AP STAT: EXAM REVIEW: Unit 3

A cause and effect relationship between 2 variables can best de determined from which of the following? A. a survey conducted using an SRS of individuals B. a survey conducted using a stratified random sample of individuals C. when the 2 variables have a correlation coefficient near 1 or -1 D. an observational study where the observational units are chosen randomly E. a controlled experiment where the observational units are assigned randomly

E. a controlled experiment where the observational units are assigned randomly

In which of the following situations would it be most difficult to use a census? A. to determine what proportion of licensed bicycles on a university campus have lights B. to determine what proportion of students in a high school supported wearing uniforms C. to determine what proportion of registered students enrolled in a college employed more than 20 hours a week D. to determine what proportion of single-family dwellings in a small town have 2-car garages E. to determine what proportion of fish in Lake Michigan are bass

E. to determine what proportion of fish in Lake Michigan are bass

A confounding variable can/cannot be distinguished

cannot

Name the sampling strategy: Randomly select 10 stores around the country and survey all the employees that work at those stores.

cluster sample

Randomizes block design

experimental design that decreases the variability within the samples

Generating random digits on your calculator

rand Int(starting, ending, how many at a time)

Name the sampling strategy: Each employee has a 3-digit identification number. Randomly chose 40 numbers.

simple random sample

Sample

those who actually respond

Matched pairs method of sampling is used to compare _____ treatments

2

A candidate for mayor of Dallas calls 1,000 people chosen at random from the city telephone directory; 850 of them respond. What are the sampling frame and the sample in this example? A. SF: the telephone directory. S: the 850 people who respond B. SF: the telephone directory. S: the 1,000 people who are called C. SF: the 1,000 people who are called. S: the 850 people who respond D. SF: all Dallas residents. S: the 1,000 people who are called E. SF: all Dallas residnts. S: the 850 people who respond

A. SF: the telephone directory. S: the 850 people who respond

A stratified random sample addresses the same issues as which of the following experimental designs? A. a block design B. a double-blind experiment C. an experiment with a placebo D. a matched pairs design E. a confounded, nonrandomized study

A. a block design

The manager of a public swimming pool wants to compare the effectiveness of 2 laundry detergents, detergent A and detergent B, in cleaning the towels that are used daily. As each dirty towel is turned in, it is placed into the only washing machine on the premises. When the washing machine contains 20 towels, the manager flips a coin to determine whether detergent A or detergent B will be used for that load. The cleanliness of the load of towels is rated on a scale of 1 to 10 by a person who does not know which detergent was used. The manager continues this experiment for many days. Which of the following best describes the manager's study? A. a completely randomized design B. a randomized block design with detergent A and detergent B as blocks C. a randomizes block design with the washing machine as the block D. a matched-pairs design with detergent A and detergent B as the pair E. an observational study

A. a completely randomized design

Suppose that 30% of the subscribers to a cable television service watch the shopping channel at least once a week. You are to design a simulation to estimate the probability that none of 5 randomly selected subscribers watches the shopping channel at least once a week. Which of the following assignments of the digits 0 through 9 would be appropriate for modeling an individual subscriber's behavior in this simulation? A. assign 0,1,2 as watching the shopping channel at least once a week and 3,4,5,6,7,8, and 9 as not watching B. assign 1,2,3,4 as watching the shopping channel at least once a week and 4,5,6,7,8, and 9 as not watching C. assign 1,2,3,4,5 as watching the shopping channel at least once a week and 6,7,8,9 and 0 as not watching D. assign 0 as watching the shopping channel at least once a week and 1,2,3,4 and 5 as not watching; ignore digits 6,7,8, and 9 E. assign 3 as watching the shopping channel at least once a week and 0,1;2,4,5,6,7,8 and 9 as not watching

A. assign 0,1,2 as watching the shopping channel at least once a week and 3,4,5,6,7,8, and 9 as not watching

In an experiment, the primary purpose of blinding is to reduce A. bias B. confounding C. randomness D. under-coverage E. variation

A. bias

An important advantage of using a randomized block design in an experiment is: A. it controls for the effects of factors that may confound your results B. eliminating of all possible lurking variables that may confound the effect of the treatment C. reducing bias associated with using multiple interviewers D. collecting information from the subjects before and after the administration of a treatment E. all of above

