a) each person may contribute only one response to the contingency table
b) the variables are measured on either an interval or ratio scale
c) there are at least 10 responses obtained in each cell of a 2x2 table
d) there are at least 5 responses obtained in each cell of a 2x3 or larger table
Answer: B
a) the interaction of Factor A with Factor B, and error variance
b) the effects of Factor A, Factor B and error variance
c) the interaction of Factor A with factor B
d) the effects of treatment Factor A and error variance
e) error variance
Answer: A
a) the interaction of the two treatment factors and error variance
b) the effect of Factor A
c) the effect of Factor A with Factor B removed
d) the effects of Factor A and error variance
e) error variance
Answer: D
Answer: they are predicting the same variance in Y
Answer: compare predictors's betas or standardized slopes
Answer: one goes into the equation because there is nothing the other two could add
I. This appears to be a well-conducted controlled experiment.
II. This observational study should be faulted for a lack of blinding.
III. A lurking variable involving who received what treatment makes any conclusion suspect.
A) I only
B) II only
C) III only
D) I and II
E) II and III
Answer: III only
A) Neither the volunteers nor the drug company executives know which volunteers are take the drug and which are taking the placebo.
B) Neither the volunteers nor the evaluator know which volunteers are taking the drug and which are taking the placebo.
C) The volunteers in both groups do not know whether they are taking the drug or the placebo.
D) The volunteers in both groups are blindfolded when they take the drug or placebo.
E) As long as the subjects are randomly assigned to the two groups, there is no need to make the experiment double-blinded.
Answer: neither the volunteers nor the evaluator know which volunteers are taking the drug and which are taking the placebo
A) This is not an experiment
B) Double-blind experiment
C) Matched pairs experiment
D) Cluster experiment
E) Completely randomized comparative experiment
Answer: Matched pairs experiment
A) Selection bias
B) Sampling bias
C) Nonresponse bias
D) Uncoverage bias
E) Response bias
Answer: Response bias
A) Large samples show less sampling variability.
B) The response variable will be measured more effectively.
C) It will be less of a problem if the randomization is imperfect.
D) There is a smaller probability of bias.
E) Large samples are more diverse.
Answer: large samples show less sampling variability
A) It uses a stratified sample rather than a simple random sample.
B) People who feel strongly about the issue are more likely to respond.
C) Some registered voters who call might not vote in the election.
D) Viewers should be told about the issues before the survey is conducted.
E) The wording of the question is biased.
Answer: people who feel strongly about the issue are more likely to respond
A) Same sex couples are likely to be underrepresented in the sample.
B) The wording of the question could influence the response.
C) Only those who feel strongly about the issue are likely to respond.
D) Not all registered voters who respond to the survey are likely to vote.
E) Married couples are likely to vote the same way.
Answer: the wording of the question could influence the response
A) After a population is separated into distinct groups, one or more of these groups are randomly selected in their entirety to be the sample.
B) A sample chosen in such a way that every possible sample of a given size has an equal chance to be the sample.
C) A value is randomly selected from an ordered list and then every nth value in the list after that first value is selected from the sample.
D) A sample in which respondents volunteer their response.
E) Select a sample in such a way that the proportion of some variables thought to impact the response is approximately the same in the sample as in the population.
Answer: a value is randomly selected from an ordered list and every nth value in the list after that first value is selected from the sample
A) Undercoverage
B) Response bias
C) Size of sample
D) Nonresponse
E) Voluntary response bias
Answer: Nonresponse
A) There was no control group.
B) Nonresponse bias
C) There was insufficient attention to the placebo effect.
D) Because final heights were not measured, it is impossible to tell if the hormone affected final height or only accelerated growth and made no difference to final height.
E) There was no blinding.
Answer: nonresponse bias
A) presence of a Major League baseball team causes the number of traffic incidents to rise (perhaps due to the large number of people leaving the ballpark.)
