Deck 8: Measuring

Question 1

A radio talk show invites listeners to call a telephone number to vote Yes or No on whether they support a bond issue for a new school. About 1500 people call in. Over 80 percent say No. As an estimate of community opinion, this result is:

A) accurate to within ± 3 percent with 95 percent confidence.
B) not trustworthy because of nonsampling errors.
C) not valid because the sample size of 1500 is too small.
D) unethical due to lack of informed consent.
E) badly biased due to voluntary response.

Answer 1

badly biased due to voluntary response.

Question 2

In one of the first attempts to discover the speed of light, Simon Newcomb in 1882 made 66 measurements of the time light takes to travel between the Washington Monument and his laboratory on the Potomac River. Why did Newcomb repeat his measurement 66 times and take the average of the 66 as his final result?

A) Averaging several measurements reduces any bias that is present in the instruments.
B) The average of several measurements is more reliable (less variable) than a single measurement.
C) Even if a measuring process is not valid, averaging several measurements made by this process will be valid.
D) Both A and B are correct.
E) Answers A, B, and C are correct.

Answer 2

The average of several measurements is more reliable (less variable) than a single measurement.

Question 3

A researcher creates a machine that will measure the total electrical activity in a human brain over a short period of time. She claims that this measures the happiness of the brain's owner. A psychologist says that's not true because the amount of electrical activity isn't related to "the emotional state of well-being" usually called happiness. The psychologist is claiming that electrical activity as a measure of happiness is:

A) invalid.
B) biased.
C) not reliable.
D) not precise.

Answer 3

invalid.

Question 4

In order to inexpensively determine the contamination level of a sample of water, a new test is known to yield almost exactly the same value when repeatedly used on samples from the same container of water. However, these individual values are not close to the true average contamination level for the large container. The concern with using this new, cheaper test to determine the contamination level for a single sample of water is that this measurement method is not:

A) unbiased.
B) random.
C) valid.
D) reliable.
E) variable.

Question 5

IQ tests are intended to measure "general problem-solving ability," which is what people mean by intelligence. Some experts think IQ tests measure not intelligence but how much education and how much exposure to middle-class culture a person has. These experts say that IQ tests are:

A) biased.
B) not valid.
C) not reliable.
D) highly variable.
E) subject to nonsampling errors.

Question 6

A music professor says that his school's new test for "creative musical analysis" can't be trusted because the test counts any discordant string of pitches as creative. The music professor is attacking the test's:

A) validity.
B) reliability.
C) margin of error.
D) confidence level.

Question 7

A company used to give IQ tests to all job applicants. This is now illegal because IQ is not related to the performance of workers in all the company's jobs. That is, IQ as a measure of future performance on the job is:

A) biased.
B) invalid.
C) imprecise.
D) unreliable.
E) a sampling error.

Question 8

Professor Iconu has developed a new test of level of spiritual awareness for his course on religions of the world. Any such test must have several versions because some people take the test more than once. Unfortunately, it turns out that the same person often gets very different scores, depending on which version of the test is offered, even when taking the versions at nearly the same time. The test suffers from:

A) large bias.
B) confounding.
C) large sampling errors.
D) low reliability.

Question 9

It is hard to measure "intelligence." To do it the easy way, one can measure the circumference of the head, just above the ears, in inches, and call the result "intelligence." Not only is this method easy; it gives nearly the same number every time one repeats the measurement on the same person. Measuring intelligence this way is:

A) not reliable and not valid.
B) highly reliable but not valid.
C) valid but not reliable.
D) both valid and highly reliable.

Question 10

One might try to measure how rich people are by looking at the car they drive. In fact, driving a fancy car has little to do with income (most luxury cars are leased). In statistical terms, measuring income by car model is:

A) not reliable.
B) not valid.
C) biased.
D) not precise.

Question 11

A nephew visits his Aunt Tess for five days. Every morning he weighs himself, and the five readings are very different. When he gets home and compares the average from his aunt's scale to the reading on his scale (which he regards as his true weight), he realizes the average is almost exactly the same. As a measure of his weight on his scale, the reading on his aunt's scale is:

A) unbiased and reliable.
B) unbiased and unreliable.
C) 95 percent accurate.
D) biased and unreliable.
E) biased and reliable.