A. it controls for the effects of factors that may confound your results

A researcher is testing the effect of a new fertilizer on crop growth. He marks 30 plots in a field, splits the plots in half, and randomly assigns the new fertilizer to one half of the plot and the old fertilizer to the other half. After 4 weeks, he measures the crop yield and compares the effects of the two fertilizers. This design is an example of A. matched pairs experiment B. completely randomized comparative experiment C. cluster experiment D. double-blind experiment E. this is not an experiment

A. matched pairs experiment

Which of the following statements is true? A. nonresponse can cause bias in surveys because nonrespondents may have different opinions than people who responded B. bias arising from undercoverage can be compensated for by increasing sample size C. stratified random sampling is often employed to reduce the impact of response bias D. people's responses to survey questions tend not to be influenced by the age, race, or sex of the interviewer E. sophisticated statistical methods can always correct the results if the population you are sampling from is different from the population of interest, for example, due to undercoverage

A. nonresponse can cause bias in surveys because nonrespondents may have different opinions than people who responded

A member of Congress wants to know what his constituents think of proposed legislation on health insurance. His staff reports that 228 letters have been received on the subject, of which 193 opposed the legislation. What is the population in this situation? A. the constituents B. the 228 letters received C. the 193 opposing the legislation D. Congress E. none of the above

A. the constituents

A probability sample is any sample in which A. every member of the population has the same chance of being selected B. every member of the population has a known, nonzero chance of being selected C. the population is first divided into groups of similar individuals and then a separate SRS is selected from each group and combined to form the full sample D. all collections of members of the population have the same chance of being selected

B. every member of the population has a known, nonzero chance of being selected

The most important advantage of experiments over observational studies is that A. experiments are usually easier to carry out B. experiments can give better evidence of causation C. confounding cannot happen in experiments D. an observational study cannot have a response variable E. observational studies cannot use random samples

B. experiments can give better evidence of causation

What is the one reason for using random allocation to assign units to treatments in an experiment? A. to produce the placebo effect B. to produce experimental groups that are similar C. to eliminate lack of realism D. to produce the blocks in a block design

B. to produce experimental groups that are similar

A local tax reform group polls the residents of the school district and asks the question, "Do you think the school board should stop spending taxpayers' money on non-essential arts programs in elementary schools?" The results of this poll are likely to A. underestimate support for arts programs because of undercoverage B. underestimate support for arts programs because of non-sampling error C. overestimate support for arts programs because of undercoverage D. overestimate support for arts programs because of non-sampling error E. accurately estimate support for arts programs

B. underestimate support for arts programs because of non-sampling error

Which of the following are true statements? 1. voluntary response samples often underrepresent people with strong opinions 2. convenience samples with non-neutral wording often lead to under coverage bias 3. questionnaires with non-neutral wording are likely to have response bias A. 1 and 2 B. 1 and 3 C. 2 and 3 D. 1, 2, and 3 E. none of the above give the correct set of responses

C. 2 and 3

Which of the following is not a major principle of good design for all experiments? A. comparison to a control B. replication C. blocking D. randomization E. all of these are significant for every experiment

C. blocking

In an experiment, an observed effect so large that it would rarely occur by chance is called A. an outlier B. influential C. statistically significant D. bias E. replication

C. statistically significant

The results of an experiment are said to be statistically significant if what? A. they are important to statisticians, regardless of their importance to the investigators B. both researchers and statisticians agree the results are meaningful and important C. the observed effect is too large to attribute plausible to chance D. they support the findings of previous, similar study

C. the observed effect is too large to attribute plausible to chance

For a certain experiment you have 8 subjects, of which 4 are female and 4 are male. The names of the subjects are listed below: Males: atwater, bacon, chu, diaz Females: johnson, king, liu, moore There are 2 treatments, A and B. If a randomized block design is used, with the subjects blocked by their gender, which of the following is not a possible group of subjects who receive treatment A? A. atwater, chu, king, liu B. bacon, chu, liu, moore C. atwater, diaz, liu, king D. atwater, bacon, chu, johnson E. atwater, bacon, johnson, king

