Homework Problem:

On the graph paper that is provided for you I want you to analyze this data and create two scatter plots.  One plot will be on the front of the paper and the other will be on the back of the graph paper.  Pick any two attributes and label your x and y axis with the attributes that are being used.  Make sure that you scale the graph paper and the two axis to fit your data.

 Name Age Education* (# of years) Annual Income\$ Vacations Taken (in the last year) # of pets # of siblings Bill 34 6 38,000 0 4 1 John 67 9 123,000 2 0 2 Carrie 23 8 30,000 1 1 2 Pat 45 8 52,000 2 2 2 Steve 46 8 46,000 1 3 3 Sarah 38 8 41,000 2 2 2 Pete 50 10 98,000 4 1 0 Eric 44 8 53,000 2 0 2 Dan 40 10 57,000 2 2 1 Gene 71 4 27,000 0 2 5 Jack 68 6 49,000 2 1 0 Ashley 29 8 45,000 1 2 2 Stacy 36 8 52,000 1 1 2 Brittany 46 4 34,000 0 3 2 Fran 54 8 61,000 3 5 0 Tom 39 8 50,000 1 1 4 Mario 24 4 39,000 0 0 1 Dale 68 4 105,000 2 3 6 Tammy 62 4 26,000 0 0 2 Ann 25 6 38,000 1 2 3 Susie 54 10 49,000 3 4 1 Jen 33 12 75,000 4 1 2 Lenny 60 8 57,000 1 0 0 Lois 71 8 24,000 2 2 2 Tiffany 46 4 30,000 1 2 3 Sam 32 8 62,000 2 0 2 Pam 48 6 54,000 3 6 3

* - education (starting in ninth grade)

\$ - in thousands

After creating the scatter plots I want you to show a best-fit line that you feel is as accurate as possible to the data that you have graphed on your paper.  Also the following questions need to be answered.

1.  I want you to tell me why you put the best-fit line on the graph where you did?

2. What is the mean, median and mode of the data for the attributes that were used above?

3. What other predictions can be made from the data on the graph.  I want two or three predictions on the data that you used.

(For example you can tell me how many years of education that a 35 year old who makes \$56,000 would have).

4. What can be concluded from the # of pets category and # of siblings category?

5. What other correlations could be sought from this data?

6. Has enough data been collected to make assumptions and accurate predictions?  What can be done to make our predictions more accurate?