Baidu
map

线性回归中非多重共线性假定与解决方案(2)

2013-12-18 MedSci MedSci原创

>t            (7.40) 由于xt 1,xt 2存在多重共线性,因而从模型中剔除xt 2。模型(7.40) 变成    yt= b0 + b1* xt 1+ ut *    &

第五节 多重共线性的解决方案 完全不存在多重共线性是一个很强的假定。实际中,经 济变量随着经济形势的起伏,总要表现出某种程度的共同变化特征。当然,完全多重共线性在实际经济问题中很少见,所以多重共线性的一般表现形式是不完全多重 共线性。当解释变量间存在不完全多重共线性时。主要是对回归系数的估计带来严重后果。尽管回归系数的普通最小二乘估计量仍具有无偏性,但由于回归系数估计 量的方差变大,使回归系数估计量的抽样精度下降,的值有可能远离真值bj,从而使回归系数估计值变得毫无意义。 为克服模型中的多重共线性,下面介绍几种方法。 1. 直接合并解释变量     当模型中存在多重共线性时,在不失去实际意义的前提下,可以把有关的解释变量直接合并,从而降低或消除多重共线性。 继续看例7.2。如果研究的目的是预测全国货运量,那么可以把重工业总产值和轻工业总产值合并为工业总产值,从而使模型中的解释变量个数减少到两个以消除多重共线性。甚至还可以与农业总产值合并,变为工农业总产值。解释变量变成了一个,自然消除了多重共线性。 2. 利用已知信息合并解释变量  &

版权声明:
本网站所有内容来源注明为“梅斯医学”或“MedSci原创”的文字、图片和音视频资料,版权均属于梅斯医学所有。非经授权,任何媒体、网站或个人不得转载,授权转载时须注明来源为“梅斯医学”。其它来源的文章系转载文章,或“梅斯号”自媒体发布的文章,仅系出于传递更多信息之目的,本站仅负责审核内容合规,其内容不代表本站立场,本站不负责内容的准确性和版权。如果存在侵权、或不希望被转载的媒体或个人可与我们联系,我们将立即进行删除处理。
在此留言
评论区 (3)
#插入话题
  1. [GetPortalCommentsPageByObjectIdResponse(id=1987975, encodeId=f6a0198e97530, content=<a href='/topic/show?id=446a91002d6' target=_blank style='color:#2F92EE;'>#解决方案#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=82, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=91002, encryptionId=446a91002d6, topicName=解决方案)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=c279140, createdName=vividelife, createdTime=Sun Jan 05 09:46:00 CST 2014, time=2014-01-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1946394, encodeId=30e71946394c1, content=<a href='/topic/show?id=184f30033b6' target=_blank style='color:#2F92EE;'>#共线性#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=75, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=30033, encryptionId=184f30033b6, topicName=共线性)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=9cb02500048, createdName=ms6832696159214430, createdTime=Wed Mar 26 10:46:00 CST 2014, time=2014-03-26, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1701378, encodeId=dde71e013789e, content=<a href='/topic/show?id=214ee756845' target=_blank style='color:#2F92EE;'>#线性回归#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=75, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=77568, encryptionId=214ee756845, topicName=线性回归)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=748630348850, createdName=天堂的云, createdTime=Tue Jan 28 06:46:00 CST 2014, time=2014-01-28, status=1, ipAttribution=)]
  2. [GetPortalCommentsPageByObjectIdResponse(id=1987975, encodeId=f6a0198e97530, content=<a href='/topic/show?id=446a91002d6' target=_blank style='color:#2F92EE;'>#解决方案#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=82, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=91002, encryptionId=446a91002d6, topicName=解决方案)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=c279140, createdName=vividelife, createdTime=Sun Jan 05 09:46:00 CST 2014, time=2014-01-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1946394, encodeId=30e71946394c1, content=<a href='/topic/show?id=184f30033b6' target=_blank style='color:#2F92EE;'>#共线性#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=75, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=30033, encryptionId=184f30033b6, topicName=共线性)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=9cb02500048, createdName=ms6832696159214430, createdTime=Wed Mar 26 10:46:00 CST 2014, time=2014-03-26, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1701378, encodeId=dde71e013789e, content=<a href='/topic/show?id=214ee756845' target=_blank style='color:#2F92EE;'>#线性回归#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=75, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=77568, encryptionId=214ee756845, topicName=线性回归)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=748630348850, createdName=天堂的云, createdTime=Tue Jan 28 06:46:00 CST 2014, time=2014-01-28, status=1, ipAttribution=)]
  3. [GetPortalCommentsPageByObjectIdResponse(id=1987975, encodeId=f6a0198e97530, content=<a href='/topic/show?id=446a91002d6' target=_blank style='color:#2F92EE;'>#解决方案#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=82, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=91002, encryptionId=446a91002d6, topicName=解决方案)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=c279140, createdName=vividelife, createdTime=Sun Jan 05 09:46:00 CST 2014, time=2014-01-05, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1946394, encodeId=30e71946394c1, content=<a href='/topic/show?id=184f30033b6' target=_blank style='color:#2F92EE;'>#共线性#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=75, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=30033, encryptionId=184f30033b6, topicName=共线性)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=9cb02500048, createdName=ms6832696159214430, createdTime=Wed Mar 26 10:46:00 CST 2014, time=2014-03-26, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1701378, encodeId=dde71e013789e, content=<a href='/topic/show?id=214ee756845' target=_blank style='color:#2F92EE;'>#线性回归#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=75, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=77568, encryptionId=214ee756845, topicName=线性回归)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=748630348850, createdName=天堂的云, createdTime=Tue Jan 28 06:46:00 CST 2014, time=2014-01-28, status=1, ipAttribution=)]

相关资讯

线性回归中非多重共线性假定与解决方案(1)

span>                 (7.27)        (7.28)当样本容量增大时,和也增大,而趋近于总体相关系数,为某一个确定的值,所以与均趋于减小,从而提高了

Spine:术前冠状位脊柱不平衡对术后功能无显著影响

脊柱畸形矫正时恢复脊柱冠状位和矢状位的平衡一直是脊柱外科医生工作的主要目标。从术后X片的角度来说,大部分患者均能达到矢状位和冠状位矫形的平衡,但其最终的临床功能预后确并不一定好,对脊柱外科医生而言,如何达到完美矫正畸形目的的同时改善患者的功能预后一直是一个挑战。既往已有对矫形术后影像学X片和矫形功能预后相关性进行的研究,矢状位不平衡会对患者术后产生不利影响,如疼痛增加,功能预后变差等,该结论不前已

Baidu
map
Baidu
map
Baidu
map