Scribd
Upload
23 views1 page

Practice Questions

This document asks several questions about properties of regression models: (1) It asks whether certain statements about correlation, OLS estimators, and residuals are true, false, or uncertain. (2) It asks about the estimators and variances of coefficients in two regression models, and the advantage of one model over the other. (3) It asks about estimating a regression model without an intercept term, and whether adding an intercept makes sense. (4) It asks whether additional statements about means, intercepts, regression lines, and coefficients of determination are true, false, or uncertain.

Uploaded by

Ravi Kant Soni
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
23 views1 page

Practice Questions

This document asks several questions about properties of regression models: (1) It asks whether certain statements about correlation, OLS estimators, and residuals are true, false, or uncertain. (2) It asks about the estimators and variances of coefficients in two regression models, and the advantage of one model over the other. (3) It asks about estimating a regression model without an intercept term, and whether adding an intercept makes sense. (4) It asks whether additional statements about means, intercepts, regression lines, and coefficients of determination are true, false, or uncertain.

Uploaded by

Ravi Kant Soni
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 1

(1) Explain whether the following are true, false, or uncertain: (a) If the correlation between two random

variables is zero, there is no relationship between these variables. (b) Even if the error term in the CLRM is not normally distributed, the OLS estimators are unbiased. (c) If there is no intercept in the regression model, the estimated errors will not sum to zero. (d) In a regression model with an intercept term, the sum of the residuals is always zero. (e) The conditional and unconditional means of a random variable are the same. (2) Consider the following PRFs: Model I: Yi = b1 + b2*Xi + ui Model II: Yi = a1 + a2*(Xi X ) + ui (a) Find the estimators of b1 and a1. Are they identical? Are their variances identical? (b) Find the estimators of b2 and a2. Are they identical? Are their variances identical? (c) What is the advantage, if any, of model II over model I? (3) Given the model Yi = b1 + ui find the OLS estimator of b1. What is its variance, and the RSS? Does the estimated b1 make intuitive sense? Instead of the given model, is it worth estimating the model Yi = b1 + b2*Xi + ui? If not, why bother with regression analysis? (4) Explain whether the following are true, false, or uncertain: (a) The conditional and unconditional means of the errors in the PRF (in the context of the population) are the same. (b) In the two-variable PRF if the slope coefficient is zero, the intercept coefficient is estimated by the sample mean Y . (c) The regression line yi = b1 + b2*xi + ui , where xi = (Xi X ) and yi = (Yi Y ), must pass through the origin. (d) The regression line Yi = b1 + b2*Xi + ui passes through the point ( X , Y ). (e) The coefficient of determination in a simple linear regression model without an intercept term may be negative.

You might also like