Announcements
Helpful Suggestions for Final Exam
•  Reminder: Final exam Monday 10:30am-12:30pm will be
held in both DBH 1100 and DBH 1600. Room/seat/version
assignments will be emailed Sunday night.
Don’t forget:
•  Do not round between steps! Use at least three
decimal places. Ideally – do all the steps at once on
your calculator (but show your work!).
•  On multiple choice questions, cover up the answers
while reading the question. Take a minute to try to
figure out the answer before looking at the answer
options.
•  If you get stuck on a question, move on and come
back to it.
•  Read all of the directions and each problem carefully.
–  Apperson 20420 scantron form
–  No. 2 pencil for use on scantron form (bubble in ID
number and version letter correctly)
–  Two 8.5”x11” hand-written sheets of notes, front and back
–  Calculator (no cell phones/ipads/computers)
•  EEE Survey and EEE Evaluation close Sunday!
•  Two more discussions today reviewing for the final exam
DBH 1500 3-5pm.
1
2
3
4
Important Summary Tables
in our Textbook
•  Sampling Distributions: p. 359 (end of Ch. 9)
•  Confidence Intervals: p. 446 (end of Ch. 11)
•  Hypothesis Tests: p. 548 (end of Ch. 13)
!
5
!
!
6
Normal/t Probabilities and Percentiles
Table A.2: Multipliers for confidence intervals.
–  Attached to the back of the final exam.
–  “Infinite” row = z* multipliers – use for confidence
intervals involving proportions.
–  Use corresponding df row for t* multipliers in
confidence intervals involving means.
!
We did not cover in detail a hypothesis test for a difference in two
proportions using the normal approximation. Instead, we use a chisquared test for this situation.
(You do, however, need to know how to calculate and interpret a
confidence interval for a difference in proportions!)
!
•  p-value and normal probability calculations will
not be required on the final exam (which require R
Commander); BUT you should know
–  the Empirical Rule,
–  how to interpret z-scores,
–  how to draw the area under the curve corresponding to
p-values, and
–  how to interpret a p-value
7
CQ: Which Scenario?
Determining the Appropriate Parameter
(Section 13.6: See examples, page 538)
Retired professional tennis players Martina Navratilova,
Monica Seles, John McEnroe, and Jimmy Connors are all
left-handed. About 10% of the general population is lefthanded. Researchers are interested if the proportion of
professional tennis players that are left-handed is larger than
that of the general population.
•  Is the response variable for each unit categorical
(yes, no; agree, don’t agree; etc.) or quantitative
(height, IQ, weight gain, etc.)?
•  Is there one sample or two?
•  If two, independent or paired?
Variable type
(Parameter type)
One sample
(No pairing)
Paired
Data
A.  One population proportion.
B.  Difference in two population proportions.
C.  One population mean.
D.  Population mean of paired differences.
E.  Difference in two population means.
Two independent
samples
Categorical
(Proportions)
p
None
p1 − p2
Quantitative
(Means)
µ
µd
µ1 − µ2
8
9
Retired professional tennis players Martina Navratilova,
Monica Seles, John McEnroe, and Jimmy Connors are all
left-handed. About 10% of the general population is lefthanded. Researchers are interested if the proportion of
professional tennis players that are left-handed is larger than
that of the general population.
One Population Proportion:
Population?
All professional tennis players
Parameter of interest?
p = proportion of all professional tennis players that
are left-handed
Hypotheses?
H0: p = 0.10 vs. Ha: p > 0.10
10
CQ: Which Scenario?
Data on the testosterone levels (ng/dL in saliva) of men in
different professions were given in a paper published in the
Journal of Personality and Social Psychology (Dabbs et al.,
1990). The researchers suggest that there are occupational
differences in mean testosterone level between medical
doctors and university professors.
A.  One population proportion.
B.  Difference in two population proportions.
C.  One population mean.
D.  Population mean of paired differences.
E.  Difference in two population means.
11
12
CQ: Which Scenario?
Data on the testosterone levels (ng/dL in saliva) of men in
different professions were given in a paper published in the
Journal of Personality and Social Psychology (Dabbs et al.,
1990). The researchers would like to estimate the difference
in mean testosterone level between medical doctors and
university professors.
Difference in Population Means (Independent Samples):
Populations?
(1)  All male medical doctors; and
(2)  All male university professors
Parameter of interest?
µ1 – µ2 = difference in mean testosterone levels between
medical doctors and university professors (doctors –
professors)
Hypotheses?
H0: µ1 – µ2 = 0 vs. Ha: µ1 – µ2 ≠ 0
In a study done in England, Voss and Mulligan (2000)
collected data on height (short or not) and whether or not the
student had ever been bullied in school for 209 secondary
school students. The researchers are interested in if shorter
students have a higher chance of being bullied in school.
A.  One population proportion.
B.  Difference in two population proportions.
C.  One population mean.
D.  Population mean of paired differences.
E.  Difference in two population means.
13
In a study done in England, Voss and Mulligan (2000)
collected data on height (short or not) and whether or not the
student had ever been bullied in school for 209 secondary
school students. The researchers are interested in if shorter
students have a higher chance of being bullied in school.
Difference in Population Proportions:
Populations?
(1)  All short secondary school students in England; and
(2)  All “not short” secondary school students in England
Parameter of interest?
p1 – p2 = difference in proportions of students being bullied
between short students and not short students in the
population (short – not)
Hypotheses?
H0: p1 – p2 = 0 vs. Ha: p1 – p2 > 0
14
CQ: Which Scenario?
A company manufactures a homeopathic drug that it claims
can reduce the time it takes to overcome jet lag after longdistance flights. A researcher would like to test that claim.
She recruits 46 people who take frequent trips from San
Francisco to London and assigns them to take a placebo for
one of their trips and the drug for the other trip, in random
order. She then asks them how many days it took to recover
from jet lag under each condition.
A. 
B. 
C. 
D. 
E. 
One population proportion.
Difference in two population proportions.
One population mean.
Population mean of paired differences.
Difference in two population means.
15
A company manufactures a homeopathic drug that it claims can
reduce the time it takes to overcome jet lag after long-distance
flights. A researcher would like to test that claim. She recruits 46
people who take frequent trips from San Francisco to London and
assigns them to take a placebo for one of their trips and the drug
for the other trip, in random order. She then asks them how many
days it took to recover from jet lag under each condition.
Paired Population Mean Difference:
Population?
All people who take frequent trips from San Francisco to
London
Parameter of interest?
µd = mean difference in time it takes to overcome jet lag
between taking a homeopathic drug and taking a placebo in the
population of frequent fliers (homeopathic – placebo)
Hypotheses?
H0: µd = 0 vs. Ha: µd < 0
17
16
CQ: Which Scenario?
The box of Yvette’s favorite cereal states that the net
contents weigh 12 ounces. Yvette is suspicious of this claim
because the package never seems full to her. She plans to
measure the weight of the contents of the next 20 boxes she
buys and find out whether she is being short-changed.
A.  One population proportion.
B.  Difference in two population proportions.
C.  One population mean.
D.  Population mean of paired differences.
E.  Difference in two population means.
18
The box of Yvette’s favorite cereal states that the net
contents weigh 12 ounces. Yvette is suspicious of this claim
because the package never seems full to her. She plans to
measure the weight of the contents of the next 20 boxes she
buys and find out whether she is being short-changed.
One Population Mean:
Population?
All cereal boxes
Parameter of interest?
µ = mean weight of the population of cereal boxes
Hypotheses?
H0: µ = 12 vs. Ha: µ < 12
19