AP Statistics Mr.

Maine
Test 3 10/17/14

Name:______________________

Multiple choice questions are 5 points each.

1. All but one of the following statements
includes a fundamental misuse of statistics.
Which statement could possibly be correct?
(a) There is a Pearsons r of 0.54 between the
position a football player plays and their weight.
(b) The correlation between planting rate and
yield of corn was found to be r=0.23.
(c) The correlation between the gas mileage of
a car and its weight is r=0.71 MPG.
(d) We found a high correlation (r=1.09)
between the height and age of children.
(e) We found a correlation of r=.63 between
gender and political party preference.
2. In a scatterplot reflecting a strong correlation, if each x-value were decreased by one unit and the y-values
remained the same, then the correlation r would
(a) Decrease by 1 unit
(b) Decease slightly
(c) Increase slightly
(d) Stay the same
(e) Cant tell without knowing the data values
3. A local community college announces the correlation between college entrance exam grades and scholastic
achievement was found to be 1.08. On the basis of this you would tell the college that
(a) The entrance exam is a good predictor of success.
(b) The exam is a poor predictor of success.
(c) Students who do best on this exam will be poor students.
(d) Students at this school are underachieving.
(e) The college should hire a new statistician.
4. The equation of the least squares regression line for the points on a scatterplot is
the residual for the point (2 , 1.5)?
(a) 2.1
(b) -2.1
(c) 2.6
(d) 1.6
(e) -1.6

y = 4.1

- 0.5x. What is

5. Which of the following is the quantity that is minimized by the least squares regression algorithm?
( )()
1

(a)
1

(b)
(c)
(d)
(e)

( )2
( )2
( )2
( )2

6. If the correlation between body weight and annual income were high and positive, we could conclude that:
(a) High incomes cause people to eat more food.
(b) Low incomes cause people to eat less food.
(c) High-income people tend to spend a greater proportion of their income on food than low-income
people, on average.
(d) High-income people tend to be heavier than low income people, on average.
(e) High incomes cause people to gain weight.

7. Which of the following is true about Chebyshevs Rule and/or the Empirical Rule?
(a) The Empirical Rule applies to highly skewed distributions.
(b) In a normal distribution, about 95% of data is below 2 standard deviations above the mean.
(c) Chebyshevs Rule tells us more than the Empirical Rule about a normally distributed variable.
(d) Chebyshevs Rule is important because it is always true.
(e) There is an easy algebraic formula for the percentages in the Empirical Rule.
8. Suppose that nothing is known about the distribution of test scores on one of Mr. Maines overly cruel
physics exams except the mean, 48, and the standard deviation, 10. In total, 80 people took the exam.
(a) What is the MOST students that could possibly have scored above 68?

(b) If the distribution of scores was approximately normal, how many students probably scored above 68?

(c) If the distribution of scores was approximately normal, at roughly what percentile is a score of 38?

(d) What is the z-score of a raw score of 33?

9. A small sample from a large group of students is asked the question, On a scale of 1 to 100, where 1 is utter
hatred and 100 is the best thing in your life, how much do you enjoy stat tests? The respondents offer up the
answers {- 50, pi, 5, 9, 102}. As you can see, the students are a sarcastic and uncooperative lot. If we are to use
this data to try to make educated guesses about the population, then:
(a) The 43rd percentile in the population is probably between which two values?

(b) Use linear interpolation to estimate the 55th percentile in the population.

10. Express Pearsons correlation coefficient in terms of z-scores.

11. (Written last year and inspired by Facebook conversations between seniors at the time while I was writing
the test) Sophie complains that Nathan wont stop sending her cute duck videos on YouTube, and that the
resulting distraction prevents her from studying for her statistics exam on correlation the next day. Fortunately,
everything works out! She watches the videos and aces the exam anyway. But now, her curiosity piqued and
freshly plagued by an unhealthy fascination with correlation, she surveys her classmates and collects data on
both test scores and the number of hours spent watching viral videos on the Internet over the previous week. For
the 69 students in AP Statistics, she finds that the mean test score is 80.2, with sample standard deviation 10.1
points. They spent, on average, 24.1 hours per week watching ducklings, cats, twerking, and The Fox on video
sites, with sample standard deviation 13.8 hours per week. The two variables have a correlation coefficient of 0.612.
(a) Determine the equation of the LSRL of test grade (y) on weekly hours of YouTube videos (x).

(b) For each additional hour of YouTube watched per week, what is the average change in the corresponding
students stat test score? If you couldnt do the previous part, you can still answer this conceptually in
terms of what the answer would have been if you could do it.

(c) Is it correct from the negative correlation to conclude that watching more YouTube videos causes
students to earn lower statistics grades? Explain your answer.

(d) Mr. Maine suggests that perhaps low test scores are depressing, and that the resulting gloom drives
students to watch more duckling videos in an attempt to cheer up. So Sophie swaps her two axes and
repeats the analysis. Will the correlation coefficient be the same, lower, higher, or is it impossible to
predict from the information given?

12. Sketch a scatterplot for two variables that have 1 (i.e. below -0.8 or so), but for which the LSRL is a
poor model of the relationship between the variables.

13. The table below shows the mens 800-meter run world records, in seconds. Assume a linear fit and use the
data below to find both the LSRL and r. Then use the LSRL for the data up through 1985 to predict the
current record. The actual value, if youre curious, is 100.91 s, set at the London Olympic games.
Year
Record
1905
113.4
1915
111.9
1925
111.9
1935
109.7
1945
106.6
1955
105.7
1965
104.3
1975
104.1
1985
101.73
~~~~~~~~~~~~~~~~~~~~~~

Extra Credit: The equation for a normal distribution (Gaussian function) is =

1
2

( 2
) 2

. The coefficient

doesnt really change the overall shape of the distribution, since it multiplies the whole function by a constant.
So why is it there?