An advertising firm wishes to demonstrate to its clients the effectiveness of the advertising campaigns it has conducted. The following bivariate data on fifteen recent campaigns, including the cost of each campaign (in millions of dollars) and the resulting percentage increase in sales following the campaign, were presented by the firm. Based on these data, we would compute the least-squares regression line to be =y+6.110.20x

, with

x

representing campaign cost and

y

representing the resulting percentage increase in sales. (This line is shown in Figure 1, along with a scatter plot of the data.)

Campaign cost, x
(in millions of dollars) Increase in sales, y
(percent)
1.96 6.57
3.73 6.99
2.47 6.57
2.02 6.75
2.94 6.50
1.64 6.59
3.16 6.86
3.30 6.58
3.46 6.85
1.30 6.33
3.63 6.78
1.81 6.16
excelw. gif Send data
to Excel
x

1

1.5

2

2.5

3

3.5

4

y

6

6.2

6.4

6.6

6.8

7

7.2

0

Answer the following:

1. Fill in the blank: For these data, values for percentage increase in sales that are less than the mean of the values for percentage increase in sales tend to be paired with values for campaign cost that are the mean of the values for campaign cost. Choose onegreater thanless than
2. Fill in the blank: According to the regression equation, for an increase of one million dollars in advertising campaign cost, there is a corresponding of 0.20 percent in sales. Choose oneincreasedecrease
3. What was the observed percentage increase in sales when the advertising campaign cost was 1.30 million dollars?
4. From the regression equation, what is the predicted percentage increase in sales when the advertising campaign cost is 1.30 million dollars? (Round your answer to at least two decimal places.)