B) association is due to the presence of a lurking variable. (Major League teams tend to be in large cities with more people, hence a greater number of traffic incidents)
C) observed association is purely coincidental. It is implausible to believe the observed association could be anything other than accidental.
D) association makes no sense, since many people take public transit or walk to baseball games.
E) high number of traffic incidents is responsible for the presence of Major League baseball teams (more traffic incidents means more people have cars, making it easier for them to get to the ballpark.)
Answer: association is due to the presence of a lurking variable. (Major League teams tend to be in large cities with more people, hence a greater number of traffic incidents)
A) A controlled experiment where the observational units are assigned randomly.
B) When the two variables have a correlation coefficient near 1.
C) A survey conducted using a simple random sample of individuals.
D) An observational study where the observational units are chosen randomly.
E) A survey conducted using a stratified random sample of individuals
Answer: a controlled experiment where the observational units are assigned randomly
A) Have the volunteers wear the socks made from the new material for a month, and check the wear on the socks at the end of the month.
B) Allow half of the volunteers to wear cotton socks, while the other half wear socks made of the new material. Compare the wear on the socks at the end of the month.
C) For each volunteer, randomly choose which foot wears a cotton sock, while the other foot wears a sock made of the new material. Compare the wear on the socks at the end of the month.
D) Randomly assign half of the volunteers to wear cotton socks, while the other half wear socks made of the new material. Compare the wear on the socks at the end of the month.
E) Randomly assign half of the volunteers to wear cotton socks, while the other half wear socks made of the new material. At the end of two weeks, the volunteers should change sock types. Compare the wear on the socks at the end of the month.
Answer: for each volunteer, randomly choose which foot wears a cotton sock, while the other foot wears a sock made of the new material. compare the wear on the socks at the end of the month
A) Atwater, Bacon, Johnson, King
B) Atwater, Diaz, Liu, King
C) Atwater, Chu, King, Liu
D) Bacon, Chu, Liu
E) Atwater, Bacon, Chu, Johnson
Answer: Atwater, Bacon, Chu, Johnson
A) Assign 0, 1, 2, 3 as having a master's degree and 4, 5, 6, 7, 8, 9 as not having a degree.
B) Assign 0, 1 as having a master's degree and 2, 3, 4, 5, 6, 7, 8, 9 as not having a degree.
C) Assign 0, 1, 2 as having a master's degree and 4, 5, 6, 7, 8, 9 as not having a degree.
D) Assign 1, 2, 3, 4, 5 as having a master's degree and 0, 6, 7, 8, 9 as not having a degree.
E) Assign 7, 8, 9 as having a master's degree and 0, 1, 2, 3, 4, 5, 6 as not having a degree.
Answer: assign 0, 1, 2, 3 as having a master's degree and 4, 5, 6, 7, 8, 9 as not having a degree
A) Convenience
B) Simple random
C) Stratified random
D) Cluster
E) Systematic
Answer: Cluster
A) The population is divided into groups that are similar on some characteristic.
B) Random sampling is part of the sampling procedure.
C) Each individual unit in the population belongs to one and only one of the strata.
D) Every possible subset of the population, of the desired sample size, has an equal chance of being selected.
E) The strata are based on facts known before the sample is selected.
Answer: every possible subset of the population, of the desired sample size, has an equal chance of being selected
A) To determine the proportion of red snappers with a high mercury level in the Gulf of Mexico.
B) To determine the mean wage earned by construction workers in a small town.
C) To determine the mean selling price of houses in your neighborhood.
D) To determine the proportion of students with a learning disability in a small rural area high school.
E) To determine the difference between the proportion of engineering professors and the proportion of business professors in favor of the new teaching initiative at a large university.
Answer: to determine the proportion of red snappers with a high mercury level in the Gulf of Mexico
A) Each of the 320 people is assigned a number. Twenty numbers are randomly selected by a computer and the people corresponding to these 20 numbers are the sample
B) The sample will consist of the first 20 people who volunteer to be part of the sample.
