1. In a study, 28 adults with mild periodontal disease are assessed before and 6 months after the implementation of a dental-education program intended to promote better oral hygiene. After 6 months, periodontal status improved in 15 patients, declined in 8, and remained the same in 5.
Choose one answer:
Assess the impact of the program statistically (use a two-sided test).
We do not reject H_0 at the 5% level and conclude that patients have not significantly changed on the program.
We reject H_0 at the 5% level and conclude that patients have significantly changed on the program.
We reject H_0 at the 5% level and conclude that patients have not significantly changed on the program.
We do not reject H_0 at the 5% level and conclude that patients have significantly changed on the program.
2. data can be ordered but do not have specific numeric values. Thus, common arithmetic cannot be performed on ordinal data in a meaningful way.
Choose one answer:
ordinal
interval
ratio
nominal
3. A ______________ design is a type of randomized clinical trial in which each participant is randomized to either group A or group B which receive different treatments, then later switch treatments.
Choose one answer:
cross-over
case-control
prospective
retrospective
4. Suppose researchers do an epidemiologic investigation of people entering a sexually transmitted disease clinic. They find that 160 of 200 patients who are diagnosed as having gonorrhea and 50 of 105 patients who are diagnosed as having nongonococcal urethritis have had previous episodes of urethritis.
Are the present diagnosis and prior episodes of urethritis associated? (Hint: a chi-square test with Yates' correction)
Choose one answer:
Gonorrhea patients are significantly more likely to have prior episodes of urethritis than NGU patients.
Gonorrhea patients are not significantly more likely to have prior episodes of urethritis than NGU patients.
5. The _______ rate is defined as the proportion of participants in the placebo group who actually receive the active treatment outside the study protocol.
6. I DID IT
7. I DID IT
8. I DID IT
9. For any sample point ( x subscript i, y subscript i), the ___________________ of that point about the regression line is defined by ( stack y subscript i with hat on top minus top enclose y). (Hint: the blank is two words)
10. The following statistics are taken from an article by Burch relating cigarette smoking to lung cancer. The article presents data relating mortality from lung cancer to average cigarette consumption (lb/person) for females in England and Wales over a 40-year period. The data are given in the table below.
Cigarette consumption and lung-cancer mortality in England and Wales, 1930-1969
Period
log_{10} mortality (over 5 years), y
log_{10} annual cigarette consumption (lb/person), x
1930-1934
-2.35
-0.26
1935-1939
-2.20
-0.03
1940-1944
-2.12
0.30
1945-1949
-1.95
0.37
1950-1954
-1.85
0.40
1955-1959
-1.80
0.50
1960-1 ...
AMERICAN LANGUAGE HUB_Level2_Student'sBook_Answerkey.pdf
1. In a study, 28 adults with mild periodontal disease are assesse
1. 1. In a study, 28 adults with mild periodontal disease are
assessed before and 6 months after the implementation of a
dental-education program intended to promote better oral
hygiene. After 6 months, periodontal status improved in 15
patients, declined in 8, and remained the same in 5.
Choose one answer:
Assess the impact of the program statistically (use a two-sided
test).
We do not reject H_0 at the 5% level and conclude that patients
have not significantly changed on the program.
We reject H_0 at the 5% level and conclude that patients have
significantly changed on the program.
We reject H_0 at the 5% level and conclude that patients have
not significantly changed on the program.
We do not reject H_0 at the 5% level and conclude that patients
have significantly changed on the program.
2. data can be ordered but do not have specific numeric values.
Thus, common arithmetic cannot be performed on ordinal data
in a meaningful way.
Choose one answer:
ordinal
interval
ratio
2. nominal
3. A ______________ design is a type of randomized clinical
trial in which each participant is randomized to either group A
or group B which receive different treatments, then later switch
treatments.
Choose one answer:
cross-over
case-control
prospective
retrospective
4. Suppose researchers do an epidemiologic investigation of
people entering a sexually transmitted disease clinic. They find
that 160 of 200 patients who are diagnosed as having gonorrhea
and 50 of 105 patients who are diagnosed as having
nongonococcal urethritis have had previous episodes of
urethritis.
