A13 Multiple Regression Assignment Use Excel to develop a linear regression equa
ID: 3108949 • Letter: A
Question
A13
Multiple Regression Assignment
Use Excel to develop a linear regression equation to predict number of games lost for a baseball team based on rainy days and payroll using the following data set. Use the equation to answer the questions listed below.
Year
Games Lost
Rainy Days
Payroll (000’s)
1993
25
26
175
1994
20
30
178
1995
10
3
240
1996
15
6
235
1997
22
17
180
1998
12
10
241
1999
25
22
173
2000
8
2
255
2001
4
2
267
2002
28
38
160
2003
29
34
147
What is the regression equation?
According to the R2 and adjusted R2, is the line of the regression equation a good fit to the data?
According to the t statistic, is either independent variable significant?
According to the F statistic, is the entire equation significant?
What is the number of wins with no rainy days and no payroll (ignore your common sense and use the calculated results)?
How many wins would you expect with 15 rainy days and a payroll of 220?
Year
Games Lost
Rainy Days
Payroll (000’s)
1993
25
26
175
1994
20
30
178
1995
10
3
240
1996
15
6
235
1997
22
17
180
1998
12
10
241
1999
25
22
173
2000
8
2
255
2001
4
2
267
2002
28
38
160
2003
29
34
147
Explanation / Answer
Regression Equation:Regression equation takes the form of Y=a+bx+c, where Y is the dependent variable that the equation tries to predict, X is the independent variable that is being used to predict Y, a is the Y-intercept of the line, and c is a value called the regression residual.
According to the R2 and adjusted R2, is the line of the regression equation a good fit to the data: No line of regression equation does not fit to the data.
According to the t statistic, is either independent variable significant: Yes.The independent t-test, also called the two sample t-test, independent-samples t-test or student's t-test, is an inferential statistical test that determines whether there is a statistically significant difference between the means in two unrelated groups.
According to the F statistic, is the entire equation significant: Yes. F-test in regression compares the fits of different linear models. Unlike t-tests that can assess only one regression coefficient at a time, the F-test can assess multiple coefficients simultaneously.