D. atwater, bacon, chu, johnson

When working on a table of random digits and you need 50 labels, use ___-___

01-50

Suppose that the night before a national election, the host of a radio show asked callers to call his program and indicate which of the candidates they would vote for. At the end of the program, the radio show host indicated that, based on his survey, a certain candidate would likely win. However, on the election day, the candidate lost. Which of the following is the most likely explanation for why the radio show's survey was wrong? A. the survey was voluntary, and only those who wanted to participate did B. the question to the callers was slanted, producing incorrect results C. a large number of callers lied in their responses D. the survey was accurate, but many people changed their minds when they voted E. the sample size was too small

A. the survey was voluntary, and only those who wanted to participate did

A polling form is interested in surveying a representative sample of registered voters in the US. The form has automated its sampling so that random phone numbers within the US are called. Each time a number is called, the procedure below is followed. if there is no response or if an answering machine is reached, another number is automatically called if a person answers, a survey worker verifies that the person is at least 18 years of age if the person is not at least 18 years of age, no response is recorded, and another number is called if the person is at least 18 years of age, that person is surveyed Some people claim the procedure being used does not permit the results to be extended to all registered voters. Which of the following is NOT a legitimate concern about the procedure being used? A. registered voters with children under the age of 18 years may be underrepresented in the sample B. registered voters with unlisted telephone numbers may be underrepresented in the sample C. registered voters who have more than one telephone number may be overrepresented in the sample D. registered voters who live in households consisting of more than one voter may be underrepresented E. people who are not registered to vote may bias the sample results

B. registered voters with unlisted telephone numbers may be underrepresented in the sample

When the effects of 2 variables in an experiment cannot be separates and hence we cannot say which is responsible for the observed responses, we say the variables are what? A. dependent B. factors C. confounded D. blocked

C. confounded

If changes in a response variable are due to the effects of the explanatory variable as well as the effects of lurking variables, and we cannot distinguish between these effects, we are said to have A. a cause and effect relation between the explanatory and response variable B. a placebo effect C. confounding D. correlation E. extrapolated

C. confounding

A researcher identifies a sample of teenagers and chooses 2 males, both 16, from lower-income families. She randomly assigns one of the males to be in an intensive tutoring course; she places the second male in a standard classroom. She continues doing this with pairs of males and females. This is an example of A. blocking based on gender B. match pairs on responses before and after the tutoring session C. matched pairs on gender, age, and income status for random assignment D. completely randomized teenagers to treatment and control groups E. blocking teenagers based on gender, age, and income status

C. matched pairs on gender, age, and income status for random assignment

A new cough medicine was given to a group of 25 subjects who had a cough due to the common cold. 30 minutes after taking the new medicine, 20 of the subjects reported that their coughs had disappeared. From this information you conclude A. that the remedy is effective for the treatment of coughs B. nothing, because the sample size is too small C. nothing, because there is no control group for comparison D. that the new treatment is better than the old medicine E. that the remedy is not effective for the treatment of coughs

C. nothing, because there is no control group for comparison

At a college the scores on the chemistry final exam are approximately normally distributed, with a mean of 75 and a SD of 12. The scores on the calculus final are also approximately normally distributed with a mean of 80 and a SD of 8. A student scored 81 on the chemistry final and 84 on the calculus final. Relative to the students in each respective class, in which subject did this student do better? A. the student did better in chemistry B. the student did better in calculus C. the student did equally well in each course D. there is no basis for comparison E. there is not enough information, because the number of students in each class is not known

C. the student did equally well in each course

To check the effect of cold temperature on the elasticity of two brands of rubber bands, one box of Brand A and one box of Brand B rubber bands are tested. 10 bands from the Brand A box are placed in a freezer for 2 hours and 10 bands from Brand B are kept at room temperature. The amount of stretch before breakage is measure on each rubber band, and the mean for the cold bands is compared to the mean for the others. Is this a good experimental design? A. no, because the means are not proper statistics for comparison B. no, because more than 2 bands should be used C. no, because more temperatures should be used D. no, because temperature is confounded with brand E. yes

