSquaresSquareFValuePrFModel22657.858591328.92930229.50.0001Error1057.904485.79045CorrectedTotal122715.76308由AnalysisofVariance表可知:FValue=229.50,PrF远小于0.05,故回归方程的线性性及各参数的显著性检验均通过。(2)参数显著性检验ParameterStandardVariableEstimateErrorTypeIISSFValuePrFIntercept52.577352.286173062.60416528.91.0001x11.468310.12130848.43186146.52.0001x20.662250.045851207.78227208.58.0001由结果可知,X1,X2均通过检验。(3)建立线性回归方程为:2166.047.158.52xxy,且拟合优度达到R2=0.9787。可知,方程拟合效果很好。Ⅳ-2聚类分析DNA是由A,T,C,G这4种碱基按一定顺序排成的序列,长短不一,其中碱基含量的百分比不同通常能揭示该序列的一些规律,试根据下表所给出的20条DNA序列的碱基含量百分比对其20条DNA序列进行分类。(注,计算式下面的数据需要转置)1234567891011121314151617181920A3330304726393931232039362833324039322422T151773212142121171555555755715129556262C19182412261411182330531190927131619G4446502047444041484511161413710151087解:编写代码如下:dataex;inputatcg@@;cards;0.29730.13510.17120.39640.27030.15320.16220.41440.27030.06310.21620.45050.42340.28830.10810.18020.23420.10810.23420.42340.35140.12610.12610.39640.35140.18920.09910.36040.27930.18920.16220.36940.20720.15320.20720.43240.18180.13640.27270.40910.35450.50000.04550.10000.32730.50000.02730.14550.25450.51820.10000.12730.30000.50000.08180.11820.29090.645500.06360.36360.46360.08180.09090.35450.26360.24550.13640.29090.50000.11820.09090.21820.56360.14550.07270.20000.56360.17270.0636;procclustermethod=singleccc;proctree;run;聚类图如下,根据动态聚类图可以看出,此处20个DNA序列分成三类较为合适,具体情况如下:观察SPRSQ,发现分三类最好第一类:4,17;第二类:1,2,3,5,6,7,8,9,10;第三类:11,12,13,14,15,16,18,19,20Ⅳ-4主成分分析某市为全面分析机械类各企业的经济效益,选择了8个不同的利润指标,14个企业关于这8个指标的统计数据如下表,试进行主成分分析并将14个企业的经济效益进行排序。解:编写主成分分析的程序如下:企业净产值利润率固定资产利润率总产值利润率销售收入利润率产品成本利润率物耗利润率人均利润率流动资金利润率140.424.77.26.18.38.72.44220.0225.012.711.211.012.920.23.5429.1313.23.33.94.34.45.50.5783.6422.36.75.63.76.07.40.1767.3534.311.87.17.18.08.91.72627.5635.612.516.416.722.829.33.01726.6722.07.89.910.212.617.60.84710.6848.413.410.99.910.913.91.77217.8940.619.119.819.029.739.62.44935.81024.88.09.88.911.916.20.78913.71112.59.74.24.24.66.50.8743.9121.80.60.70.70.81.10.0561.01332.313.99.48.39.813.32.12617.11438.59.111.39.512.216.41.32711.6dataex;inputx1-x8;cards;40.424.77.26.18.38.72.44220.025.012.711.211.012.920.23.5429.113.23.33.94.34.45.50.5783.622.36.75.63.76.07.40.1767.334.311.87.17.18.08.91.72627.535.612.516.416.722.829.33.01726.622.07.89.910.212.617.60.84710.648.413.410.99.910.913.91.77217.840.619.119.819.029.739.62.44935.824.88.09.88.911.916.20.78913.712.59.74.24.24.66.50.8743.91.80.60.70.70.81.10.0561.032.313.99.48.39.813.32.12617.138.59.111.39.512.216.41.32711.6;procprincompout=prin;varx1-x8;run;procprintdata=prin;varprin1-prin13;run;根据运行结果,以累积贡献率超过90%为标准,可选择三个主成分EigenvaluesoftheCorrelationMatrixEigenvalueDifferenceProportionCumulative16.136623515.094493210.76710.767121.042130300.606176660.13030.897330.435953650.215581580.05450.951840.220372070.068465210.02750.979450.151906860.143079420.01900.998460.008827440.005865060.00110.999570.002962380.001738590.00040.999880.001223790.00021.0000根据特征向量可以写出主成分表达式:根据特征向量可以写出主成分表达式:如第一主成分可写为如下,其它类似:8765432136.032.037.038.038.039.030.032.01xxxxxxxxprin由变量前的系数大小可见,第一主成分主要是反映总产值利润率、销售收入利润率和产品成本利润率的,是用来衡量企业经营状况的一个综合指标,其它可类似分析。另外,还可进行主成分得分分析,主成分得分的结果如下:可见,在第一主成分上得分最高的是企业9,在第二主成分上得分最高的是企业1,在第三主成分上得分最高的是企业2。Ⅳ-5因子分析有10例患者的4项肝功能指标的观测数据如下表,试作这4项指标的因子分析并对病人进行病情分析。患者转氨酶量肝大指数硫酸锌浊度胎甲球1402.05202101.553031203.0135042504.518051203.59506101.512507401.0194082704.0136091703.0960101302.03050解:编写因子分析程序如下:dataex;inputabcd;cards;402.0520101.55301203.013502504.51801203.5950101.51250401.019402704.013601703.09601302.03050;proccorrout=ex1;procfactordata=ex1outstat=ex2method=prinpriors=onerotate=orthomaxscore;procscoredata=exscore=ex2out=ex3;procprint;run;根据程序结果,按累积贡献率超过90%,选择三个公因子:为了便于解释,旋转过后的因子模式为:由此可写出:3211.022.096.0FFFa,其它类似。标准化因子得分系数如下:由此有dcbaF02.007.054.050.01,其它类似。根据上式有因子得分结果如下:在三个公因子上得分最高的患者依次是:4,10,8。Ⅳ-6典型相关分析棉花红铃虫第一代发蛾高峰日y1、第一代累计百株卵量y2、发蛾高峰日百株卵量y3及2月下旬至3月中旬的平均气温x1(℃)、1月下旬至3月上旬的日照小时累计数的常用对数x2的16组观测数据如下表,试作气象指标x1、x2与y1、y2、y3的典型相关分析。x1x2y1y2y319.2002.01418646.314.329.1002.17016930.714.038.6002.258171144.669.3410.2332.20617169.222.755.6002.06718116.07.365.3672.19717112.38.076.1332.1701742.71.388.2002.10017226.37.998.8001.983186247.185.2107.6002.14617647.712.7119.7002.074176536.25.3128.3672.102172137.658.01312.1672.284176118.943.31410.2672.24216162.729.3158.9002.28317126.28.3168.2332.068172123.932.7答案仅供参考假设:x1、x2服从二元正态分布;y1、y2、y3服从三元正态分布与多元线性回归揭示一个变量与一组变量的相关关系不同的是,典型相关分析是用于揭示了两组多元随机变量之间的相关关系。上题中为揭示两组随机变量x=(x1、x
本文标题:数学建模作业多元统计
链接地址:https://www.777doc.com/doc-2331356 .html