CPS questions given in class (2 more will occur as options in other sections).
1. (5pts) The difficulties in estimating harmful effects of excess ionizing radiation include (MTF):
A) We have few people exposed to the low doses that are of greatest interest to us
B) There is not an accepted way of combining the effects of different types of radiation for measuring its health effects
C) The effects of moderate excess doses (e.g., 3 times the annual average) are slight, which makes it difficult to estimate the effects of low doses
D) In cases of large exposures, time lags occur between radiation exposure and cancer appearance, so that people exposed may die from other causes before they have time to develop a cancer from the radiation
E) There are no good non-human animal models for estimating the cancer-causing effects of low levels of (excess) radiation in humans.
F) A proliferation of electronic devices, such as microwave ovens and cell phones, has increased the U.S. population exposure to ionizing radiation in ways that cannot be easily measured.
2. (4pts) You conduct a survey of 200 people attending home football games, for all home games during the season. The poll questions are the same each game (all multiple choice), and each game you have pollsters gathering the same data in two ways from each participant to verify that they have given you their true response.
Which types of errors can plausibly explain any differences you observe between the distributions of responses obtained at different games (multiple T/F)?
(A) Sampling (B) Bias (C) RPA (D) None
3-6 (3pts each) Which types of errors are indicated in the following? (one answer each) Your options are
A) Sampling |
B) Human & Technical |
C) Bias |
D) RPA |
E) None |
3 (3 pts) You weigh yourself on a scale. It reads 155#, but you know your weight is 150#. You get off the scale, and it reads 5#. What type of error is indicated by the difference between your true weight and the weight indicated by the scale? (A) (B) (C) (D) (E)
4. (3pts) You reset the scale to 0 and get on it. Your exact weight is 150.3789 but the scale reads 150.
(A)
(B) (C) (D)
(E)
5. (3pts) You purchase 1 lotto ticket each week for a year in which the
weekly odds of winning are 1/1000. Your
7th wins but your other 51 don’t.
What type of “error” explains the discrepancy between the week you won
and the weeks you didn’t? (A) (B)
(C) (D) (E)
6 (3pts). You sample Austin for people’s attitudes about defaulting on student loans.
100 UT students: 51 favor no penalty
100 Austinites, not UT students: 10 favor no penalty
Which type of error plausibly explains the big difference between the two groups? (one only) (A) (B) (C) (D) (E)
7. (4pts) Which types of errors are lessened (or at least detected) with replication (MTF) ?
(A) Sampling (B) Human & Technical (C) Bias (D) RPA
8. (3pts) The split sample procedure in drug testing is an example of which property of ideal data (one only):
(A) Blind (B) Replication (C) Randomization (D) Standards
Radiation
9. (4 points).
Which are true? (easy)
(A) High doses
are used as models of low doses when calculating the cancer risk from radiation
exposure
(B)
The use of a single measure of radiation exposure for different types of
radiation (rem or rad) is a false model, at least because the different types
of radiation have different biological effects. It is therefore NOT a useful model for measuring the harmful
effect of radiation.
(C) The abstract models underlying our
understanding of the cancer risk caused by radiation include (i) different
types of cancer, (ii) different types of radiation, and (iii) different doses.
10. (4
pts). Which are true? (medium difficulty)
(A) The type of cancer most
commonly studied in conjunction with radiation has been leukemia because of its
relatively short time-lag between radiation exposure and appearance of the
cancer (5 years).
(B)
Living in Denver increases your background level of radiation compared
to living in Austin because of higher levels of radioactive potassium (K) in
your bones.
(C) We do not try to estimate elevated cancer rates from people given
medical X-rays on a yearly basis because the effects of this excess radiation
are too small to measure.
(11-13).
For each of the following descriptions, indicate the types of error present
(the italicized phrase identifies the
error). Mark a type of error only if it is definitely present. Do not assume
any more than what is explicitly mentioned in the problem. One answer only for each question.
|
(A)
Rounding, Precision and accuracy |
Types
of Error: |
(B)
Sampling |
|
(C)
Human and technical |
|
(D)
Bias |
|
(E)
No error is indicated |
11. (4 pts)
Two forms of an advertisement are tested to decide
which is better by giving either form to 200 students and then having them fill
out a questionnaire that reveals how well the advertisement worked. The two forms of the ad are assigned to
students randomly, and the students are unaware that there are different forms
of the ad. The questionnaire is
multiple choice and scored on a machine, whose performance is checked initially
by putting through a form whose answers are all known in advance. .
