ECO 391 - Final Exam Questions And All Correct Answers.

T - Answer We test the significance of a correlation coefficient in order to determine if the relationship implied by the sample correlation coefficient is real or due to chance. T - Answer An R-squared of zero is the worst possible model. F - Answer Hypothesis testing always tests whether a regression coefficient is different from T - Answer An adjusted R-squared can be used to determine if we should have added a new variable to our model. F - Answer The following is a positive/right, one-tailed hypothesis test: Ho: p ≥ 0.8 and Ha: p 0.8 T - Answer Explanatory variables, independent variables, and x-variables are all the same kind of variables, referring to the variables on the right side of a regression equation. T - Answer A partial F-test is used to test whether or not we should include a variable in our regression. F - Answer A prediction interval is the same as a confidence interval. F - Answer Multicollinearity exists when one x-variable is a perfect function of another. For this reason, it rarely occurs in the real world. F - Answer Heteroskedasticity occurs when the error term is correlated with an explanatory variable. T - Answer We can remedy heteroscedasticity using corrected standard errors, aka White's standard errors. T - Answer A common violation of OLS is that the error term is serially correlated.