Are the present diagnosis and prior episodes of urethritis
associated? (Hint: a chi-square test with Yates' correction)
Choose one answer:
Gonorrhea patients are significantly more likely to have prior
episodes of urethritis than NGU patients.
Gonorrhea patients are not significantly more likely to have
prior episodes of urethritis than NGU patients.
5. The _______ rate is defined as the proportion of participants
3. in the placebo group who actually receive the active treatment
outside the study protocol.
6. I DID IT
7. I DID IT
8. I DID IT
9. For any sample point ( x subscript i, y subscript i), the
___________________ of that point about the regression line is
defined by ( stack y subscript i with hat on top minus top
enclose y). (Hint: the blank is two words)
10. The following statistics are taken from an article by Burch
relating cigarette smoking to lung cancer. The article presents
data relating mortality from lung cancer to average cigarette
consumption (lb/person) for females in England and Wales over
a 40-year period. The data are given in the table below.
Cigarette consumption and lung-cancer mortality in England
and Wales, 1930-1969
Period
log_{10} mortality (over 5 years), y
log_{10} annual cigarette consumption (lb/person), x
1930-1934
-2.35
-0.26
1935-1939
-2.20
-0.03
1940-1944
4. -2.12
0.30
1945-1949
-1.95
0.37
1950-1954
-1.85
0.40
1955-1959
-1.80
0.50
1960-1964
-1.70
0.55
1965-1969
-1.58
0.55
Source: Based on the Journal of the Royal Statistical Society,
A., 141, 437-477, 1978.
Compute the correlation between 5-year lung-cancer mortality
and annual cigarette consumption when each is expressed in the
log_{10} scale.
11. A ____________ variable is a variable that is associated
with both the disease and the exposure variable. Such a variable
must usually be controlled for before looking at a disease-
exposure relationship.
Choose one answer:
confounding
random
discrete
5. continuous
12. Researchers compare protein intake among three groups of
postmenopausal women: (1) women eating a standard American
diet (STD), (2) women eating a lacto-ovo-vegetarian diet
(LAC), and (3) women eating a strict vegetarian diet (VEG).
The m e a n space plus-or-minus space 1 space s d for protein
intake (mg) is presented in the table below.
Protein intake (mg) among three dietary groups of
postmenopausal women
Group Mean sd n
STD 75 9 10
LAC 57 13 10
VEG 47 17 6
Perform a statistical procedure to compare the means of the
three groups using the critical-value method. Report the p-value
from this test.
13. In a 1985 study of the relationship between contraceptive
use and infertility, 89 of 283 infertile women, compared with
640 of 3833 control (fertile) women, had used an intrauterine
device (IUD) at some time in their lives.
Use the normal-theory method to test for significant differences
in contraceptive-use patterns between the two groups.
Choose one answer
The difference in previous IUD usage rates is highly significant
with cases significantly more likely to have previously used an
IUD than controls, with p<0.001.
6. The difference in previous IUD usage rates is highly significant
with cases significantly more likely to have previously used an
IUD than controls, with p<0.01.
The difference in previous IUD usage rates is not significantly
more likely to have previously used an IUD than controls, with
p<0.001.
The difference in previous IUD usage rates is not significantly
more likely to have previously used an IUD than controls, with
p<0.01.
14. I DID IT
15. I DID IT
16. I DID IT
17. A negative confounder is a variable that either
Choose one answer:
is postively associated with both exposure and disease
is negatively associated with disease and positively associated
with exposure
is positively associated with disease and negatively associated
with exposure
is negatively associated with both exposure and disease
18. I DID IT
19. Consider the information from Problem 18. Two hundred
subjects are selected randomly from the population and
followed for various lengths of time. The average length of
follow-up is 1.5 years. Suppose that at the end of the study, the
estimated rate is 4 per 100 person-years. How many events must
have been observed in order to yield the estimated rate of 4 per
100 person-years?
7. 20. I DID IT
1. The data in the table are a sample from a larger data set
collected on people discharged from a selected Pennsylvania
hospital as part of a retrospective chart review of antibiotic
usage in hospitals.
Hospital-stay data
ID number
Duration of hospital stay
Received Antibiotics?
