<P><FONT size=3>consider the one-variable regression model:Yi=B0+B1Xi+ui,and suppose that it satisfies the assumption in key concept 4.3. </FONT><FONT size=3>suppose that Yi is measured with error,so that the data are &yacute;=Yi+wi,where wi is the measurement error which is i.i.d and independetn of Yi and Xi.Consider the population regression &yacute;=B0+B1+vi,where vi is the regression error using the mismeasured depdendent bariable,&yacute;.</FONT></P>
<P><FONT size=3>问题：
a.show that vi=ui+wi
b.show that the regression &yacute;=B0+B1Xi+vi satisfied the assumption in key concept 4.3.(Assume that wi is indepent of Yj and Xj
for all values of i and j has a finite fourth moment.)
c.Are the OLS estimators consistent?
d.Can confidence intervals be constructed in the ususl way?
e.Evaluate the statement:"Measrement error in the X's is a serious problem.Measurement error in Y is not."
（附带：经典回归假设条件
key concept 4.3 Yi=B0+B1Xi+ui,where:E(ui|Xi)=0; (Xi,Yi) are i.i.d;(Xi,ui) have nonzero finite fourth moments）</FONT></P>

[此贴子已经被作者于2005-1-6 12:54:01编辑过]