In: Statistics and Probability
Advertisement ($'000) Sales ($'000)
1068 4489
1026 5611
767 3290
885 4113
1156 4883
1146 5425
892 4414
938 5506
769 3346
677 3673
1184 6542
1009 5088
Solution:
· Construct a scatter plot with this data.
The required scatter plot is given as below:
· Do you observe a relationship between both variables?
From above scatterplot we observe the positive linear relationship or association between the two variables.
· Use Excel to fit a linear regression line to the data. What is the fitted regression model?
The regression model by using Excel is given as below:
Regression Statistics |
||||||
Multiple R |
0.823733298 |
|||||
R Square |
0.678536546 |
|||||
Adjusted R Square |
0.6463902 |
|||||
Standard Error |
592.7335727 |
|||||
Observations |
12 |
|||||
ANOVA |
||||||
df |
SS |
MS |
F |
Significance F |
||
Regression |
1 |
7415845.784 |
7415845.784 |
21.10773517 |
0.00098869 |
|
Residual |
10 |
3513330.883 |
351333.0883 |
|||
Total |
11 |
10929176.67 |
||||
Coefficients |
Standard Error |
t Stat |
P-value |
Lower 95% |
Upper 95% |
|
Intercept |
-25.16823406 |
1042.259927 |
-0.024147752 |
0.981209823 |
-2347.468062 |
2297.131593 |
Advertisement |
4.921595798 |
1.071235915 |
4.594315528 |
0.00098869 |
2.534733447 |
7.30845815 |
The regression equation is given as below:
Sales = -25.16823406 + 4.921595798*Advertisement
· What is the slope? What does the slope tell us?Is the slope significant?
The slope is given as b = 4.921595798. The slope tell us that there is an increment of 4.92 ($’000) in the sales as there is an increment of $1000 on advertisement.
The slope is statistically significant because corresponding p-value is given as 0.00098869 which is less than alpha value 0.05.
· What is the intercept? Is it meaningful?
The value of intercept is given as -25.16823406.
The intercept is not meaningful, because corresponding p-value is given as 0.9812 which is greater than alpha value 0.05.
· What is the value of the regression coefficient, r? What is the value of the coefficient of determination, r^2? What does r^2 tell us?
The value of the regression coefficient r is given as 0.823733298.
The value of the coefficient of determination is given as r^2 = 0.678536546.
This value indicated that about 67.85% of the variation in the dependent variable sale is explained by the independent variable advertisement.
· Use the model to predict sales and the business spends $950,000 in advertisement. Does the model underestimate or overestimates ales?
We have
Sales = -25.16823406 + 4.921595798*Advertisement
Advertisement = 950 thousand dollar ( or $950,000)
Sales = -25.16823406 + 4.921595798*950
Sales = 4650.347774
The value of sales is lies within range, so it is underestimate.