1
5
no
2
10
no
3
6
no
4
11
no
5
5
no
6
14
yes
7
9. 3
yes
20
7
no
21
9
no
22
11
yes
23
11
no
24
9
no
25
4
no
Compute the mean and median for the duration of
hospitalization for the 25 patients.
2. Using the table from Problem 1, compute the standard
deviation and range for the duration of hospitalization for the
25 patients.
3. Select all types of measures of location:
Mode
Median
Standard Deviation
Arithmetic Mean
Variance
4. Suppose 6 of 15 students in a grade-school class develop
10. influenza, whereas 20% of grade-school students nationwide a
develop influenza. Is there evidence of an excessive number of
cases in the class? That is, what is the probability of obtaining
at least 6 cases in this class if the nationwide rate holds true?
5. Using the data from Problem 4, what is the expected number
of students in the class who will develop influenza?
6.Two events A and B are ___________________________ if
they cannot both happen at the same time. (Hint: the answer is
two words).
6. Serum cholesterol is an important risk factor for coronary
disease. We can show that serum cholesterol is approxima tely
normally distributed, with mean= 219 mg/dL and standard
deviation =50 mg/dL.
7. What proportion of the general population has borderline
high-cholesterol levels--that is, > 200 but < 250 mg/dL?
0.380
0.648
0.7324
0.620
8. Much discussion has taken place concerning possible health
hazards from exposure to anesthetic gases. In one study
conducted in 1972, 525 Michigan nurse anesthetists were
surveyed by mail questionnaires and telephone interviews to
determine the incidence rate of cancer. Of this group, 7 women
reported having a new malignancy other than skin cancer during
1971.
What is the best estimate of the 1971 incidence rate from these
11. data?
9. Using the data from Problem 8, provide a 95% confidence
interval for the true incidence rate.
10. Choose the correct word for the following sentence: If the
results of a previous trial does not affect the result of the
following trial, then the results are __________________
(dependent/independent).
Independent or Dependent
11. Approximately ___% of the probability mass falls within
two standard deviations (2 ) of the mean of a random variable.
95%
50%
68%
99.7
12. Iron-deficiency anemia is an important nutritional health
problem in the United States. A dietary assessment was
performed on 51 boys 9 to 11 years of age whose families were
below the poverty level. The mean daily iron intake among
these boys was found to be 12.50 mg with standard deviation
4.75 mg. Suppose the mean daily iron intake among a large
population of 9 to 11 year old boys from all income strata is
14.44 mg. We want to test whether the mean iron intake among
the low-income group is different from that of the general
population.
State the hypotheses that we can use to consider this question.
Perform the hypothesis test using the critical-value method with
an alpha of 0.05, and summarize your findings. Report the p-
value for this test (may give a range that includes the p-value)
13. A clinical trial is called _____________________ if neither
12. the physician nor the patient knows what treatment he or she is
getting. (Hint: the blank is two words)
14. In a study, 28 adults with mild periodontal disease are
assessed before and 6 months after implementation of a dental -
education program intended to promote better oral hygiene.
After 6 months, periodontal status improved in 15 patients,
declined in 8, and remained the same in 5.
Assess the impact of the program statistically (use a two-sided
test)
15. Two drugs (A, B) are compared for the medical treatment of
duodenal ulcer. For this purpose, patients are carefully matched
with regard to age, gender, and clinical condition. The treatment
results based on 200 matched pairs show that for 89 matched
pairs both treatments are effective; for 90 matched pairs both
treatments are ineffective; for 5 matched pairs drug A is
effective, whereas drug B is ineffective; and for 16 matched
pairs drug B is effective, whereas drug A is ineffective.
What test procedure can be used to assess the results?
McNemar’s test for correlated proportions
Fisher’s exact Test
The Paired t Test
The Sign Test
16. The standard screening test for Down's syndrome is based
on a combination of maternal age and the level of serum alpha-
fetoprotein. Using this test 80% of Down's syndrome cases can
be identified, while 5% of normals are detected as positive.
What is the sensitivity and specificity of the test?
17. Lutein, an important carotenoid in the maintenance of ocular
health, has been found postmortem in th macula of eyes. Hence,
a study is planned to supplement patients with high doses of
lutein in capsule form to possibly prevent age-related macular
degeneration, an important eye disease that can cause partial or
13. total blindness in large numbers of elderly people.