C) The 320 names are put into an alphabetical list and the list numbered from 1 to 320. A number between 1 and 304 (inclusive) is selected at random. The person corresponding to that number and the next 19 people on the list are selected for the sample.
D) The 320 names are put into an alphabetical list. One of the first 16 names on the list is selected at random as part of the sample. Every 16th name on the list is then selected for the sample.
E) All 320 names are written on slips of paper and the slips are put into a box. Twenty slips are selected at random from the box.
Answer: the 320 names are put into an alphabetical list and the list numbered from 1 to 320. a number between 1 and 304 (inclusive) is selected at random. the person corresponding to that number and the next 19 people on the list are selected for the sample
A) It is a pattern of errors that tend to cancel one another out so that the overall result still accurately reflects the true value.
B) Bias error refers to sample takers who have a problem with bigotry.
C) Every sample design will generate a certain amount of random error.
D) The pattern of errors is loaded in one direction and therefore do not balance each other out, producing a true distortion.
Answer: the patterns of errors is loaded in one direction and therefore do not balance each other our, producing a true distortion
A) a matched pairs experiment.
B) a completely randomized experiment.
C) a block design, but not a matched pairs experiment.
D) an observational study.
E) impossible to classify unless more details of the study are provided.
Answer: a matched pairs experiment
A) that the remedy is effective for the treatment of headaches.
B) nothing, because there is no control group for comparison.
C) that the remedy is not effective for the treatment of headaches.
D) nothing, because the sample size is too small.
E) that the new treatment is better than aspirin.
Answer: nothing, because there is no control group for comparison
A) The placebo effect is a concern for all experiments.
B) Blocking eliminates the effects of all lurking variables.
C) Control is a key component in experimental design. Thus, a control group that receives a placebo is a requirement for experimentation.
D) Replication is a key component in experimental design. Thus an experiment needs to be conducted on repeated samples before generalizing results.
E) Randomization is a key component in experimental design. Randomization is used to reduce bias.
Answer: randomization is a key component in experimental design. randomization is used to reduce bias
A) Blinded block design observational study
B) Randomly assigned observational study
C) Block design with random assignment
D) Blind experiment with random assignment
E) Double-blind comparative experiment
Answer: double-blind comparative experiment
A) That the remedy is effective for the treatment of coughs.
B) Nothing, because there is no control group for comparison.
C) That the treatment is better than the old medicine.
D) Nothing, because the sample size is too small.
E) That the remedy is not effective for the treatment of coughs.
Answer: nothing, because there is no control group for comparison
A) No, because not every sample of the intended size has an equal chance of being selected.
B) Yes, because 24 out of every 25 students who are not selected will form a control group.
C) Yes, because this is an example of systematic sampling, which is a special case of simple random sampling.
D) Yes, because every student has the same chance of being selected.
E) Yes, but only if there is a single entrance to the school.
Answer: no, because not every sample of the intended size has an equal chance of being selected
A) Systematic sampling
B) Stratified random sampling
C) Convenience sampling
D) Simple random sampling
E) Cluster sampling
Answer: stratified random sampling
A) The contents of one section of the table are independent of other sections of the table.
B) Each digit 0 through 9 occurs with equal frequency.
C) Each three-digit number 000 through 999 occurs with equal frequency.
D) The table will contain, somewhere, the sequence 1234.
E) Consecutive rows do not start with the same digit.
Answer: consecutive rows do not start with the same digit
A) Simple random sampling
B) Two-stage sampling
C) Stratified random sampling
D) Convenience sampling
E) Cluster sampling
Answer: stratified random sampling
A) Cluster sample, because the population is divided into 5 clusters -- name 5 offices in 5 countries.
B) Stratified sample, because the population is divided into 5 strata -- namely 5 offices in 5 countries.
C) Simple random sample, because this is the simplest sampling method.
D) Simple random sample, because this is the only method for which inferential techniques are available.
E) Simple random sample, because this is the only method that gives unbiased results.
