## Question

###### Profit Forecasting: company interested predicting prafit number of projects based explanatory variables: Measure of risk assigned at the outset of the project (X1 RISK) and the expenditure on research and development for the project (xz RD). Data on the three variables PROFIT, RISK, and RD are available in the worksheet entitled RDS_ PROFIT measured thousands of dollars and RD measured In hundreds of dollars Use the data to fit two separate regression modelsFor the first model (Linear Model AKA

Profit Forecasting: company interested predicting prafit number of projects based explanatory variables: Measure of risk assigned at the outset of the project (X1 RISK) and the expenditure on research and development for the project (xz RD). Data on the three variables PROFIT, RISK, and RD are available in the worksheet entitled RDS_ PROFIT measured thousands of dollars and RD measured In hundreds of dollars Use the data to fit two separate regression models For the first model (Linear Model AKA First Order Model) _ regress PROFIT on the two explanatory variables RISK and RD. (Hint: "Regress PROFIT on x" implies that PROFIT is the variable and is the explanatory variable:) a) State the linear mode equation_ 9 = Ro + B1X1 BzXz Y = Bo + 01*1 + 026,2) Y = Bo 01*1 62*12 Ba*z Y = Bo 064) Bz*z Y = fo 81*1 62*2 Baxz2 However; there some evidence that the relationship between RD and PROFIT is nonlinear: Therefore, next fit the second order polynomial regression model, regress PROFIT RISK, and RDSQR (the squarc of the RD variable) explanatory variables: (Hint: You will have creatc thc RDSQR variablc yoursclf: ) b} State the transformed model equation (i,ev the second order polynomial regression model equation}. Y = Po 81x1 Bz( 9 = Ro R1*1 62X2 9 = Bo + 81*1 Bzxz B3x22 9 = Bo + Bc4)+ Bzx2 9 = Bo B1*1 Bzx12 Baxz