Model 1: OLS, using observations 1983-2014 (T = 32) Dependent variable: CalfCrop Coefficient Std. Error t-ratio p-value const 2694.28 3696.82 0.7288 0.4724 FeederPrice_1 3.09406 7.79828 0.3968 0.6947 AlfalfaPrice_1 2.97568 9.19335 0.3237 0.7487 CornPrice_1 272.885 180.172 1.515 0.1415 CalfCrop_1 0.926477 0.0798886 11.60 <0.0001 *** Mean dependent var 38281.53 S.D. dependent var 2347.141 Sum squared resid 5531982 S.E. of regression 452.6458 R-squared 0.967608 Adjusted R-squared 0.962809 F(4, 27) 201.6333 P-value(F) 1.09e-19 Log-likelihood 238.3712 Akaike criterion 486.7423 Schwarz criterion 494.0710 Hannan-Quinn 489.1716 rho 0.355217 Durbin's h 2.252551 a) Test for multicollinearity using the variance inflation factors (VIF). Insert the output below. Comment on what it suggests about multicollinearity in the model. Gretl: In the model output window, Tests, Collinearity. Variance Inflation Factors Minimum possible value = 1.0 Values > 10.0 may indicate a collinearity problem FeederPrice_1 7.655 AlfalfaPrice_1 16.558 CornPrice_1 8.222 CalfCrop_1 5.710 VIF(j) = 1/(1 - R(j)^2), where R(j) is the multiple correlation coefficient between variable j and the other independent variables b) Estimate the model again after dropping the lagged alfalfa price variable. The reason for dropping a variable is the high correlation between the two prices and the assumption that one of the two variables is sufficient to represent feed