Overall, the responses to the two ads are slightly different, but a
statistical analysis indicates that these differences are not significant. What
type of error is used to explain the difference in responses to the two
forms of the advertisement? (one
answer only)
(A) (B) (C) (D) (E)
12. (4 pts) A
racing car’s performance on a track is compared with and without a fuel
additive. In multiple trials with and
without the additive, the car’s top speed is consistently 3 miles per hour
faster with the additive, but fuel use is also higher (per mile) with the
additive. Thus, it is determined that
the additive is advantageous only for short races, because more time is taken
refueling the car than is gained by the small increase in top speed. What type of error in data is indicated by the
difference in speed of the car with and without the fuel additive? (one
only)
(A) (B) (C) (D) (E)
13. (4 pts) Researchers in the late 1800s and early
1900s attempted to measure the “intelligence” of different human races by
filling empty skulls with lead shot to determine brain volume. They knew the race of each skull at the time
they were filling it and apparently (and unconsciously) took more care to
settle the shot in some skulls – of Caucasians – than in others. Thus, their
measures of brain volumes were smaller for the non-Caucasians (larger for
Caucasians) than should have been if the procedure had been conducted the same
on all skulls. What type of error is the systematic
difference in skull measurement between Caucasian skulls and non-Caucasian
skulls? (one only)
(A) (B) (C) (D) (E)
14 (6 pts)
Which of the following points about protocols (written procedures for data) are
correct? (MTF)
A)
Protocols are models with the goal of describing how
data are to be gathered and/or analyzed.
B)
If the protocol is followed, the types of errors
likely to be present in data can be understood from reading the protocol
C)
The point made in lecture that protocols have become
a substitute for data quality in some government arenas was illustrated with the example of the FBI DNA lab being
reviewed only for whether it was documenting on paper that it followed its
protocol, not how good its data were.
D)
An important means of reducing errors in data is to
change (improve) a protocol
E)
If followed to the letter, a
written procedure minimizes errors in the data. That is, most error creeps in because the data are not gathered
strictly according to the protocol (CPS question)
F)
Even
when the protocol is followed, there are usually many subtle ways in which the
written protocol does not describe how the data were collected. This is one way in which the written
procedure is a false model (CPS question)
15-16. Do-it-yourself protocol. You are conducting an
external review/test of a DNA lab. Your job is to send two tubes to the lab,
with labels. There are several options for the content of and label on a tube.
You must decide which contents to send and how to label the tubes so that the
features of ideal data requested in the question are present from the lab's perspective.
If a tube has a person's name on it, the lab can assume that the tube contents
belong to the name of the person on the label. If a tube is labeled with a
number, the contents are unknown to the lab but known to you. Your options for
tube contents and tube labels are:
option |
tube label |
Contents in the
tube are from |
Blood type |
Gender |
(A) |
Sam Brown |
Sam Brown |
A |
Male |
(B) |
Holly Berry |
Holly Berry |
B |
Female |
(C) |
Rachael King |
Rachael King |
O |
Female |
(D) |
#13 |
Joel Sachs |
AB |
Male |
(E) |
#21 |
Joel Sachs |
AB |
Male |
(F) |
#100 |
Pam Hines |
O |
Female |
(G) |
Anna Himler |
Anna Himler |
B |
Female |
(H) |
#17 |
Ulrich Mueller |
B |
Male |
(I) |
No combination of tubes can satisfy the protocol |
In the following questions, choose two letters among
options (A)-(H) to describe the two tubes that will be sent to the lab. The
tube labels are the only information the lab receives about the samples. If it
is possible to satisfy the protocol, the question will require exactly two
letters and only two letters --
one for each tube. Thus, the answer for a question might be (A) & (B), or
it might be (D) & (F). If more than one pair of options are possible
correct answers, fill in only one correct pair of options. Thus, if (A) &
(B) is one acceptable answer, and (C) & (D) is another acceptable answer, fill
in either (A)&(B) or
(C)&(D), but not both. If a factor
(such as identity, blood type, gender) is not specified in the protocol, then
that factor will be ignored in grading the answer. Alternatively, if a
protocol cannot be satisfied with
two from (A)-(H), fill in (I).
15. (3 pts) Choose two
tubes to guarantee replication of blood type but not individual or
gender; the replication of blood type should be fully blind to the lab –
that is, the lab should not be able to tell from the information on the tubes
that the two samples have the same blood type.
two tubes: (A) (B) (C) (D) (E) (F) (G) (H) (I)
16. (3 pts) Make the
tube identities fully blind to the lab and replicated for gender and
blood type but not replicated for individual.
two tubes: (A) (B) (C) (D) (E) (F) (G) (H) (I)
17.(4 pts). A recent change to the class protocol for collecting and recording homework has been implemented this semester because (one only)
A) The instructors found a new way to streamline the process
B) Too many homework grades were being challenged
C) An error occurred in keeping track of all homeworks.