D. no, because temperature is confounded with brand

A consumer product agency tests oles per gallon for a sample of automobiles using each of 4 different octanes of gasoline. Which of the following is true? A. there are 4 explanatory variables and 1 response variable B. there is 1 explanatory variable with 4 levels of response C. milers per gallon is the only explanatory variable, but there are 4 response variables corresponding to the different octanes D. there are 4 levels of a single explanatory variable E. none of the above are true

D. there are 4 levels of a single explanatory variable

A study of existing records of 27,000 automobile accidents involving children in Michigan found that about 10% of children who were wearing a seatbelt (group SB) were injured and that about 15% of children who were not wearing a seatbelt (group NSB) were injured. Which of the following statements should NOT be included in a summary report about this study? A. driver behavior may be a potential confounding factor B. the child's location in the car may be a potential confounding factor C. this study was not an experiment, and cause and effect inferences are not warranted D. this study demonstrates clearly that seat belts save children from injury E. seatbelt usage is associated with child injury during automobile accidents involving children

D. this study demonstrates clearly that seat belts save children from injury

The essential difference between an experiment and an observational study is that A. observational studies may have confounded variables, but experiments never do B. in an experiment, people must give their informed consent before being allowed to participate C. observational studies are always biased D. observational studies cannot have response variables E. an experiment imposes treatments on the subjects, but an observational study does not

E. an experiment imposes treatments on the subjects, but an observational study does not

Can watching a movie temporarily raise your pulse rate? Researchers have 50 volunteers check their pulse rates. Then they watch an action film, after which they take their pulse rates once more. Which aspect of experimentation is present in this research? A. a placebo B. blinding C. randomization D. a control group E. none of these

E. none of these

Which of the following are true statements? 1. under-coverage bias can be overcome by greatly increasing the sample size 2. well-designed probability samples always eliminate bias 3. response bias results only from the wording of survey questions A. 1 only B. 2 only C. 3 only D. 2 and 3 E. none of these

E. none of these

Population

intended group, all residents of ____

Voluntary response bias

introduced when individuals can chose on their own to participate in the sample, not recoverable

3 requirements of an SRS

label, randomize, select

Name the sampling strategy: Choose the 4th person that arrives to work for each shift.

systematic sample

The Physician's Health Study, a large medical experiment, involving 22,000 male physicians, attempted to determine whether aspirin could help prevent heart attacks. In this study, one group of about 11,0000 physicians took an aspiring every other day, while a control group took a placebo. After several years, it was determined that the physicians in the group that took aspiring had significantly fewer heart attacks than the physicians in the control group. Which of the following statements explains why it would not be appropriate to say that everyone should take an aspiring every other day? 1. the study included only physicians, and different results may occur in other occupations 2. the study included only males and there may be different results for females 3. although taking aspirin may be helpful in preventing heart attacks, it may be harmful to some other aspects of health A. 1 only B. 2 only C. 3 only D. 2 and 3 only E. 1, 2, and 3

E. 1, 2, and 3

The buyer for an electronics store wants to estimate the proportion of defective wireless game controllers in a shipment of 5,000 controllers from the store's primary supplier. The shipment consists of 200 boxes each containing 25 controllers. The buyer numbers the boxes from 1 to 200 and randomly selects six numbers in that range. She then opens the six boxes with the corresponding numbers, examines all 25 controllers in each of these boxes, and determines the proportion of the 150 controllers that are defective. What type of sample is this? A. biased random sample B. nonrandom sample C. simple random sample D. stratified random sample E. cluster random sample

E. cluster random sample

Double-blind stufy

both subjects and evaluators are unaware

Lurking variable

variable associated with both y and x that makes it appear that x may be causing y

Confounding variable

variable whose effects on y can't be distinguished from the effect of x

A researcher wishes to test a new drug developed to treat hypertension (high blood pressure). A group of 40 hypertensive men and 60 hypertensive women is to be used. The experimenter randomly assigns 20 of the men and 30 of the women to the placebo and assigns the rest to the treatment. The major reason for separate assignment for men and women is that A. it is a large study with 100 subjects B. the new drug may affect men and women differently C. the new drug may affect hypertensive and non-hypertensive people differently D. this design uses matched pairs to detect the new-drug effect E. there must be an equal number of subjects in both the placebo group and the treatment group

