A CEO of a large pharmaceutical company would like to determine if he should be placing more ...

A CEO of a large   pharmaceutical company would like to determine if he should be placing more   money allotted in the budget next year for television advertising of a new   drug marketed for controlling asthma. He wonders whether there is a strong   relationship between the amount of money spent on television advertising for   this new drug called XBC and the number of orders received. The manufacturing   process of this drug is very difficult and requires stability so the CEO   would prefer to generate a stable number of orders. The cost of advertising   is always an important consideration in the phase I roll-out of a new drug.   Data that have been collected over the past 20 months indicate the amount of   money spent of television advertising and the number of orders received.    The   use of linear regression is a critical tool for a manager's decision-making   ability. Please carefully read the example below and try to answer the   questions in terms of the problem context. The results are as follows: 

       Month Advertising Cost (thousands of   dollars), x Number of Orders, y   1 $68.93  4,902,000   2 72.62 3,893,000   3 79.58 5,299,000   4 58.67 4,130,000   5 69.18 4,367,000   6 70.14 5,111,000   7 83.37 3,923,000   8 68.88 4,935,000   9 82.99 5,276,000   10 75.23 4,654,000   11 81.38 4,598,000   12 52.9 2,967,000   13 61.27 3,999,000   14 79.19 4,345,000   15 80.03 4,934,000   16 78.21 4,653,000   17 83.77 5,625,000   18 62.53 3,978,000   19 88.76 4,999,000   20 72.64 5,834,000  

     a. Set   up a scatter diagram and calculate the associated correlation coefficient.   Discuss how strong you think the relationship is between the amount of money   spent on television advertising and the number of orders received. Please use   the Correlation procedures within Excel under Tools   > Data Analysis. The Scatterplot can more   easily be generated using the Chart procedure.         b.   Assuming there is a statistically significant relationship, use the least   squares method to find the regression equation to predict   the advertising costs based on the number of   orders received. Please use the regression procedure within Excel under Tools > Data Analysis to   construct this equation.          c.   Interpret the meaning of the slope, b1, in the regression equation.          d. Predict   the monthly advertising cost when the number of orders is 5,100,000. (Hint:   Be very careful with assigning the dependent variable for this problem)          e. Compute   the coefficient of determination, r2, and interpret its meaning.          SEE =   572901.30. This is the amount by which the model under-predicts or   over-predicts.