D) No change in class protocol has been implemented this semester.
(18,
19). For each of the following statements, mark the appropriate letters
that describe the data design features present. Mark a data feature only if it
is explicitly present in the problem description. MTF
(A) explicit protocol |
(C)
standards |
(E)
blind |
(B)
replicates |
(D)
random |
(F)
none |
18. (4pts) Two forms of an advertisement are tested to decide which is better by
giving either form to 200 students and then having them fill out a
questionnaire that reveals how well the advertisement worked. The two forms of the ad are assigned to
students randomly, and the students are unaware that there are different forms
of the ad. The questionnaire is
multiple choice and scored on a machine, whose performance is checked initially
by putting through a form whose answers are all known in advance. Overall, the responses to the two ads are
slightly different, but a statistical analysis indicates that these differences
are not significant. What
features of ideal data are indicated?
(yes, this is the same as one used above for “error”)
(A) (B) (C) (D) (E) (F)
19. (4 pts) A police group decides to determine how gullible the public is to scams. Hundreds of people are sent invitations to seminars about how to obtain government subsidies (“free money”) for home improvement; of course, no mention is made in this invitation about the real purpose. Each person is invited to only one seminar, but different people are invited to different seminars, so that the police group can try different scamming methods and see which are the most effective. Approximately 50% of the invitees attend their seminar, where they are encouraged to provide the seminar organizers with social security numbers, bank account numbers, and other data that a con artist could use. The attendees are then informed of their vulnerability to scams. Which features are indicated?
(A) (B) (C) (D) (E) (F)
Drug Testing
20. ( 5 pts). What
constitutes a standard in a drug test for evaluating lab error rates? (MTF)
A)
A sample with a known level of drug present.
B)
A sample known to be drug-free.
C)
A written procedure describing the level of
performance to be upheld by the lab
D)
Any measure taken by the lab to detect or reduce
human and technical error
E)
A proficiency test given to the lab that does the
analysis, regardless of whether the test is blind.
21 (5 pts) Which
of the following properties of ideal data are mandated by for DoT drug-testing
procedures? MTF
A) Standards
are not part of the protocol but are often tested anyway
B) The
test procedure must be replicated for all positive samples
C) The
samples must be coded so that their identities are unknown to the lab
D) A
person who tests positive on a first test may request a second test
E) Samples
are to be tested in a random order
F) Monthly
proficiency tests are conducted by an outside agency
22
(4pts) Which of the following
properties apply to DNA and/or DNA typing? (MTF)
A) The RMP (random match probability) is typically less
than 1/billion for the best methods
B) In the Castro case, several lab errors and
violations of protocol were discovered that contributed to a gross
miscalculation of the RMP.
C) DNA typing using mitochondria usually has larger
RMPs (closer to 1.0) but can use poorer DNA samples than STR methods.
D) Blood is a poor source of DNA for typing because our
red blood cells do not have nuclei.
23
(5pts) Changes
to DNA typing methods since its inception include which of the following (MTF):
A) The RMP calculated in the famous, first DNA
typing case in Britain was only about 1/1000; it is now much, much smaller
(1/billion or better).
B) The basic principle underling DNA typing has not
changed – that we all have differences in our DNA that make us unique (except
for identical twins).
C) The DNA barcode is now read by a machine, so
false matches in DNA typing cases have almost been eliminated.
D) Most labs now subject themselves to blind
proficiency testing
E) The Houston Crime lab was recently exposed for
major problems in its DNA analyses.
24-26
(3 pts each). Fill in the blanks of
the “consequences” column of the table with the best single option (most
specific) from the list below the table.
The question number is given in each blank. One answer only per question.
Deviation from Ideal Data |
Consequences |
Samples not handled blindly |
24. |
Insufficient replication of the DNA typing process
in a case |
25.
|
Inadequate protocols for analysis of results |
26. |
Your choices
for consequences are:
(A) Improper calculation of RMP (random match
probability) in some cases
(B) DNA sample degradation occurs (loss of DNA
quality)
(C) The RMP threshold for conviction will appear to
be exceeded when it is actually not exceeded
(D) Sample mix-ups in a case can go undetected
(E) This protocol is no longer applicable because of
recent changes in DNA typing methods
(F) The protocol allows for a biased willingness to
accept results
(G) The STR (short tandem repeat) RMP will not match
the mitochondrial RMP
(H) The protocol increases the likelihood of sample
mix-up
(I) The full extent of lab error rates remains
unknown
(J) This
protocol allows outliers of natural variation to escape detection
27. (4 pts.) Exam
Key Code: Fill in (AB) on question 27 to indicate your exam code. Also, fill in the correct bubbles for your
name and pad number on the scantron form.