Instructions
Visit one of the bookstores either ‘2nd and Charles’ or ‘Books-A-Million’ here in Laredo and select 10 different books from any genre (not including textbook). Next, determine the number of pages and the cost for each book. Record the two data and write the titles for each book and submit it on a separate paper.
Collect and list the bivariate data, i.e., number of pages and the cost of each book. [0.8 points]
Construct and insert a scatter plot using the Statistical Package for Social Sciences (SPSS) program. Please explain your steps in producing the scatter plot. [0.8 points]
Note: let the number of pages be the independent variable, x and the cost of the book be the dependent variable, y ̂.
Analyze the data [0.8 points]
Find a.
Find b.
Find and write the linear equation in the form of y ̂=a+bx and round to two decimal places.
Find the correlation coefficient.
Find the p-value.
Note: Must do 2 parts. 1.) Show your work (algebraically) w/answers completely and explain your steps. 2.) Redo the work using the SPSS program and provide a copy of the answers
Insert the scatter plot from part b. including the regression line using the SPSS program. [0.8 points]
Discussion Questions [0.8 points]
Using the p-value, is the correlation significant? Why or why not?
Does the line seem to fit the data? Why?
What does the correlation imply about the relationship between the number of pages and the cost of the book?
Using the linear regression in part c., what will be the cost of the book when the book has 40 pages?
What will be the cost of the book when the book has 1000 pages?
Are there any outliers? If so, which point(s) is/are the outlier?
If any outlier(s) is/are removed, will the correlation coefficient and the p-value improve the significant relationship between the number of pages and the cost of the book?
Should the outlier(s), if any, be removed? Why or why not?
Note: Please explain your answers with complete sentences and show your work completely.