Answer: stratified sample, because the population is divided into 5 strata -- namely 5 offices in 5 countries
A) Divide the number of members by 40 to get a value k. Choose one of the first kth names on the list, using a random number generator. Then choose every kth name of the list after that name.
B) Get the sign-in lists for each day of the week, Monday through Friday. Randomly choose 8 names from each day for the survey.
C) Randomly pick a morning and survey the first 40 people who come in the door that day.
D) Put each member's name on a slip of paper and randomly select 40 slips.
E) Mail out surveys to every member and use the first 40 that are returned.
Answer: Put each member's name on a slip of paper and randomly select 40 slips
A) Randomly select 10 students from each of the four senior calculus classes.
B) Write the name of each student in the senior class on a slip of paper and put the papers in a container. Then randomly select 40 slips of paper from the container.
C) From a list of all seniors, select one of the first 10 names at random. Then select every nth name on the list until you have 40 people selected.
D) Assuming that students are randomly assigned to classes, select two classes at random and include those students in your sample.
E) Select the first 40 seniors to pass through the cafeteria door at lunch.
Answer: write the name of each student in the senior class and put the papers in a container. then randomly select 40 slips of paper from the container
A) randomization makes the analysis easier since the data can be collected and entered into the computer in any order.
B) randomization is a good way to create two groups of 20 intersections that are as similar as possible, so that comparisons can be made between the two groups.
C) randomization eliminates the impact of any confounding variables.
D) randomization reduces the impact of outliers.
E) randomization ensures that the study is double-blind.
Answer: randomization is a good way to create two groups of 20 intersections that are as similar as possible, so that comparisons can be made between the two groups
A) 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.
B) Slight changes in the wording of questions can make a measurable difference in survey results.
C) Non-sampling errors can distort the results of a census.
D) People will sometimes answer a question differently for different interviewers.
E) Nonresponse can cause bias in surveys because nonrespondents often tend to behave differently than people who respond.
Answer: A
A) A control group would allow the experimenter to determine which of the two exercise programs improves physical fitness the most.
B) A control group would eliminate the need for blinding in the study.
C) There would be no added benefit to having a control group.
D) A control group would eliminate the placebo effect.
E) A control group would allow the experimenter to determine if either of the exercise programs is more effective than current programs for physical fitness.
Answer: A control group would allow the experimenter to determine if either of the exercise of the programs is more effective than current programs for physical fitness
A) Participants should be kept blind as to which block they are in.
B) Participants should be randomly assigned to blocks.
C) Participants in the same block should receive the same lotion.
D) Participants within each block should be as similar as possible with respect to how easily they get sunburned.
E) Participants with each block should be as different as possible with respect to how easily they get sunburned.
Answer: participants within each block should be as similar as possible with respect to how easily they get sunburned
A) A complete census
B) A least squares regression line showing high correlation
C) A simple random sample
D) A well-designed, well-conducted survey
E) A controlled experiment
Answer: a controlled experiment
A) Yes, because it uses randomization and blocking.
B) No, because proportions of students passing would be more appropriate.
C) No, because so many more students take statistics at the university.
D) No, because the exam should have been given to all the students.
E) No, because there is a confounding variable: different kinds of schools
Answer: no, because there is a confounding variable: different kinds of schools
A) variability due to sampling
B) bias
C) nonsampling error
D) confounding
E) a sampling frame that is incomplete
Answer: variability due to sampling
A) Response bias and undercoverage
B) Response bias and nonresponse
C) Voluntary response bias and nonresponse
D) Nonresponse and undercoverage
E) Voluntary response bias and undercoverage
Answer: response bias and nonresponse
A) To determine what proportion of registered students enrolled in a college are employed more than 20 hours each week.
B) To determine what proportion of fish in Lake Michigan are bass.
C) To determine what proportion of single-family dwellings in a small town have two-car garages.
D) To determine what proportion of licensed bicycles on a university campus have lights.
E) To determine what proportion of students in a high school support wearing uniforms.