Question 12

Wake Forest University claims that SAT scores should not be used to predict college success (and no longer requires them for admission), because SAT scores do not adequately measure how well students will perform when they attend college. Thus, to predict college success, the SAT score measurement is claimed to be:

A) biased.
B) random.
C) invalid.
D) unreliable.
E) variable.

Question 13

The Environmental Protection Agency sends four identical samples of polluted water to the Acme Chemical Analysis Laboratory. The lab measures the amount of dioxin in each sample. The lab reports dioxin concentrations of 141, 323, 74, and 923 parts per billion. Dioxin measurements made by Acme are:

A) not reliable.
B) not biased.
C) invalid.
D) confounded.
E) categorical.

Question 14

Professor Ziegenfuss of the Geology Department has ordered a new instrument that is supposed to measure the iron content of iron ore. After the instrument arrives, he uses it to measure the iron content of five test samples of ore, all of which are known to be exactly 16 percent iron. The numbers given by the machine on these five test samples are 8 percent, 3 percent, 28 percent, 16 percent, and 25 percent. Based on these measurements, one can conclude that the new instrument:

A) is unbiased.
B) is not reliable.
C) suffers from the placebo effect.
D) is confounded.
E) Both A and B are correct.

Question 15

A local police department gives all job applicants a test in American history. However, experience shows that these test scores are unrelated to future job performance. As a measure of ability to do police work, the history test scores:

A) are response variables.
B) are biased.
C) are confounded.
D) are invalid.
E) have predictive validity.

Question 16

An office worker sets her coffee maker to start brewing coffee at 5:30 A.M. On some mornings it starts five minutes early. On others it starts 10 minutes early. It is always early, but there is no telling when the coffee will start to be made or be finished. The timer on the coffee maker is:

A) biased.
B) invalid.
C) imprecise.
D) unreliable.
E) a sampling error.

Question 17

A measurement process that does not systematically overstate or understate the true value of the quantity being measured is called:

A) valid.
B) reliable.
C) random.
D) unbiased.

Question 18

A local police department gives all job applicants a test of their knowledge of modern popular music. Experience shows that those who score well on this test tend to become very poor police officers. As a measure of future job performance, the music test scores:

A) are response variables.
B) are biased.
C) are confounded.
D) are invalid.
E) have predictive validity.

Question 19

In an experiment to study the effect of vibrations on plant growth, the height of a chrysanthemum was measured three times. The reason for making the measurement three times instead of just once was probably to:

A) decrease bias.
B) eliminate confounding.
C) increase reliability.
D) completely eliminate measurement error.

Question 20

"In American History, 20 students failed. Only 11 students failed World History. American History must be a more difficult course than World History." This statement is criticized because the measurement "number of students who fail" is being used as an indicator of "course difficulty." Thus, "number of students who fail" is claimed to be

A) categorical.
B) unreliable.
C) invalid.
D) confounded.
E) biased.

Question 21

Ex Regious State University, in its public relations materials for prospective students, proudly points out the accomplishments of its 96 alumni who have reached the zenith of their fields: millionaires, CEOs, and university presidents. They contrast this with Pricy Small U., a small private school, in the same town, with only 22 alumni who have reached similar levels of achievement in spite of the smaller school's greater cost.
What would be a more appropriate measure that would make the comparison fair?

A) Compare the percentage of students who have achieved those career goals.
B) Compare the number of students each year who have achieved those career goals.
C) Compare the number of students and staff who have achieved those career goals.
D) Compare the number of students who have not achieved those career goals.

Question 22

A local delicatessen has a scale on which the staff weigh the meat their customers buy. They don't realize it, but it always reads very close to 10 percent less than the actual weight, and they are losing money. The measurements from this scale are:

A) biased and unreliable.
B) biased and reliable.
C) unbiased and unreliable.
D) unbiased and reliable.

Question 23

Over the past few years, college enrollments have increased dramatically across the United States. Over this same time period, an educational task force reports that the number of students dropping out of college has significantly increased. A college newspaper reports on these results by stating, "In an effort to meet the demand of more students, it appears that colleges and universities are not providing the same level of support for students to graduate as they were a few years ago."
What is wrong with the college newspaper's interpretation of the results?

A) Because more people attend college these days, one should expect that more people will drop out of college.
B) The newspaper is assuming that students drop out because of a lack of support.
C) Both A and B are correct.
D) Neither A nor B is correct.