To assess compliance in study participants, a blood sampl e will
be drawn. It is estimated that a serum lutein would indicate
that a participant is taking study medication.
The study began in 1999. A test sample of 9 participants had
their lutein level measured in 1999 and again in 2003. The
researchers found a calibration error in the 1999 assays, but the
2003 assays were correct. The data are shown in the table
below.
Serum-lutein data analyzed in 1999 and 2003
Sample
1999 Serum-lutein level
2003 Serum-lutein level
1
3.5
6.4
2
2.9
7.5
3
4.1
8.4
4
5.1
9.6
5
6.4
12.0
6
1.9
4.2
7
1.3
3.1
8
14. 4.1
6.3
9
2.3
4.4
Mean
3.511
6.878
sd
1.616
2.839
Using regression methods, derive a calibration formula
predicting the 2003 level as a function of the 199 level.
y=0.999+1.674x
y=-0.999+1.674x
y=0.999-1.674x
y=0.999x+1.674
18. The probability of a _________________ (Type 1
error/Type 2 error) is the probability of accepting the null
hypothesis when H_1 is true.
19. In a ________________ study the same group of people is
followed over time.
Longitudinal
Cross-sectional
Paired
Double blind
20. A recent article by Kenfield et al. studied the relationship
between various aspects of smoking and mortality among
104,519 women in the Nurses' Health Study (NHS) from 1980-
2004. One issue is whether there is a mortality benefit fr om
quitting smoking vs. continuing to smoke and, if so, how long it
takes for the mortality experience of former smokers to
approximate that to never smokers. The data in the table below
were presented comparing former smokers with current
15. smokers.
Relationship of time since quitting to total mortality
Number of deaths
Number of person-years of follow-up
Current smokers
3,602
420,761
Former smokers
Quit <5 yrs
889
124,095
Quit 5-9 yrs
669
113,056
Quit 10-14 yrs
590
111,701
Quit 15-19 yrs
541
117,914
Quit 20+ yrs
1,707
336,177
What is the estimated mortality rate and 95% confidence
interval per 1000 person-years among current smokers?
16. Chapter 12 Homework
Multi-sample Inference
1. Some common strategies for treating hypertensive patients by
nonpharmacologic methods include (1)
weight reduction and (2) trying to get the patient to relax more
by mediational or other techniques.
Suppose these strategies are evaluated by randomizing
hypertensive patients to four group who receive
the following types of nonpharmacologic therapy: Group 1 :
Patients receive counseling for both weight
reduction and meditation.
Group 2 : Patients receive counseling for weight reduction but
not for meditation.
Group 3 : Patients receive counseling for meditation but not for
weight reduction.
Group 4 : Patients receive no counseling at all.
Suppose 20 hypertensive patients are assigned at random to
each of the four groups, and the change in
diastolic blood pressure (DBP) is noted in these patients after 1-
month period. The results are given
in the table below.
Change in DBP among hypertensive patients who receive
different kinds of nonpharmacologic therapy
Group Mean change in DBP (baseline-follow up) (mm-Hg) sd
change n
1 8.6 6.2 20
2 5.3 5.4 20
3 4.9 7.0 20
4 1.1 6.5 20
(a) Test the hypothesis that mean change in DBP is the same
among the four groups.
17. (b) Analyze whether counseling for weight reduction has a
significant effect on reducing blood pres-
sure.
(c) Analyze whether meditation instruction has a significant
effect on reducing blood pressure.
(d) Is there any relationship between the effects of weight-
reduction counseling and meditation coun-
seling on blood-pressure reduction? That is, does weight-
reduction counseling work better for
people who receive meditational counseling or for people who
do not receive meditation counsel-
ing, or is there no difference in effect between these two
subgroups?
1
2. A randomized trial examined the effects of lipid-modifying
therapy (simvastatin plus niacin) and an-
tioxidants (vitamins E and C, beta-carotene, and selenium) on
cardiovascular protection in patients
with clinical coronary disease, low HDL cholesterol, and normal
LDL cholesterol. A total of 160
patients were randomized into four groups: placebo lipid-
lowering and placebo antioxidants, active
lipid-lowering and placebo antioxidants, placebo lipid-lowering
and active antioxidants, or active lipid-
lowering and active antioxidants.
