Extrapolation (Models)

1. (4pts)  Class and the book described 5 examples of extrapolation, listed below.  For which of those was the extrapolation eventually replaced by observations suggesting that the original extrapolation was incorrect?  MTF

A)    a chemicalÕs maximum exposure threshold at 1 millionth of the LD50 dose in a suitable rodent model

B)    fetal alcohol syndrome

C)    rodent models of cancer

D)    risk of second-hand tobacco smoke

 

2. (3pts).  Four graphs of extrapolation were illustrated in lecture and the book.  To which types of extrapolation do the graphs apply?  MTF

A)    extrapolation across species (fish to humans)

B)    extrapolation across doses

C)    extrapolation across related hazards

 

Errors in Data

 

3. (4pts)  Two samples of opinion from the same student body differ but the difference is not statistically significant.  To what type of error do we attribute the difference?  One answer only.

A)  Sampling        B) Bias         C) RPA             D) Human and technical                       E) None

 

4. (4pts) Pre-election polls often use a particular medium for contacting people (e.g., landline phones).  Although polls typically involve thousands of participants, and multiple polls are taken, their results often differ by large margins and in the same direction from the election results.  What type of error accounts for the difference between voter opinions measured by polls and the voter opinions in the actual election?  One answer only.

A)  Sampling        B) Bias         C) RPA             D) Human and technical                       E) None

 

5. (4 pts) Charmin advertises 500 sheets of toilet paper per roll.  A competitor decides to check out the claim, but instead of counting the sheets, takes the following shortcut.  The competitor measures the length of 5 sheets to the nearest 1/6 inch, multiplies it by 100 and compares it to the length of the entire roll.   The entire roll comes out 7 inches short of the calculated length for 500 sheets, and a single sheet is 4 inches long.  The competitor thus claims fraudulent advertising by Charmin, but an actual count reveals that there were indeed 500 sheets in the roll.  What type of error accounts for the difference between the calculated number of sheets and the actual number of sheets? (one answer only)

 

A)  Sampling        B) Bias         C) RPA             D) Human and technical                       E) None

 

6. (4 pts)  A survey of several hundred men and women between the ages of 20 and 40 finds that 4/5 of women do not like to spend Sunday watching football, whereas half the men do prefer this activity.  The difference is observed in a follow-up survey.  What type of data error is indicated by the consistent difference between the sexes in preference for watching football on Sunday? (one answer only)

 

A)  Sampling        B) Bias         C) RPA             D) Human and technical                       E) None

 

7. (5 pts) A customer complains that prices charged at the Far West HEB grocery store are often different than the advertised prices, and further suggests that the difference often goes in favor of the store (the charged price is usually higher than the advertised price).  The store does an audit of all 2630 items it sells and finds that there are several items marked differently than charged.  A distribution of the differences is shown below;

the center bar at 0 represents items for which the charged price was the same as the advertised price;

bars to the left of center are items in which charged price was more than advertised,

bars to the right are those in which the charged price was less than advertised.

 

Which options fairly describe the data and the customer complaints?  MTF

 

A)    The suggestion that the store usually charges more than advertised is a claim that the price differences are biased.

B)    The distribution shown clearly supports a claim of bias against customers because of the tall bar to left of center (at Ð1).

C)    The distribution shown clearly supports a claim of bias in favor of customers because of the tall bar to right of center (at +1).

D)    The study cannot assess bias because the 2630 items were not chosen randomly.

 

Ideal Data : Fixes

8.  (4pts) In which of the following studies would the protocol need to include a design feature to ensure that subjects are blinded to avoid bias?  Do not choose any options in which a blind design feature would not be possible or would not be necessary.  All options describe the subjects (underlined) as well as the purpose of the study.  MTF

A)    Rats fed a substance to see if it causes cancer in them.

B)    Humans accidentally exposed to a high dose of a chemical now being observed because they fear its possible toxic effects. 

C)    Students filling out a form graded by a machine to test whether they respond favorably to a scam. 

D)    Different car repair shops in Austin being evaluated by an independent agency to find out if they treat the average customer fairly.