Answer: To determine what proportion of fish in Lake Michigan are bass
A) It's likely that the results are not accurate because people tend to lie in voluntary surveys.
B) It's likely that this result is higher than the true population proportion because
persons unhappy in their marriages are more likely to respond.
C) There is no way of predicting whether the results are biased or not.
D) It's likely that this result is lower than the true proportion because persons unhappy in their marriages are unlikely to respond.
E) It's likely that this result is an accurate reflection of the population
Answer: It's likely that this result is higher than the true population proportion because persons unhappy in their marriages are more likely to respond
a. survey five friends concerning their opinions of a local hockey team
b. from a list of all students in your school, randomly select 20 to answer a survey about internet use
c. identify four ethnic groups at your school. From each group, choose enough respondents so that the final sample contains roughly the same proportion of each group as the school population
d. take a random sample of five voting precincts in a large metropolitan area and do an exit poll at each voting site
e. measure the length of time each fifth person entering a restaurant has to wait to be seated
Answer: take a random sample of five voting precincts in a large metropolitan area and do an exit poll at each voting site
a. thousands of loan rates from all branches in the Midwest
b. loan rates from ten of your neighbors who bank at the local branch
c. a random sample of one thousand loan rates
d. all loan rates from all branches in one town and a random sample of loan rates from other areas of branches
e. less than one hundred loan rates from one brain in a town
Answer: a random sample of one thousand loan rates
a. insufficient attention to the placebo effect
b. response bias
c. no control group
d. lack of random selection
e. lack of random assignment
Answer: lack of random selection
a. use smaller sample sizes
b. when possible, avoid the use of human interviewers, relying on computerized dialing instead
c. use larger sample sizes
d. use no more than 3 or 4 words in any question
Answer: use larger sample sizes
a. randomization is a good way to create two groups of 20 families that are as similar as possible except for the treatments they receive
b. randomization makes the analysis easier since the data can be collected and entered into the computer in any order
c. randomization eliminates the impact of any confounding variables
d. randomization reduces the impact of outliers
e. randomization ensures that the study is double-blinded
Answer: randomization is a good way to create two groups of 20 families that are as similar as possible except for the treatments they receive
a.) Decrease
b.) Increase
c.) Stayed the same
d.) Disappeared
Answer: A
a.) can never be larger than the mean
b.) is always larger than the median
c.) is always larger than the mean
d.) None of these alternative is correct
Answer: D
a.) mode
b.) standard deviation
c.) range
d.) interquartile range
Answer: A
a.) is negative since all the numbers are negative
b.) must be at least zero
c.) cannot be computed since all the numbers are negative
d.) can be either negative or positive
Answer: B
a.) the median
b.) the mode
c.) the trimmed mean
d.) any of the above
Answer: C
a.) is the same as the coefficient of determination
b.) can be larger than 1
c.) cannot be larger than 1
d.) cannot be negative
Answer: C
a.) 0 and 1
b.) -1 and +1
c.) minus infinity and plus infinity
d.) 1 and 100
Answer: B
a.) variance
b.) coefficient of variation
c.) correlation coefficient
d.) standard deviation
Answer: C
a.) a positive variance of the x values
b.) a positive variance of the y values
c.) the standard deviation is positive
d.) positive relation between the independent and the dependent variables
Answer: D
a.) variance
b.) covariance
c.) standard deviation
d.) coefficient of variation
Answer: B
a.) the variance of the population
b.) the standard deviation of the sample
c.) the standard deviation of the population
d.) the variance of the sample
Answer: A
a.) the variance of the population
b.) the standard deviation of the sample
c.) the standard deviation of the population
d.) the variance of the sample
Answer: C
a.) always greater than zero
b.) always less than zero
c.) sometimes greater than and sometimes less than zero, depending on the data elements
d.) always equal to zero
Answer: D
a.) their standard deviations must also be equal
b.) their medians must also be equal
c.) their modes must also be equal
d.) None of these alternative is correct
Answer: D
a.) zero
b.) larger than the standard deviation
c.) negative
d.) smaller than the standard deviation
Answer: C
a.) is always smaller than the true value of the population variance
b.) is always larger than the true value of the population variance
c.) could be smaller, equal to, or larger than the true value of the population variance
d.) can never be zero
Answer: C
a.) larger than the variance
b.) zero
c.) negative
d.) smaller than the variance
Answer: C
a.) mean
b.) median
c.) mode
d.) variance
Answer: A
a.) range
b.) median
c.) mode
d.) mean
Answer: D
a.) the range
b.) the interquartile range
c.) the absolute value of the range
d.) the standard deviation
Answer: D
a.) as much as possible since computations are easier
b.) only when individual data values are unavailable
c.) whenever computer packages for descriptive statistics are unavailable
d.) only when the data are from a population
Answer: B
a.) the variance
b.) the standard deviation
c.) the range
d.) the interquartile range
Answer: C
a.) data values are treated as if they occur at the midpoint of a class
b.) the grouped data result is more accurate than the ungrouped result
c.) the grouped data computations are used only when a population is being analyzed
d.) None of these alternative is correct.
