Hello, I have a really basic question to ask. There are two variables X and Y, which are highly correlated to each other. I have obtained a simple linear regression line Y = mX + b by minimizing the perpendicular residuals from the data points to the line (because both of my variables contain errors). However, I don't know how to estimate the variance of the regression parameters, which could be used to find out the confidence intervals. I have the book "Generalized Linear Models" by P.McCullagh and J.A. Nelder, but the math involved there is quite beyond me. Thanks for your time : )
Have a nice day Shi. . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