 

9.  - 11 (3 pts each) In the following table, fill in the appropriate ÔfixesÕ for each type of error.  A fix may merely enable you to detect the error.  MTF

Error

ÔFixÕ

Sampling

  9. (A)  replication        (B) random       (C) blind           (D) standards

Bias

10. (A)  replication        (B) random       (C) blind           (D) standards

Human and technical

11. (A)  replication        (B) random       (C) blind           (D) standards

(12, 13). For each of the following statements, mark the appropriate letters that describe the features present. Mark a data feature only if it is explicitly present at some level in the problem description.

 

12. (4pts). An instructor gives two exams during the first part of the semester.  Both exams are on Wednesday, as has been the policy in the past.  The class complains that Monday exams would lead to higher scores, on the grounds that students are more rested and have more time to study immediately before Mondays.  The instructor bows to class pressure and gives the next two exams on Mondays.  The scores are not higher than for the first two exams, so the instructor concludes that the day of an exam makes no difference.      MTF

 

(A) explicit protocol

(C) standards

(E) blind

(B) replication

(D) random

(F) none

 

 

13. (4pts) You are hired as a consultant for a company selling home pregnancy tests to help them market a product that will be easy to use and give accurate results.  You advise them to put a picture of a woman on the front of the box and directions for use on the back.  Furthermore you suggest that they provide supplies for just a single test, so that if a woman wants to test herself again, she has to purchase a second kit.  Finally you suggest that they include a sample solution in the kit that will provide a definite positive result that can be used if the woman tests negative.  Which aspects of the ideal data template would be satisfied by a single kit if your recommendations are followed?  MTF

 

(A) explicit protocol

(C) standards

(E) blind

(B) replication

(D) random

(F) none

 

14 (4 pts).  The following pair of graphs was shown in relation to the coin flip demo in class.  Which points were illustrated by either or both graphs?  The horizontal axis is the proportion heads, and both horizontal axes span 0 to 1.  The left graph is based on 10 flips per observation, the right is based on over 1000 per observation. MTF

 

 

(A)    The left graph exhibits considerable RPA error, because the average proportion of heads inaccurately matches the observed number of people who got 50% heads. 

(B)    The left graph shows more replication (more coin flips) because there are more bars in the graph than in the right graph

(C)    Sampling error reduces bias

(D)    The right graph has the least sampling error.

(E)    With 10 flips per student, most of the class failed to get within 5% of the expected frequency (50% heads)

(F)     The left graph has more bias than the right because it has more observations well outside of 50%

 

 (15, 16). Do-it-yourself protocol. You are conducting an external review/test of a genotyping 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. 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. A ? indicates that you do not know the individualÕs status for that characteristic.  Your options for tube contents and tube labels are:

option

 tube label

Contents in the tube are from

Blood type

Gender

Marker status

(A)

Laura Baker

Laura Baker

B

Female

+

(B)

Harry Wichman

Harry Wichman

A

Male

?

(C)

Rachael Springman

Rachael Springman

AB

Female

+

(D)

#132

Harry Wichman

A

Male

?

(E)

#218

Patsy Cline

A

Female

+

(F)

#10

Pam Hines

O

Female

negative

(G)

Jerry Allison

Jerry Allison

A

Male

+

(H)

#101

Brent Iverson

AB

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, and the lab does not have prior information about the individuals.  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, etc.) 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 achieve replication of blood type but nothing else.  You should know both that blood type is replicated and that nothing else is replicated, and the replication should be blind to the lab (you can assume the lab will know gender from the name on the tube).

two tubes or I:              (A)        (B)        (C)        (D)        (E)        (F)        (G)       (H)            (I)

 

16. (3 pts) Make the tubes replicated for marker, gender and blood type, but all replication is blind to the lab.  You should know that the replication is present, even if you donÕt know the marker, gender, and blood type.

two tubes or I:              (A)        (B)        (C)        (D)        (E)        (F)        (G)       (H)            (I)

 

 

 

 

17. (5pts) Which options identify a ÒfixÓ for the type of error indicated; a ÒfixÓ may either reduce that error or at least allow  you to detect/measure that error in at least some cases. MTF

A)         error:  sample mix-up.  Fix: split the samples before testing; have each tested separately; look for discrepancies

B)         error:  the lab deliberately creates ÔdataÕ that they think the prosecution wants. Fix:  send requests to the lab blinded, so that the lab cannot discern what the prosecution wants

C)         error:  the RMP is calculated improperly due to inadequate protocol  Fix:  split samples before testing; have each tested separately; look for discrepancies

D)         error:  lab occasionally declares false matches, but they often go undetected.  Fix: split the samples before testing; have each tested separately; look for discrepancies

