Ch11 Verified Test Bank More About Hypothesis Testing - Statistics 11th Edition Test Questions and Answer Key by Robert S. Witte. DOCX document preview.
MULTIPLE‑CHOICE TEST ITEMS
CHAPTER 11
MORE ABOUT HYPOTHESIS TESTING
11.1 Insofar as we must generalize from a sample to a population, the observed difference between the sample mean and the hypothesized population mean
a) can't be interpreted at face value.
b) might be due to variability or chance.
c) might be real.
d) is described by all of the above
11.2 Before generalizing beyond the existing data, we must always measure the effect of
a) variability.
b) the independent variable.
c) the investigator.
d) the generalization.
11.3 Having made a decision to either retain or reject the null hypothesis, we don't know definitely whether this decision is
a) common or rare.
b) probable or improbable.
c) correct or incorrect.
d) significant or insignificant.
11.4 It would be unwise to completely eliminate the rejection regions because then a
a) true hypothesis never would be rejected.
b) true hypothesis never would be retained.
c) false hypothesis never would be rejected.
d) false hypothesis never would be retained.
11.5 Traditional hypothesis tests tend to produce correct decisions if the null hypothesis is
a) true.
b) false.
c) either true or false.
d) either true or seriously false.
11.6 If the null hypothesis is seriously false, there is a high probability that this hypothesis will be
a) rejected.
b) retained.
c) revised.
d) retested.
11.7 Retention of the null hypothesis implies that the null hypothesis
a) is true.
b) is probably true.
c) could be true.
d) could be any of the above, depending on circumstances.
11.8 Rejection of the null hypothesis implies that the null hypothesis
a) is false.
b) probably is false.
c) could be false.
d) could be any of the above, depending on circumstances.
11.9 The decision to retain the null hypothesis is __________ the decision to reject the null hypothesis.
a) as strong as
b) stronger than
c) weaker than
d) unrelated to
11.10 The null hypothesis is tested directly because it
a) possesses the necessary precision.
b) contains a bias that might compromise the outcome.
c) reflects the investigator's primary concern.
d) reflects the investigator's hunch.
Ans; a
11.11 The research hypothesis is tested indirectly because it
a) lacks the necessary precision.
b) reflects the researcher's hunch.
c) can't withstand a direct analysis.
d) contains a bias that might compromise the outcome.
11.12 Strong support for the research hypothesis occurs whenever
the null hypothesis is
a) retained.
b) rejected.
c) tested with a very large sample size.
d) stated precisely.
11.13 (NOTE: This question requires Greek letters.) An investigator is concerned only about detecting the possibility that the mean IQ for a population of high school students is smaller than 100. Therefore, the alternative hypothesis should take the form
a) μ = 100
b) μ ≠ 100
c) μ > 100
d) μ < 100
11.14 The advantage of a one‑tailed test is that it increases the likelihood of detecting a
a) false null hypothesis.
b) false null hypothesis in the direction of concern.
c) true null hypothesis.
d) true null hypothesis in the direction of concern.
11.15 When used appropriately, a one‑tailed test is more
a) precise.
b) descriptive.
c) definitive.
d) sensitive.
11.16 An investigator should be prepared to justify a one‑tailed test on the basis of
a) the observed difference.
b) a strong hunch.
c) the null hypothesis.
d) logical considerations.
11.17 Having committed yourself to a one-tailed test, you must retain the null hypothesis regardless of how far the observed z deviates from the hypothesized population mean in
a) the direction of no concern.
b) the direction of concern.
c) either direction.
d) the negative direction.
11.18 Having committed yourself to a one-tailed test, the formal statement of the null hypothesis, H0, should be expanded to include values of the population mean
a) in either direction.
b) in the direction of no concern.
c) suggested by the observed sample mean.
d) more deviant that the critical z.
11.19 When the rejection of a true null hypothesis has horrendous consequences, use a level of significance equal to
a) .10
b) .05
c) .01
d) .001
11.20 In real-life applications, unless there are obvious reasons for selecting either a larger or smaller level of significance, select a level of significance equal to
a) .10
b) .05
c) .01
d) .001
11.21 The largest level of significance reported in most professional journals equals
a) .10
b) .05
c) .01
d) .001
11.22 (NOTE: This question requires Greek letters.) A standardized test of reading comprehension is designed to yield a value of 6.0 if sixth graders are progressing as expected. In hopes of accelerating their reading comprehension, a random sample of 36 sixth graders undergo an enriched reading program and attain a mean score of 6.4. The appropriate statistical hypotheses are:
a) H0: μ < 6.0
H1: μ > 6.0
b) H0: μ = 6.0
H1: μ ≠ 6.0
c) H0: μ < 6.4
H1: μ > 6.4
d) H0: μ = 6.4
H1: μ ≠ 6.4
11.23 It doesn't make sense to test a null hypothesis that the population mean equals the observed value of the sample mean because
a) the null hypothesis always would be rejected.
b) it would be impossible for the population mean to equal the observed value of the sample mean.
c) the population mean never equals a single value.
d) the z ratio always would equal zero.
11.24 The appropriate decision rule for a one-tailed test, lower tail critical, at the .05 level of significance, is to reject if
a) z ≤ 
b) z ≥
c) z ≤ 1.65
d) z ≥ 1.65
11.25 Prior to a hypothesis test, we must be concerned about ______________ possible outcomes.
a) two
b) three
c) four
d) five
11.26 If the null hypothesis is true, we hope to retain the hypothesis and conclude that it
a) is true.
b) probably is true.
c) most likely is true.
d) could be true.
11.27 If the null hypothesis is really false and we reject the hypothesis, we have made a
a) mistake.
b) correct decision.
c) type I error.
d) type II error.
