Test 4B AP Statistics Name:

Directions: Do all of your work on these sheets.

Part 1: Multiple Choice. Circle the letter corresponding to the best answer.
1. Which of the following scatterplots would indicate that Y is growing exponentially over time
!a" !#" !c"
!d" !e" none of these
$onsider the two%way ta#le of data at the right&
2. The percent of cars listed in the ta#le with
4%cylinder engines that are made in 'ermany is
!a" ()&*+&
!#" ,(+&
!c" *)+&
!d" -)+&
!e" .(+&
3. /rom the ta#le we might conclude that
!a" there is clearly no relation #etween country of
origin and num#er of cylinders&
!#" the correlation #etween country of origin and
num#er of cylinders is li0ely to #e a#out )&*&
!c" a regression line fitted to these data would
pro#a#ly have a negative slope&
!d" there is evidence of some relation #etween
country of origin and num#er of cylinders&
!e" the 1nited States has far more cars than any
of the other countries&
4. According to the (..) census2 those states with an a#ove%average num#er X of people who fail to
complete high school tend to have an a#ove average num#er Y of infant deaths& 3n other words2
there is a positive association #etween X and Y& The most plausi#le explanation for this is
!a" X causes Y& Programs to 0eep teens in school will help reduce the num#er of infant deaths&
!#" Y causes 4& Programs that reduce infant deaths will ultimately reduce high school dropouts&
!c" 5ur0ing varia#les are pro#a#ly present& /or example2 states with large populations will have
#oth larger num#ers of people who don6t complete high school and more infant deaths&
!d" Both of these varia#les are directly affected #y the higher incidence of cancer in certain states&
!e" The association #etween X and Y is purely coincidental&
$hapter 4 ( Test 4B
Part 2: Free Response
Answer completely, but be concise. Show your thought process clearly.
5. 3n a study of the relationship #etween the amount of violence a person watches on T7 and the
viewer6s age2 -( regular T7 watchers were randomly selected and classified according to their age
group and whether they were a 8low%violence9 or 8high%violence9 viewer& :ere is a two%way ta#le
of the results&
Age Group
1634 3554 55 and over Total
Amount of Low 8 12 21
Violence
Watched High 18 15 7
Total
!a" $ompute !in percents" the marginal distri#ution of age group for all people surveyed&

!#" $onstruct a #ar graph on the grid provided to show your results visually&
!c" $ompute !in percents" the conditional distri#ution of age group among 8low%violence9 viewers&
Then do the same for 8high%violence9 viewers&
!d" Write a few sentences explaining what the conditional distri#utions in !c" tell you&
$hapter 4 , Test 4B
6. $ell phones2 a fairly recent innovation2 have #ecome increasingly popular with all segments of our
society& According to the Strategis 'roup2 the num#er of cellular and personal communications
systems su#scri#ers in the 1nited States increased dramatically #eginning in (..)2 as shown in the
following ta#le&
No. of subscribers
Year (millions)
1990 5.3
1991 7.6
1992 11.0
1993 16.0
1994 24.1
1995 33.8
1996 43.4
!a" Apply a test to show that the num#er of su#scri#ers is increasing exponentially&
!#" ;nter the data into your calculator& Then perform an appropriate transformation to lineari<e the
data& /ind the e=uation of the least%s=uares line for the transformed data& >ecord it #elow& Be
sure to define any varia#les you use&
!c" :ow well does the linear model you calculated in !#" fit the transformed data ?ustify your
answer with graphical and numerical evidence&
!d" The Strategis 'roup predicts @)&- million su#scri#ers in (..-2 and ..&, million in the year
,)))& :ow many su#scri#ers does your model predict for these years Show your method&
$hapter 4 A Test 4B
7. Bver the past A) years in the 1nited States there has #een a strong positive correlation #etween
cigarette sales and the num#er of high school graduates& 3s the association #etween these two
varia#les most li0ely due to causation2 confounding2 or common response ?ustify your answer&
8. To help consumers ma0e informed decisions a#out health care2 the government releases data a#out
patient outcomes in hospitals& Cou want to compare :ospital A and :ospital B2 which serve your
community& Not all surgery cases are e=ually serious2 however& Patients are classified as #eing in
either 8poor9 or 8good9 condition #efore surgery& :ere are the data #ro0en down #y patient
condition&
'ood $ondition Poor $ondition
:ospital A :ospital B :ospital A :ospital B
Died E - Died *@ -
Survived *.4 *., Survived (44A (.,
Total E)) E)) Total (*)) ,))
!a" $alculate the percent of patients in good condition who survive at :ospital A and :ospital B&
Do li0ewise for the patients in poor condition&
!#" 1se the ta#les a#ove to create a two%way ta#le that shows the relationship #etween which
hospital a patient goes to and survival status&
!c" $alculate the percent of patients that survive at each hospital&
!d" ;xplain your findings in !a" and !c"&
I pledge that I hae neither gien nor receied aid on this test.FFFFFFFFFFFFFFFFFFFFFFFFFFFFF
$hapter 4 4 Test 4B
Answer G- rest on next page
$hapter 4 * Test 4B
$hapter 4 E Test 4B
$hapter 4 @ Test 4B