B. the new drug may affect men and women differently

In the late 1990's, Scotland was considering independence from England. An opinion poll showed that 51% of Scots favor "independence." Another poll taken at the same time showed that only 34% favored being "separate" from England. The reason these differ by so much is that A. samples will usually differ just by chance due to random sampling B. the wording of questions has a big effect on poll results C. more follow-up efforts reduced the nonresponse rate of the second poll D. the sample sizes are different, so the margins of error are different E. the second poll suffered from undercoverage

B. the wording of questions has a big effect on poll results

A researcher is testing a company's new stain remover. He has contracted with 40 families who have agreed to test the product. He randomly assigns 20 families to the group that will use the new stain remover and 20 to the group that will use the company's current product. The most important reason for this random assignment is that A. randomization makes the analysis easier since the data can be collected and entered into the computer in any order B. randomization eliminates the impact of any confounding variables C. randomization is a good way to create 2 groups of 20 families that are as similar as possible, except for the treatments they receive D. randomization ensures that the study is double-blind E. randomization reduces the impact of outliers

C. randomization is a good way to create 2 groups of 20 families that are as similar as possible, except for the treatments they receive

A movie studio runs an experiment in order to decide which of 2 previews to use for its advertising campaign for an upcoming movie. One preview features the movie's romantic scenes and is expected to appeal more to women. The other preview features the movie's action scenes and is expected to appeal more to men. 16 subjects take part in this experiment, 8 women and 8 men. After viewing one of the previews, each person will rate how much he or she wants to see the movie. Which of the following best describes how blocking should be used in this experiment? A. use blocking, with half the mean and half the women in each block B. do not block, because the preview that is chosen will have to be shown to audiences consisting of both men and women C. do not block, because the response will be confounded with gender D. use blocking, with the men in one block and the women in the other E. do not block, because the number of subjects is too small

D. use blocking, with the men in one block and the women in the other

A researcher planning a survey of heads of households in New York has census lists for each of the 62 counties in the state. The procedure will be to obtain a simple random sample of heads of households from each of the counties rather than grouping all the census lists together and obtaining a sample from the entire group. Which of the following is a true statement about the resulting stratified sample? 1. it is more susceptible to bias than would be a simple random sample 2. it is easier and more cost effective than a simple random sample 3. it gives comparative information that a simple random sample wouldn't give A. 1 and 2 B. 1 and 3 C. 2 and 3 D. 1, 2, and 3 E. none of the above gives the complete set of true responses

E. none of the above gives the complete set of true responses

A bank surveyed all of its 60 employees to determine the proportion who participate in volunteer activities. Which of the following statements is true? A. the bank should not use the data from this survey because this is an observational study B. the bank can use the result of this survey to prove that woking for the bank causes employees to participate in volunteer activities C. the bank did not select a random sample of employees, so the survey will not provide the bank with useful information D. the bank would have to use the survey to construct a confidence interval in order to estimate the proportion of employees who participate in volunteer activities E. the bank does not need to use an inference procedure to determine the proportion of employees who participate in volunteer activities because the survey was a census of all employees.

E. the bank does not need to use an inference procedure to determine the proportion of employees who participate in volunteer activities because the survey was a census of all employees.

Response bias

anything in the design that influenced responses, interview behavior, wording of the question

3 principles of experimental design

control, randomization, replication

Undercoverage

design flaw that leaves a part of the population out or gives a part of the population less representation, can recover if you can identify and go after them

Advantage of adding a control group

it will reduce variability of the responses, makes it easier to detect differences among treatment groups

Nonresponse bias

large fraction os those samples fails to respond, can recover if you can identify and go after them

An advantage to a stratified sample

more demographics/regions can be represented

With a voluntary sample, many who have stronger negative/positive opinions are left out

negative

Example of matched pairs

one new shoe and one old shoe to test the efficiency of the new shoes

Random digits are truly _____

random, if another list of random digits is used to select the sample, the results obtained with the list actually used would be just as likely to be selected as any other set of 3 names

Blocking

reduces variability within the treatment groups

Name the sampling strategy: There are 4 employee classifications: supervisors, full-time clerks, part-time clerks, and maintenance staff. Randomly select 10 people from each category.

stratified sample