Question 24

A student's research shows that there were more car accidents in 2015 than there were in 1915. He concludes that people were better drivers in 1915 than in 2015.
Why is it not valid to use these two numbers to assess driving abilities in these two years?

A) People had more distractions on the road in 2010 than they had in 1910.
B) The numbers were compiled by a student instead of by a professional researcher.
C) The number of cars in the United States increased substantially from 1910 to 2010.
D) One shouldn't compare years that are so far apart.

Question 25

A student's research shows that there were more car accidents in 2015 than there were in 1915. He concludes that people were better drivers in 1915 than in 2015.
What would be a more appropriate or valid measure for this comparison?

A) Compare the number of car accidents in 1905 and 2005.
B) Compare the accident rates (percentages) for 1915 and 2015.
C) Compare the number of car accidents in those years, grouped by region.
D) Compare the number of people who don't have an accident for 1915 and 2015.

Question 26

Ex Regious State University, in its public relations materials for prospective students, proudly points out the accomplishments of its 96 alumni who have reached the zenith of their fields: millionaires, CEOs, and university presidents. They contrast this with Pricy Small U., a small private school, in the same town, with only 22 alumni who have reached similar levels of achievement in spite of the smaller school's greater cost.
Why is it not fair to use these two numbers to conclude that students from Ex Regious State do better in these fields than those of Pricy Small U.?

A) Ex Regious State's public relations department may be lying.
B) Where students go to school has nothing to do with how successful they are.
C) One school may have more students than the other school has.
D) They should be comparing athletic accomplishments.

Question 27

When repeated measurements each have a systematic error in the same direction, one says that the measurements contain:

A) precision.
B) random error.
C) bias.
D) measurement error.

Question 28

The diameter of a metal rod was measured eight times and the results in millimeters were: 29.2, 29.2, 29.1, 29.2, 29.2, 29.2, 29.3, 29.2. The true diameter of the rod is 29.2 millimeters. The measurement process appears to be:

A) biased and unreliable.
B) reliable but somewhat biased.
C) unbiased but unreliable.
D) unbiased and reliable.

Question 29

In a recent study on veterinary practices, 25 cases of negligence were discovered at 10 randomly selected large veterinary hospitals in the state, compared to 12 cases of negligence at 10 randomly selected small veterinary clinics in the state. "The data show that it is safer to take pets to small clinics because visits to small clinics result in fewer cases of negligence." What is wrong with the preceding statement?

A) Larger hospitals will be safer because they have more doctors.
B) There are more patients at larger hospitals, so percentages should be compared.
C) The measurements are obviously biased.
D) It is unethical because of a lack of informed consent.

Question 30

A measurement that yields highly variable results in repeated measurements on the same individual is said to be:

A) unreliable.
B) invalid.
C) unbiased.
D) random.

Question 31

Professor Faulpelz asks a random sample of high school freshmen about their TV viewing habits. Four years later, he obtains their final high school grade-point averages and compares these with the answers about TV viewing habits. He finds that students who watch a lot of TV get lower grades than those who don't. When it comes to high school GPA, the answers to the Faulpelz questionnaire on TV viewing habits:

A) have predictive validity.
B) are invalid because they are biased against students whose parents watch TV a lot.
C) are invalid because there were no controls.
D) are invalid because of convenience sampling.

Question 32

Over the past few years, college enrollments have increased dramatically across the United States. Over this same time period, an educational task force reports that the number of students dropping out of college has significantly increased. A college newspaper reports on these results by stating, "In an effort to meet the demand of more students, it appears that colleges and universities are not providing the same level of support for students to graduate as they were a few years ago."
What would be a more appropriate or valid measure for this comparison?

A) The number of students dropping out of college from 30 or more years ago should be compared to the number dropping out this year.
B) The percentage of students dropping out of college from a few years ago should be compared to the percentage from this year.
C) The number of students receiving support from a few years ago should be compared to the number receiving support this year.
D) There is no more appropriate or valid measure than what was used.

Question 33

How can one measure intelligence? One way is to measure the size of the brain. New technology makes it possible to measure the volume of a person's brain in cubic inches without injury. What is more, the measurement gives close to the same answer when one repeats it. But how big the brain is has no relation to how smart a person is. As a measure of intelligence, brain volume is:

A) reliable but invalid.
B) valid but not reliable.
C) valid and reliable.
D) not reliable and invalid.