All participants had substantial stenoses (blockages) of the
coronary arteries quantified by catheteriza-
tion at baseline, and the primary endpoint was the percent
change in a person’s stenoses after 3 years
18. of treatment, with a positive change indicating an increased
amount of stenosis, as shown in the table
below. Because some patients did not complete the study, the
primary endpoint was assessed in 146
participants.
Mean changes (±sd), per patient, in the percentage of stenosis
by treatment group
Placebo Simvastain-niacin Antioxidants Simvastatin-niacin
(n = 34) (n = 33) (n = 39) plus antioxidants (n = 40)
Mean change in stenosis 3.9(±5.2) −0.4(±2.8) 1.8(±4.2)
0.7(±3.2)
(% of diameter)
Source: Based on The New England Journal of Medicine,
312(6), 329-334, 1985
(a) Perform a one-way ANOVA to assess whether there are
significant differences in mean change in
percent stenosis among the four groups.
(b) Using the LSD method, identify which pairs of groups are
significantly different.
(c) Are there significant interaction effects between
simvastatin-niacin and antioxidants? What does
an interaction effect mean in the context of this trial? (Hint:
Use the linear contrast y, y4 − y2 −
y3 + y1, where the group numbers are in the same order as in
the table above.
2
19. 3. Suppose we have separately analyzed the effects of 10 SNPs
comparing people with type I diabetes vs.
controls. The p-values from these separate analyses are given in
the table below.
Effects of 10 SNPs on type I diabetes
SNP p-value SNP p-value
1 .04 6 .62
2 .10 7 .001
3 .40 8 .01
4 .55 9 .80
5 .34 10 .005
(a) Use the Bonferroni method to correct for multiple
comparisons. Which SNPs show statistically
significant effects?
(b) Use the FDR method to correct for multiple comparisons
using an FDR=.05. Which SNPs show
statistically significant effects? How do the results compare
with those in part (a)?
3
Chapter 13 Homework
Design and Analysis Techniques for Epidemiologic Studies
1. In a 1985 study of the relationship between contraceptive use
and infertility, 89 of 283 infertile women,
compared with 640 of 3833 control (fertile) women, had used an
intrauterine device (IUD) at some
20. time in their lives.
(a) Use the normal-theory method to test for significant
differences in contraceptive-use patterns
between the two groups.
(b) Use the contingency-table method to perform the test in part
(a).
(c) Compare your results from part (a) and (b).
(d) Compute a 95% confidence interval for the difference in the
proportion of women who have ever
used IUDs between the infertile and fertile women in part (a).
(e) Compute the OR in favor of ever using an IUD for infertile
women vs. fertile women.
(f) Provide a 95% confidence interval for the true OR
corresponding to your answer in part (e).
(g) What is the relationship between your answers to part (b)
and (f).
1
2. The data in the table below were presented relating body
mass index (BMI) to progression of advanced
age-related macular degeneration (AMD), a common eye disease
in the elderly that results in significant
visual loss.
Association between BMI and progression of AMD
BMI Progression Non-progression
21. < 25 72 423
≥ 25 209 762
(a) What is the attributable risk (AR) of high BMI (≥ 25) for
progression of AMD?
(b) Provide a 95% confidence interval about this estimate.
2
Chapter 14 Homework
Hypothesis Testing: Person-Time Data
1. The data relating oral-contraceptive (OC) use and the
incidence of breast cancer in the age group 40-44
in the NHS are given in the table below.
Relationship between breast cancer incidence and OC use
among 40- to 44-year-old women in the
NHS
OC-use group Number of cases Number of person-years
Current users 19 4,761
Past users 164 121,091
Never users 113 98,091
(a) Compare the incidence density of breast cancer in current
users vs. never users, and report a
p-value.
(b) Compare the incidence density of breast cancer in past users
22. vs. never users, and report a p-value.
(c) Estimate the rate ratio comparing current users vs. never
users, and provide a 95% confidence
interval about this estimate.
(d) Estimate the rate ratio comparing past users vs. never users,
and provide a 95% confidence
interval.
