数学建模-统计与回归

hecurrentworkspace.beta3,rmse3beta3=9.47894.556319.91280.31360.0129-2.7739rmse3=3.2108故回归模型为:,剩余标准差为3.2108(3)x1=[1.54.55.02.08.56.013.58.012.57.56.58.07.58.07.512.06.02.55.07.56.0];x2=[122033111231221103010];y=[356366179479936694827865777562854357336533]';X=[ones(21,1)x1'x2'(x1.^2)'(x1.*x2)'(x2.^2)'];stepwise(X,y)x=[ones(21,1)x1'x2'(x2.^2)'];[b,bint,r,rint,stats]=regress(y,x);rcoplot(r,rint)x(17,:)=[];y(17,:)=[];[b,bint,r,rint,stats]=regress(y,x);rcoplot(r,rint)x(14,:)=[];y(14,:)=[];[b,bint,r,rint,stats]=regress(y,x);rcoplot(r,rint)b,bint,statsb=5.29135.091824.2141-3.4016bint=1.58798.99474.66695.516619.526828.9013-4.8329-1.9702stats=0.9892459.75630.00006.4484>>即;的置信区间为[1.5879,8.9947],的置信区间为[4.6669,5.5166],的置信区间为[19.5268,28.9013],的置信区间为[-4.8329,-1.9702],F=459.7563,p=0.0000P<0.05,可知回归模型显著性较好