A manager is hoping to estimate the relationship between quarterly advertising expenditures, and sales, in the same quarter. The model is motivated by the assumption that there is a linear relationship between the two variables and anticipates an intercept (Alpha) of 0 based on a best-fit least squares line. The model appears below:

Sales= Intercept + Beta * (Advertising Budget) + (residuals)

Historical data was gathered on both variables over the last 5 years (60 observations of each). Regression results appear in the table below. Use it to answer the questions which follow:

SUMMARY
Regression Statistics
Multiple R	0.49888
R Square	0.24889
Adjusted R Square	0.23571
Standard Error	0.05926
Observations	59
ANOVA
	df	SS	MS	F	Significance F
Regression	1	0.0663	0.0663	18.887	5.7764E-05
Residual	57	0.20022	0.0035
Total	58	0.26656
	Coefficients	Standard Error	t Stat	P-value	Lower 95%	Upper 95%
Intercept	0.006886	0.0077	0.892	0.376	-0.00857	0.02234
Advertising	6.7716	1.5581	4.346	5.7E-05	3.651	9.8916

a) With a benchmark 95% confidence, can we reject the null hypothesis that (Intercept = 0)?

b) What would be the consequence of the manager committing a Type 1 error regarding the slope coefficient on Advertising Budget?

c) If $5 worth of sales is required to cover each $1 worth of advertising, are you 95% confident that an increase in the advertising budget would pay for itself?

d) why it is unlikely that this relationship is linear across all amounts for Advertising Budget.