(e) How much power did the study have detecting an IRR for
breast cancer of 1.5, comparing current
OC users vs. never OC users among 40- to 44-year-old women
if
i. the true incidence rate of breast cancer among never users and
the amount of person-time for
current and never users are the same in the table above,
ii. the expected number of events for never OC users is the same
as the observed number of
events in the table above,
iii. the average follow-up time per subject is the same for both
current and never OC users?
(f) What is the expected number of events that need to be
realized n each group to achieve 80%
power to detect an IRR for breast cancer of 1.5 for current OC
users vs never OC users under
teh same assumptions as in part (e)?
1
23. 2. Suppose we wish to study the association between aspirin
intake and the incidence of colon cancer.
We find that 10% of women take 7 aspirin tablets per week
(ASA group), while 50% of women never
take aspirin (control group). The ASA group is followed for
50,000 person-years, during which 34 new
colon cancers occurred over a 20-year period. The control group
is followed for 250,000 person-years,
during which 251 new colon cancers developed over a 20-year
period.
(a) What are the estimated incidence rates in the ASA and
control groups?
(b) Is there a significant difference between these incidence
rates? Report a p-value (two-tailed).
(c) What is the estimated rate ratio for colon cancer between the
ASA and placebo groups?
(d) Provide a 95% confidence interval for the rate ratio in part
(c).
(e) Suppose we look at the subset of women with a family
history of colon cancer. Aspirin might
be more beneficial in this high-risk subgroup. We have a total
of 5000 person-years among ASA
women and 2 events. We have a total of 20,000 person-years
among control women and 20 events.
Is there a significant difference in the incidence rates of colon
cancer between these 2 groups?
Provide a p-value (two-tailed).
2
24. 1. The data in the table are a sample from a larger data set
collected on people discharged from a selected Pennsylvania
hospital as part of a retrospective chart review of antibiotic
usage in hospitals.
Hospital-stay data
ID number Duration of hospital stay Received Antibiotics?
1 5 no
2 10 no
3 6 no
4 11 no
5 5 no
6 14 yes
7 30 yes
8 11 no
9 17 no
10 3 no
11 9 no
12 3 no
13 8 yes
14 8 yes
15 5 no
16 5 no
17 7 yes
18 4 no
19 3 yes
20 7 no
21 9 no
22 11 yes
23 11 no
24 9 no
25 4 no
Compute the mean and median for the duration of
hospitalization for the 25 patients.
25. 2. Using the table from Problem 1, compute the standard
deviation and range for the duration of hospitalization for the
25 patients.
3. Select all types of measures of location:
Mode
Median
Standard Deviation
Arithmetic Mean
Variance
4. Suppose 6 of 15 students in a grade-school class develop
influenza, whereas 20% of grade-school students nationwide a
develop influenza. Is there evidence of an excessive number of
cases in the class? That is, what is the probability of obtaining
at least 6 cases in this class if the nationwide rate holds true?
5. Using the data from Problem 4, what is the expected number
of students in the class who will develop influenza?
6. Two events A and B are ___________________________ if
they cannot both happen at the same time. (Hint: the answer is
two words).
7. Serum cholesterol is an important risk factor for coronary
disease. We can show that serum cholesterol is approximately
normally distributed, with mean= 219 mg/dL and standard
deviation =50 mg/dL.
What proportion of the general population has borderline high-
cholesterol levels--that is, > 200 but < 250 mg/dL?
0.380
0.648
0.7324
0.620
26. 8. Much discussion has taken place concerning possible health
hazards from exposure to anesthetic gases. In one study
conducted in 1972, 525 Michigan nurse anesthetists were
surveyed by mail questionnaires and telephone interviews to
determine the incidence rate of cancer. Of this group, 7 women
reported having a new malignancy other than skin cancer during
1971.
What is the best estimate of the 1971 incidence rate from these
data?
9. Using the data from Problem 8, provide a 95% confidence
interval for the true incidence rate.
10. Choose the correct word for the following sentence: If the
results of a previous trial does not affect the result of the
following trial, then the results are __________________
(dependent or independent).
11. Approximately ___% of the probability mass falls within
two standard deviations (2 ) of the mean of a random variable.
