Model 1: Y=Wage X=Age, Age squared, Female, the Education variables, Temp, and Training Model 2: Y=ln(Wage) X=Age, Age squared, Female, the Education variables, Temp, and Training Model 2 Regression output is given as follow: ^ ln (Wage) = b0 + b1Age - b2Age Squared - b3Female - b4Lowedu - b5Interedu - b6Temp + b7Training ^ ln (Wage) = 1.531800763 + 0.0657640408843982Age - 0.000681070234078206AgeSquared 0.242724910738571Female - 0.521396348970448Lowedu - 0.27099538545346Interedu 0.0752749268228716Temp + 0.10471421709815Training Note that this model 2 is exponential model or log-linear model. Note that Female, Education variables, Temp, and training are all categorical data. Dummy variables. By re-estimating Model 2 with an additional variable interacting term between Temp and Training, we get Model 3. Excel summary output of Model 3 is given as follow: QUESTION 1: State the estimated equation of regression. What does interaction term capture in this case? Is the inclusion statistically justified based on its p-value? (4marks) QUESTION 2: interpret the estimated coefficients for Temp, Training and their interaction. Has there been any change in the significance of Temp or Training when the interaction term is included? (4marks)