Econometrics - Regression Analysis Study Guide Questions And Correct Answers

Classical linear regression model {Ans: made up of 5 assumptions E(ui given Xi) = 0, the average error (conditioned on X) is always 0. the distribution of those random errors is = 0 cov(ui,uj) = 0, when i x= j the variance of the error of one random error at a point has no effect on the variance of another andom error the other point, they are independt from eachother There is no relation between the two var(ui given Xi) = E(ui-E(ui))^2 = E(ui) = variance homoscedastic error variance, the variance of the errors is constant as x increases or decreases cov(ui, Xi) = 0 there is no relation between the variance of the error distribution of a point and said point The regression model is correctly specified, we are selecting the right sample and population.}Functional forms of regression models: lin-log {Ans: Y i=β1+β2(ln(Xi))+ei β2 measures the absolute change in Y for a relative change in X}direction of travel {Ans: changes in X having an impact on Y (important with regression)} {Ans: there is a distribution of points around every exogenous variables conditional mean, this distribution is u. The difference between actual data point and the