 

 

Drug Testing, DWI testing

           

18 (4pts) Which features of ideal data are mandated (in the Congressional record) for the Dept of Transportation drug testing program?  MTF

A)    replication

B)    standards

C)    blind

D)    explicit protocol

 

19. (3 pts). Which of the following would constitute 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

 

                                                              

 

DNA and Criminal Justice System

 

20. (4pts) For a technique used to declare a match between a forensic sample and a suspect, such as DNA typing, fingerprinting, or hair matching, what is the consequence of not having a reference database from the population?  MTF

A)    Without a reference database, it is not possible to conduct proficiency tests of lab error rates.

B)    Without a reference database, it is not possible to calculate a RMP (random match probability)

C)    Without a reference database, it is not possible to detect sample mixup

D)    Without a reference database, there is no benefit of blind procedures.

 

21. (4pts) If the lab declares a match between a suspect and a crime scene sample, and there is a very small probability of a random match (e.g., 1 in a billion) but a much larger probability that the lab made a mistake and falsely declared a match (e.g., 1%), what can be said about the odds that the suspect does not match the sample?               one answer

A)    The odds are still close to 1/billion because there is a 99% chance that the lab did NOT make a mistake, so 0.99x1/billion is still close to 1/billion.

B)    The odds are close to 1%, because 1% of the time the suspect will not match even though the lab indicates a match, and 1/billion times the match will be because of a random match.  1% + 1/billion is close to 1%.

C)    The odds are 1/billion divided by 1%, hence 1/(10 million)

D)    The odds cannot be calculated when two types of error are present.

 

22 (4pts) Which of the following options were said to be ideal characteristics of a forensic method to identify people?  MTF

(A)   The methods are kept confidential to the lab performing the test

(B)   A reference database exists

(C)   The characteristics measured vary continuously, are not discrete

(D)   The methods and labs are able to pass proficiency tests

(E)   The method should only be used if it can show that each person is different from everyone else

 

23 (4pts) An eyewitness video was shown in class in which a single young male was observed.  Following that video, the individuals in the class were asked to identify that person in a line-up.  Which of the following is/are true as pertains to the purpose or content of that demo?  MTF

(A)  Bias:  the demo showed how subtle clues given about the nature of the person you saw (height, appearance) could lead you to identify the wrong person even when the right person is present in the same line-up.

(B)  Bias:  the demo showed how instructions about who may be present in the line-up could influence whether you identify the wrong person

(C)  Bias:  the demo showed how the order of suspects in a line-up matter Ð that you are likely to choose someone in the middle

(D)  Accuracy of eyewitness ID:  at least 1/4 of the class identified the wrong person

(E)  Replication:  both classes were given the same instructions and choices; the responses were similar except for possible sampling error

 

24. (5pts) For which of the following methods was it said that labs failed proficiency tests or failed to take proficiency tests (failure rate of at least 10% when tested)?  If a method was not mentioned in class, do not choose it.  MTF

 

(A) fingerprints Pre-1990

(C) DNA typing

(E) bite mark ID

(G) eyewitness ID

(B) fingerprints post-2000

(D) hair matching (by microscopy, not DNA)

(F) shoeprint ID

(H) dog sniffing

 

25 (3pts). Which are true of non-DNA based hair matching?

A)    It was used in US courts for several years and was a factor in several wrongful convictions

B)    Proficiency tests revealed error rates sometimes in excess of 50%

C)    It has been discredited in the U.S.

D)    There was no reference database for hair matching

 

 

26 (3pts) Which are true about current and past DNA typing methods?  (RMP = random match probability)

A)    The DNA typing method that now gives the lowest RMP uses DNA from mitochondria

B)    The Y-STR method can estimate the number of males in a sample

C)    The original technology for DNA typing involved visual comparison of an image (as shown in class)

D)    Current DNA typing methods were said to satisfy our 4 properties of an ideal identification method

E)    DNA suitable for typing can come from small tissue samples, such as the follicle end of a hair or something you have licked.

 

 

27. (3 pts.) Exam Key Code: Fill in bubbles (AB) on question 27 to indicate your exam code; leave the other bubbles blank.  Also, fill in the correct bubbles for your name and EID on the scantron form.

 

You must turn in this hard copy (with your name on it) and your scantron to receive credit for this exam.