Simple and Multiple Regression, Evaluating Reliability of an Equation

The Lockit Company manufactures door knobs for residential homes and apartments. Lockit is considering the use of simple (single-driver) and multiple regression analyses to forecast annual sales because previous forecasts have been inaccurate. The new sales forecast will be used to initiate the budgeting process and to identify more completely the underlying process that generates sales.

Larry Abram, the controller of Lockit, has considered many possible independent variables and equations to predict sales and has narrowed his choices to four equations. Abram used annual observations from 20 prior years to estimate each of the four equations.

Following are definitions of the variables used in the four equations and a statistical summary of these equations:

Statistical Summary of Four Equations
Equation		Dependent Variable		Independent Variable (s)		Intercept		Independent Variable (Rate)		Standard Error		R Square		t-Value
1		St		St 1		$500,000		$1.10		$500,000		0.94		5.50
2		St		Gt		1,000,000		0.00001		510,000		0.90		10.00
3		St		Gt 1		900,000		0.000012		520,000		0.81		5.00
4		St				600,000				490,000		0.96
				Nt 1				10.00						4.00
				Gt				0.000002						1.50
				Gt 1				0.000003						3.00
St					= Forecasted sales in dollars for Lockit in period t
St 1					= Actual sales in dollars for Lockit in period t 1
Gt					= Forecasted U.S. gross domestic product in period t
Gt 1					= Actual U.S. gross domestic product in period t 1
Nt 1					= Lockit's net income in period t 1

Required:

1. Write Equations 2 and 4 in the form Y = a + bx. If required, round your answers to six decimal places.

Equation 2: S_t = $fill in the blank 1 + $fill in the blank 2G_t

Equation 4: S_t = $fill in the blank 3 + $fill in the blank 4N_{t 1} + $fill in the blank 5G_t + $fill in the blank 6G_{t 1}

2. If actual sales are $1,500,000 in the current year, what would be the forecasted sales for Lockit in the coming year?

$fill in the blank 7