In: Statistics and Probability
Study Time and Exam Score
An elementary statistics instructor is interested in determining how well the amount of time students spend studying for her class predicts their results on exam. The instructor asks her students to keep track of the number of hours they spent working on their statistics course between the first and second exam (including in class time, tutoring time, computer time, etc.) She then recorded their score on the second exam and the results are shown below.
Study Time | Exam Score |
30 | 72 |
40 | 85 |
30 | 75 |
35 | 78 |
45 | 89 |
15 | 58 |
15 | 71 |
50 | 94 |
30 | 78 |
0 | 10 |
20 | 75 |
10 | 43 |
15 | 62 |
20 | 65 |
25 | 68 |
25 | 60 |
25 | 70 |
30 | 68 |
40 | 82 |
35 | 75 |
(A) Name the explanatory (predictor) and response variables for this analysis.
(B) What is the slope of the regression line? Interpret this value in context.
(C) What is the y-intercept of the regression line? Interpret this value in context.
(D) Determine the regression line.
(E) Use the equation of the regression line to predict a student's score when they study:
10 hours _____
20 hours _____
30 hours ____
(F) What is the residual for a person that studies 10 hours?
(G) What is the value of the correlation coefficient? Interpret this value.
Study Time, X | Exam Score, Y | XY | X² | Y² |
30 | 72 | 2160 | 900 | 5184 |
40 | 85 | 3400 | 1600 | 7225 |
30 | 75 | 2250 | 900 | 5625 |
35 | 78 | 2730 | 1225 | 6084 |
45 | 89 | 4005 | 2025 | 7921 |
15 | 58 | 870 | 225 | 3364 |
15 | 71 | 1065 | 225 | 5041 |
50 | 94 | 4700 | 2500 | 8836 |
30 | 78 | 2340 | 900 | 6084 |
0 | 10 | 0 | 0 | 100 |
20 | 75 | 1500 | 400 | 5625 |
10 | 43 | 430 | 100 | 1849 |
15 | 62 | 930 | 225 | 3844 |
20 | 65 | 1300 | 400 | 4225 |
25 | 68 | 1700 | 625 | 4624 |
25 | 60 | 1500 | 625 | 3600 |
25 | 70 | 1750 | 625 | 4900 |
30 | 68 | 2040 | 900 | 4624 |
40 | 82 | 3280 | 1600 | 6724 |
35 | 75 | 2625 | 1225 | 5625 |
Ʃx = | Ʃy = | Ʃxy = | Ʃx² = | Ʃy² = |
535 | 1378 | 40575 | 17225 | 101104 |
Sample size, n = | 20 |
x̅ = Ʃx/n = 535/20 = | 26.75 |
y̅ = Ʃy/n = 1378/20 = | 68.9 |
SSxx = Ʃx² - (Ʃx)²/n = 17225 - (535)²/20 = | 2913.75 |
SSyy = Ʃy² - (Ʃy)²/n = 101104 - (1378)²/20 = | 6159.8 |
SSxy = Ʃxy - (Ʃx)(Ʃy)/n = 40575 - (535)(1378)/20 = | 3713.5 |
a)
Explanatory (predictor) variable = Study time
Response variables = Exam score
b)
Slope, b = SSxy/SSxx = 3713.5/2913.75 = 1.274474474
With a unit increase in study time the exam score increases by 1.2745 unit.
c)
y-intercept, a = y̅ -b* x̅ = 68.9 - (1.27447)*26.75 = 34.80780781
The y-intercept is the exam score when x =0.
d)
Regression equation :
ŷ = 34.8078 + (1.2745) x
e)
Predicted value of y at x = 10
ŷ = 34.8078 + (1.2745) * 10 = 47.5526
Predicted value of y at x = 20
ŷ = 34.8078 + (1.2745) * 20 = 60.2973
Predicted value of y at x = 30
ŷ = 34.8078 + (1.2745) * 30 = 73.042
f)
Residual = y - ŷ = 43 - 47.5526 = -4.5526
g)
Correlation coefficient, r = SSxy/√(SSxx*SSyy) = 3713.5/√(2913.75*6159.8) = 0.8765
There is a strong positive relationship between Study time and Exam score.