A credit card company is trying to understand and even predict annual charges that a customer will make on their cards using 5 variables: annual income (in $1000), household size, years of post-high school education (labeled simply "Education"), hours per week watching television (labeled "TV Hours") and age of the primary card holder.

They collect data on 100 randomly selected customers and measure the variables described above. They then perform a multiple regression analysis and find the results shown in the questions below.

Important Note: While the scenario above applies to all of the questions below, the output shown in different questions may change from question to question. Please be careful that you use the appropriate output for each question.

For this question, use the following multiple regression output (which may differ from the output in other questions, even though the variables are the same).

SUMMARY OUTPUT
Regression Statistics
Multiple R	0.534
R Square	0.285
Adjusted R Square	0.247
Standard Error	4791.473
Observations	100
ANOVA
	df	SS	MS	F	Significance F
Regression	5	859571711.8	1.72E+08	7.488	5.940E-06
Residual	94	2158071843	22958211
Total	99	3017643555
	Coefficients	Standard Error	t Stat	P-value	Lower 95%	Upper 95%
Intercept	3637.638	2700.353	1.347	0.1812	-1723.976	8999.252
Annual Income ($1000)	108.876	19.008	5.728	1.216E-07	71.135	146.617
Household Size	285.883	218.539	1.308	0.1940	-148.032	719.797
Education	-200.021	320.557	-0.624	0.5342	-836.494	436.451
TV Hours	-3.683	28.451	-0.129	0.8973	-60.175	52.808
Age	-10.82	46.632	-0.232	0.817	-103.41	81.769

Develop the estimated regression equation relating all of the independent variables included in the data to annual charges.If required, round your answer to three decimal places. For subtractive or negative numbers use a minus sign even if there is a + sign before the blank. (Example: -300)

Estimated Amount Charged = + *Annual Income ($1000s)+ *Household Size+ *Education+ *TV+ *Age