Mathematical Statistics with Applications, 7 edition ISM_Chapter08F

Mathematical Statistics with Applications, 7 edition ISM_Chapter08F

ID:42656864

大小:203.75 KB

页数:22页

时间:2019-09-19

Mathematical Statistics with Applications, 7 edition ISM_Chapter08F_第1页
Mathematical Statistics with Applications, 7 edition ISM_Chapter08F_第2页
Mathematical Statistics with Applications, 7 edition ISM_Chapter08F_第3页
Mathematical Statistics with Applications, 7 edition ISM_Chapter08F_第4页
Mathematical Statistics with Applications, 7 edition ISM_Chapter08F_第5页
资源描述:

《Mathematical Statistics with Applications, 7 edition ISM_Chapter08F》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、Chapter8:Estimation8.1LetB=B(θˆ).Then,2MSE(θˆ)=E[](θˆ−θ)2=E[(θˆ−E(θˆ)+B)2]=E⎡(θˆ−E(θˆ))⎤+E(B2)+2B×E[]θˆ−E(θˆ)⎢⎣⎥⎦2=V(θˆ)+B.8.2a.TheestimatorθˆisunbiasedifE(θˆ)=θ.Thus,B(θˆ)=0.b.E(θˆ)=θ+5.8.3a.UsingDefinition8.3,B(θˆ)=aθ+b–θ=(a–1)θ+b.*b.Letθˆ=(θˆ−b)/a.8.4a.Theyareequal.b.MSE(θˆ)>V(θˆ).

2、**28.5a.NotethatE(θˆ)=θandV(θˆ)=V[(θˆ−b)/a]=V(θˆ)/a.Then,**2MSE(θˆ)=V(θˆ)=V(θˆ)/a.2b.NotethatMSE(θˆ)=V(θˆ)+B(θˆ)=V(θˆ)+[(a−1)θ+b].Asufficientlylargevalueof*awillforceMSE(θˆ)MSE(θˆ).Example:a=.5,b=0.8.6a.E(θˆ)=aE(θˆ)+(1−a)E(θˆ

3、)=aθ+(1−a)θ=θ.312b.V(θˆ)=a2V(θˆ)+(1−a)2V(θˆ)=a2σ2+(1−a)σ2,sinceitwasassumedthatθˆand312121θˆareindependent.TominimizeV(θˆ),wecantakethefirstderivative(with23respecttoa),setitequaltozero,tofind2σ2a=.22σ+σ12(Oneshouldverifythatthesecondderivativetestshowsthatthisisindeedaminimum.)8.7Fol

4、lowingEx.8.6butwiththeconditionthatθˆandθˆarenotindependent,wefind12222V(θˆ)=aσ+(1−a)σ+2a(1−a)c.312Usingthesamemethodw/derivatives,theminimumisfoundtobe2σ−c2a=.22σ+σ−2c12158Chapter8:Estimation159Instructor’sSolutionsManual8.8a.Notethatθˆ1,θˆ2,θˆ3andθˆ5aresimplelinearcombinationsofY1,Y

5、2,andY3.So,itiseasilyshownthatallfouroftheseestimatorsareunbiased.FromEx.6.81itwasshownthatθˆhasanexponentialdistributionwithmeanθ/3,sothisestimatorisbiased.4b.ItiseasilyshownthatV(θˆ)=θ2,V(θˆ)=θ2/2,V(θˆ)=5θ2/9,andV(θˆ)=θ2/9,so1235theestimatorθˆisunbiasedandhasthesmallestvariance.58.9

6、Thedensityisintheformoftheexponentialwithmeanθ+1.WeknowthatYisunbiasedforthemeanθ+1,soanunbiasedestimatorforθissimplyY–1.8.10a.ForthePoissondistribution,E(Y)=λandsofortherandomsample,E(Y)=λ.Thus,theestimatorλˆ=Yisunbiased.2222b.TheresultfollowsfromE(Y)=λandE(Y)=V(Y)+λ=2λ,soE(C)=4λ+λ.2

7、2222c.SinceE(Y)=λandE(Y)=V(Y)+[E(Y)]=λ/n+λ=λ(1+1/n).Then,we2canconstructanunbiasedestimatorθˆ=Y+Y(4−1/n).8.11Thethirdcentralmomentisdefinedas3332E[(Y−μ)]=E[(Y−3)]=E(Y)−9E(Y)+54.Usingtheunbiasedestimatesθˆandθˆ,itcaneasilybeshownthatθˆ–9θˆ+54isan2332unbiasedestimator.8.12a.Fortheunifor

8、mdist

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。