AP Statistics / Mr. Hansen

Name: _______________________________________

11/9/2006

Mr. Hansen’s use only (bonus point for spare batteries): _______

 

Quest through p. 276 in text, Version 2

Please read: Calculator is OK throughout. However, per your vote, no written or computer-printed notes are permitted today. Scoring is 5 points per question with little or no partial credit (70 points total).

 

1.

In an exponential regression, your calculator reports r2 = 0.841. Which of the following is a true statement?

 

(A) Approximately 84% of the variation in y can be explained by the variation in x.

(B) Approximately 84% of the variation in log y can be explained by the variation in x.

(C) Approximately 91.7% of the variation in y can be explained by the variation in x.

(D) Approximately 91.7% of the variation in log y can be explained by the variation in x.

(E) Approximately 70.7% of the variation in y can be explained by the variation in x.

 

 

2.

What name is given to r2 in the LSRL setting?

 

(A) regression coefficient

(B) linear regression coefficient

(C) correlation coefficient

(D) linear correlation coefficient

(E) coefficient of determination

 

 

3.

A scatterplot shows an almost perfect linear relationship between x and y. The r2 value is close to 1, and the residual plot shows no patterns. Can we infer that a change in y causes a change in x?

 

(A) No, since it is more likely (statistically speaking) that a change in x causes a change in y.
(B) No, unless x represents the control group in a controlled experiment.

(C) No, unless y represents the control group in a controlled experiment.

(D) No, since both x and y could be affected by a lurking variable.
(E) Yes.

 

 

4.

“Person on the street” interviews, in which a newspaper, radio, or TV reporter gathers opinions from passersby in an attempt to illustrate a current-events story with lively quotes, are . . .

 

(A) anecdotal data

(B) subject to voluntary response bias

(C) subject to undercoverage bias since many people are stuck in buildings during the working day

(D) subject to response bias

(E) all of the above

 

 

5.

In a hypothetical survey of attitudes toward lunch, suppose that the mean lunch rating by freshmen (on a scale of 0 to 10, 10 being highest) is 6.2, but for seniors, the mean rating is only 3.1. Can we conclude that freshmen (on average) like lunch twice as much as seniors do?

 

(A) Yes, but only if the sample sizes were fairly large.

 

(B) Yes, but only if the sample sizes were fairly large and each sample was an SRS.

 

(C) No, since there is likely to be a great deal of response bias.

 

(D) No, since the scale is not an ordinal scale.

 

(E) No, since the scale is not a ratio scale.

 

 

 

For questions 6-9, consider the following actual data (American Sociological Review, 1981) concerning 326 criminal cases in which the death penalty was considered after the perpetrator had been convicted. The 326 defendants consisted of 160 whites and 166 blacks. Of the 160 white defendants, 151 of them were found guilty of murdering white victim(s) and 9 were found guilty of murdering black victim(s). Of the 166 black defendants, 63 of them were found guilty of murdering white victim(s) and 103 were found guilty of murdering black victim(s).

Of the 151 whites who killed white victims, 19 received a death sentence. None of the whites who killed black victims received a death sentence.

Of the 63 blacks who killed white victims, 11 received a death sentence. Of the 103 blacks who killed black victims, 6 received a death sentence.

 

 

6.

Compute the percentage of white convicts in this study (out of 160 total) who received the death penalty. ____ Compute the percentage of black convicts in this study (out of 166 total) who received the death sentence. ____ Which death penalty rate is higher, the one for white convicts or the one for black convicts? _____________

 

 

7.

Given that the victim was white, prove that black defendants were more likely to receive the death penalty than white defendants were. (Show the numbers and/or percentages that you are using.)

 

 

 

 

 

 

 

 

 

 

 

 

8.

Given that the victim was black, prove that black defendants were more likely to receive the death penalty than white defendants were. (Show the numbers and/or percentages that you are using.)

 

 

 

 

 

 

 

 

 

 

 

 

9.

What topic from the textbook is illustrated by questions 5, 6, and 7, considered as a group?

______________________________

 

 

10.

Give an example of a nominal scale that has more than 2 possible outcomes and is not ordinal.

 

 

 

 

11.

Why does any reputable survey reported in print always include the wording of the question that was used?

 

 

 

 

 

 

 

 

12.

Explain what is meant by the term push polling.

 

 

 

 

 

 

13.

State what is meant by a difference between experimental and control groups that is statistically significant.

 

 

 

____________________________________________

 

 

14.

Using the phrase statistically significant or statistical significance, explain what constitutes statistical proof of cause and effect.