UNIVERSITY OF THE PHILIPPINES CEBU

College of Science

STAT 110: PREDICTIVE STATISTICS

FIRST LONG EXAMINATION
I: Circle the letter of the correct answer.

1. I. A researcher finds that the correlation between hours studied and exam score is (r = 0.72). Which statement is
the most accurate interpretation?
(A) Studying causes exam scores to increase by 0.72 points
(B) 72% of the variation in exam scores is explained by hours studied
(C) Students who study more tend to have higher exam scores, but this does not necessarily imply causation
(D) Exam scores determine how many hours students study
2. Suppose the correlation between two variables is (r = -0.80). Which statement must be true?
(A) The variables are unrelated
(B) As one variable increases, the other tends to increase
(C) As one variable increases, the other tends to decrease
(D) The relationship is weak
3. A scatterplot shows points closely clustered around a downward sloping line. The correlation coefficient is most
likely:
(A) (0.05)
(B) (0.80)
(C) (-0.10)
(D) (-0.85)
4. A student computes the correlation between two variables and obtains (r = 1.12). What is the most reasonable
conclusion?
(A) The variables have a perfect positive relationship
(B) The variables have a strong relationship
(C) None of the above
(D) The data must contain negative values
5. Which situation would most likely produce a correlation close to zero?
(A) Students who study more tend to score higher on exams
(B) Temperature increases while ice cream sales increase
(C) Students’ shoe size and their score on a history test
(D) The more hours people exercise, the fewer calories they store
6. Consider the simple linear regression model y = β0 + β1 x. What does the parameter β1 represent in context?
(A) The value of (y) when (x = 0)
(B) The expected change in (y) for every 1-unit increase in (x)
(C) The value of (x) when (y = 0)
(D) The average value of (y)
7. A regression line has a negative slope. Which statement best describes the relationship between the variables?
 (A) There is no relationship between the variables
(B) The variables increase together
(C) As the independent variable increases, the dependent variable tends to decrease
(D) The dependent variable does not change

8. A teacher uses a regression model to predict exam scores from hours studied. What does the model primarily
provide?
(A) The exact exam score for every student
(B) An estimated exam score based on the number of hours studied
(C) Proof that studying causes higher scores
(D) The probability that a student will pass
9. In testing the significance of a correlation coefficient, the null hypothesis is typically H0 : ρ = 0. What does this
mean?

(A) The sample correlation is zero

(B) The regression slope is zero for every dataset
(C) There is no linear relationship between the variables in the population
(D) The variables are identical
10. A dataset shows a strong positive correlation between two variables. Which conclusion is most justified?

(A) One variable definitely causes the other

(B) The variables must increase at the same rate
(C) The variables tend to increase together, but other factors may explain the relationship
(D) The relationship must be perfectly linear

II: Write TRUE if the statement is correct; if FALSE, underline and change the incorrect part to make the statement
correct.

1. Correlation measures the strength and direction of the linear relationship between two quantitative variables.
2. If the correlation between two variables is negative, it means that as one variable increases, the other variable tends
to decrease.
3. A correlation coefficient of (r = 0) always means that there is absolutely no relationship of any kind between the
variables.
4. A strong correlation between two variables automatically means that one variable causes the other to change.

5. Suppose researchers observe a strong positive correlation between the number of firefighters at a fire scene and the
amount of property damage. This means that firefighters cause greater damage to property.
6. In the regression model y = β0 + β1 x, the parameter β1 represents the expected change in y for every one-unit
increase in x.
7. In simple linear regression, the regression line is chosen so that it minimizes the overall distance between the
observed points and the line.
8. In mathematics, the slope between two points is calculated using xy22 −y 1
−x1 . In statistics, the slope of a regression
line is not calculated using only two points because the data points do not necessarily lie on a single line and the
regression line must best fit all observations simultaneously.

9. If the slope β1 of a regression line is positive, the correlation coefficient must also be positive.
10. Suppose a study finds a very strong correlation between hours studied and exam scores. While it seems reasonable
that studying improves scores, correlation alone cannot prove causation because other factors may also influence
exam performance.

Page 2
III: For all problems in this section, clearly write the tables you use in your formulas (such as sums, products,
or squared deviations) to show your work. Do not round any intermediate calculations; only round your final
answers—including correlation coefficients, regression slope, intercept, or predictions—to 3 decimal places. Use
α = 0.05 as the significance level, and assume all assumptions are met.

1. Sleep and Exam Performance [2 points each]

A researcher collected data on the number of hours students slept the night before an exam and their corresponding
exam scores.

Hours of sleep (x) 3 4 5 6 6 7 8 9

Exam score (y) 55 60 65 70 72 75 80 82

(a) Draw a scatter plot for the variables.

(b) Compute the correlation coefficient r.
(c) Determine whether a linear regression model is appropriate.
(d) If appropriate, find the regression equation.
(e) Predict the exam score for a student who slept 7 hours.
(f) Interpret the meaning of the slope in context.
(g) Discuss whether predicting the score of a student who slept 12 hours is reasonable.

2. Advertising and Weekly Sales [2 points each]

A company recorded its weekly advertising expenses and the resulting sales revenue over eight weeks.

Advertising ($1000), x 1 2 3 4 5 6 7 8
Weekly sales ($1000), y 14 18 20 24 28 30 33 36

(a) Draw a scatter plot of advertising versus sales.

(b) Compute the correlation coefficient.
(c) Decide whether a regression model is appropriate for prediction.
(d) If appropriate, find the regression equation.
(e) Predict weekly sales if the company spends $5,500 on advertising.
(f) Explain the slope of the regression line in the context of advertising and sales.
(g) Is it reasonable to predict sales for advertising of $10,000? Why or why not?

IV: Derive the equation

(a) From:
Cov(X, Y )
rXY =
SX SY
To: Pn
− X̄)(Yi − Ȳ )
i=1 (Xi
rXY = qP qP .
n 2 n 2
i=1 (Xi − X̄) i=1 (Yi − Ȳ )

Bonus [5 points]: On what date did we have our first meeting in this class?

“Storms make trees take deeper roots.” — Dolly Parton

Page 3