Answer: A
a.) the data set is a sample
b.) the data set is a population
c.) the data set could be either a sample or a population
d.) the data set is from a census
Answer: A
a.) the sum of the range variances is zero
b.) the range is difficult to compute
c.) the range is influenced too much by extreme values
d.) the range is negative
Answer: C
a.) the range
b.) the 50th percentile
c.) the standard deviation
d.) the interquartile range
Answer: B
a.) greater than the median
b.) smaller than the median
c.) equal to the median
d.) positive
Answer: A
a.) negative
b.) zero
c.) positive
d.) one
Answer: C
a.) squared
b.) divided by (n-1)
c.) rounded down
d.) rounded up
Answer: D
a.) the 50th percentile
b.) another name for the variance
c.) the difference between the largest and smallest values
d.) the difference between the third quartile and the first quartile
Answer: D
a.) range
b.) mode
c.) mean
d.) median
Answer: B
a.) percentiles
b.) quartiles
c.) interquartile range
d.) all of the above are measures of dispersion
Answer: C
a.) cannot be determined
b.) is the average value of the two middle items
c.) must be equal to the mean
d.) is the average value of the two middle items when all items are arranged in ascending order
Answer: D
a.) mean
b.) median
c.) variance
d.) mode
Answer: C
a.) contains at least one third of the data elements
b.) is the same as the 25th percentile
c.) is the same as the 50th percentile
d.) is the same as the 75th percentile
Answer: B
a.) variance
b.) interquartile range
c.) range
d.) coefficient of variation
Answer: C
a.) less than or equal to this value
b.) less than this value
c.) more than or equal to this value
d.) more than this value
Answer: A
a.) first quartile
b.) second quartile
c.) third quartile
d.) fourth quartile
Answer: C
a.) relative dispersion
b.) absolute dispersion
c.) central location
d.) relative location
Answer: C
a.) mode
b.) mean
c.) 50th percentile
d.) all of the above answers are correct
Answer: C
a.) 13
b.) 24
c.) 576
d.) 28,461
Answer: B
mean = 60
mode = 73
median = 74
range = 20
variance = 324
The coefficient of variation equals
a.) 0.30%
b.) 30%
c.) 5.4%
d.) 54%
Answer: B
a.) population parameter
b.) sample statistic
c.) population variance
d.) mode
Answer: A
a.) can never be larger than the population parameter
b.) can never be equal to the population parameter
c.) can be smaller, large, or equal to the population parameter
d.) can never be smaller than the population parameter
Answer: C
a.) sample slapstick
b.) sample sadistic
c.) sample statistic
d.) sample static
Answer: C
a.) standard deviation
b.) mean
c.) variance
d.) range
Answer: B
a.) statistics, parameters
b.) parameters, statistics
c.) statistics, statistics
d.) Parameters, parameters
Answer: A
