1.
What are the required conditions for error variable in multiple regression analysis? The Internal Revenue Service (IRS) is trying to estimate the monthly amount of unpaid taxes discovered by its auditing division. The IRS estimated this figure on the basis of field auditing labor hours and number of hours of its computers used. The table given below presents these data for the last ten months. i. Develop the estimating equation best describing these data. ii. Interpret the value of regression coefficients. iii. Estimate the actual unpaid tax for field if audit labour hours is 4200 and computer hours is 1600 hours.
$\begin{array}{|c|c|c|c|} \hline \text{Month} & (X_1) \text{ Field Audit Labor Hours in 100} & (X_2) \text{ Computer Hours in 100} & (Y) \text{ Actual Unpaid Taxes Discovered million of dollars} \\ \hline \text{Jan} & 45 & 16 & 29 \\ \text{Feb} & 42 & 14 & 24 \\ \text{Mar} & 44 & 15 & 27 \\ \text{April} & 45 & 13 & 25 \\ \text{May} & 43 & 13 & 26 \\ \text{June} & 46 & 14 & 28 \\ \text{Jul} & 44 & 16 & 30 \\ \text{Aug} & 45 & 16 & 28 \\ \text{Sep} & 44 & 15 & 28 \\ \text{Oct} & 43 & 15 & 27 \\ \hline \end{array}$
$Given \sum X_1 = 12005, \sum X_2 = 4013, \sum X_1 X_2 = 6485, \sum Y = 7428, \sum X_1^2 = 19461, \sum X_2^2 = 2173$
[10]