95%
50%
68%
99.7%
12. Iron-deficiency anemia is an important nutritional health
problem in the United States. A dietary assessment was
performed on 51 boys 9 to 11 years of age whose families were
below the poverty level. The mean daily iron intake among
these boys was found to be 12.50 mg with a standard deviation
4.75 mg. Suppose the mean daily iron intake among a large
population of 9 to 11-year-old boys from all income strata is
14.44 mg. We want to test whether the mean iron intake among
the low-income group is different from that of the general
27. population.
State the hypotheses that we can use to consider this question.
Perform the hypothesis test using the critical-value method with
an alpha of 0.05, and summarize your findings. Report the p-
value for this test (may give a range that includes the p-value)
13. A clinical trial is called _____________________ if neither
the physician nor the patient knows what treatment he or she is
getting. (Hint: the blank is two words)
14. In a study, 28 adults with mild periodontal disease are
assessed before and 6 months after implementation of a dental -
education program intended to promote better oral hygiene.
After 6 months, periodontal status improved in 15 patients,
declined in 8, and remained the same in 5.
Assess the impact of the program statistically (use a two-sided
test).
15. Two drugs (A, B) are compared for the medical treatment of
duodenal ulcer. For this purpose, patients are carefully matched
with regard to age, gender, and clinical condition. The treatment
results based on 200 matched pairs show that for 89 matched
pairs both treatments are effective; for 90 matched pairs both
treatments are ineffective; for 5 matched pairs drug A is
effective, whereas drug B is ineffective; and for 16 matched
pairs drug B is effective, whereas drug A is ineffective.
What test procedure can be used to assess the results?
· McNemar's test for correlated proportions
· Fisher's Exact Test
· The Paired t Test
· The Sign Test
28. 16. The standard screening test for Down's syndrome is based
on a combination of maternal age and the level of serum alpha-
fetoprotein. Using this test 80% of Down's syndrome cases can
be identified, while 5% of normals are detected as positive.
What is the sensitivity and specificity of the test?
17. Lutein, an important carotenoid in the maintenance of ocular
health, has been found postmortem in th macula of eyes. Hence,
a study is planned to supplement patients with high doses of
lutein in capsule form to possibly prevent age-related macular
degeneration, an important eye disease that can cause partial or
total blindness in large numbers of elderly people.
To assess compliance in study participants, a blood sample will
be drawn. It is estimated that a serum lutein would indicate
that a participant is taking study medication.
The study began in 1999. A test sample of 9 participants had
their lutein level measured in 1999 and again in 2003. The
researchers found a calibration error in the 1999 assays, but the
2003 assays were correct. The data are shown in the table
below.
Serum-lutein data analyzed in 1999 and 2003
Sample 1999 Serum-lutein level 2003 Serum-lutein level
1 3.5 6.4
2 2.9 7.5
3 4.1 8.4
4 5.1 9.6
5 6.4 12.0
6 1.9 4.2
7 1.3 3.1
8 4.1 6.3
9 2.3 4.4
Mean 3.511 6.878
sd 1.616 2.839
29. Using regression methods, derive a calibration formula
predicting the 2003 level as a function of the 199 level.
y=0.999+1.674x
y=-0.999+1.674x
y=0.999-1.674x
y=0.999x+1.674
18. The probability of a _________________ (Type 1
error/Type 2 error) is the probability of accepting the null
hypothesis when H_1 is true.
19. In a ________________ study the same group of people is
followed over time.
longitudinal
cross-sectional
paired
double blind
20. A recent article by Kenfield et al. studied the relationship
between various aspects of smoking and mortality among
104,519 women in the Nurses' Health Study (NHS) from 1980-
2004. One issue is whether there is a mortality benefit from
quitting smoking vs. continuing to smoke and, if so, how long it
takes for the mortality experience of former smokers to
approximate that to never smokers. The data in the table below
were presented comparing former smokers with current
smokers.
Relationship of time since quitting to total mortality
Number of deaths
Number of person-years of follow-up
30. Current smokers
3,602
420,761
Former smokers
Quit <5 yrs
889
124,095
Quit 5-9 yrs
669
113,056
Quit 10-14 yrs
590
111,701
Quit 15-19 yrs
541
117,914
Quit 20+ yrs
1,707
336,177
What is the estimated mortality rate and 95% confidence
interval per 1000 person-years among current smokers?