11.28 Type I errors are sometimes called
a) misses.
b) wild goose chases.
c) false alarms.
d) all of the above
11.29 The null hypothesis
a) supports the researcher's hypothesis.
b) contradicts the researcher's hypothesis.
c) reflects the true state of affairs.
d) reflects the truth most of the time.
11.30 In an experiment to determine whether TV cartoons produce more aggressive behavior in grade school children, the null hypothesis states that TV cartoons have
a) an effect on aggressive behavior.
b) at least a slight effect on aggressive behavior.
c) no effect on aggressive behavior.
d) at most a weak effect on aggressive behavior.
11.31 If the null hypothesis is true, the hypothesized and true sampling distributions will
a) differ.
b) overlap.
c) coincide.
d) coexist.
11.32 The probability of a type I error equals the level of significance, given that the null hypothesis
a) could be true.
b) is true.
c) probably is true.
d) is either true or false.
11.33 The probability of a type I error equals
a) alpha.
b) one minus alpha.
c) beta.
d) one minus beta.
11.34 If the level of significance equals .05 and the null hypothesis is true, a correct decision will occur
a) with probability .95.
b) much of the time.
c) with probability .05.
d) all of the time.
11.35 If a type I error has particularly serious consequences, we can
a) increase the sample size.
b) increase the level of significance (from, for instance, .01 to .05).
c) decrease the sample size.
d) decrease the level of significance (for instance, from .05 to .01).
11.36 An effect refers to any difference between
a) true and hypothesized population means.
b) observed and hypothesized population means.
c) null and alternative hypothesized values.
d) any two means.
11.37 If the null hypothesis is false, the true sampling distribution
a) coincides with the hypothesized sampling distribution.
b) dictates the decision rule for the hypothesis test.
c) is centered about the hypothesized population mean.
d) supplies the one randomly selected sample mean (or z).
11.38 Type II errors are sometimes referred to as
a) false alarms.
b) wild goose chases.
c) misses.
d) all of the above
11.39 The probability of a type II error equals
a) alpha.
b) one minus alpha.
c) beta.
d) one minus beta.
11.40 If the null hypothesis is false, and the randomly selected z doesn't deviate beyond the critical z, the null hypothesis will be
a) correctly retained.
b) correctly rejected.
c) incorrectly retained.
d) incorrectly rejected.
11.41 If the null hypothesis is false because of a large effect, the probability of a correct decision
a) will be relatively large.
b) will be relatively small.
c) will equal one minus the level of significance.
d) will equal one minus the probability that the null hypothesis is false.
11.42 If it's important to detect even a relatively small effect, increase the
a) scope of the investigation.
b) sample size.
c) size of the effect.
d) retention region.
11.43 Reducing the size of the standard error produces a shrinkage in the
a) retention region.
b) true sampling distribution.
c) retention region or the true sampling distribution.
d) retention region and the true sampling distribution.
11.44 If sample size is excessively large, an effect usually will be
a) detected even though it has importance.
b) detected even though it lacks importance.
c) missed even though it has importance.
d) missed even though it lacks importance.
11.45 If sample size is unduly small, an effect usually will be
a) missed even though it has importance.
b) missed even though it lacks importance.
c) detected even though it has importance.
d) detected even though it lacks importance.
11.46 To locate the appropriate sample size for a projected experiment, the researcher must decide what constitutes a reasonable detection rate for the
a) smallest unimportant effect.
b) smallest important effect.
c) largest important effect.
d) largest unimportant effect.
11.47 Power refers to the probability of detecting
a) a true null hypothesis.
b) a particular effect.
c) very large effects.
d) all of the above
11.48 Power equals one minus
a) beta.
b) alpha.
c) mu.
d) sigma.
11.49 Power curves cross-classify the likelihood of detecting any possible effect with the
a) level of significance.
b) null hypothesis.
c) decision rule.
d) sample size.
11.50 Power curves help the investigator to identify a hypothesis test that has
a) the proper sensitivity.
b) exceptionally low type I and II error rates.
c) almost 100 percent accuracy.
d) the appropriate level of significance.
11.51 When consulting power curves, the default value for the level of significance is .05, while the default value for power is
a) .99
b) .95
c) .90
d) .80
11.52 When using power curves, the selection of a relatively low default value of .80 for power reflects the fact that
a) the type II error usually is less serious than a type I error.
b) higher degrees of power require large sample sizes.
c) power curves are difficult to interpret with very high degrees of power.
d) none of the above.
11.53 Sample size can be reduced by
a) enlarging the smallest important effect.
b) lowering the degree of power.
c) increasing the level of significance.
d) all of the above.
11.54 A failure to reject the null hypothesis might be due to
a) a high level of significance, such as .10.
b) low power.
c) a large sample size.
d) some combination of the above.
11.55 Metal detectors at airports are used to determine whether passengers are carrying weapons. If the null hypothesis states that a passenger isn't carrying a weapon, a type I error would occur whenever
a) a weapon‑free passenger passes the detector without activating the alarm.
b) a weapon‑free passenger passes the detector and activates the alarm.
c) a weapon‑carrying passenger passes the detector without activating the alarm.
d) a weapon‑carrying passenger passes the detector and activates the alarm.
11.56 Metal detectors at airports are used to determine whether passengers are carrying weapons. If the null hypothesis states that a passenger isn't carrying a weapon, a type II error would occur whenever
a) a weapon‑free passenger passes the detector without activating the alarm.
b) a weapon‑free passenger passes the detector and activates the alarm.
c) a weapon‑carrying passenger passes the detector without activating the alarm.
d) a weapon‑carrying passenger passes the detector and activates the alarm.
11.57 Using the .05 level of significance, a researcher retains the null hypothesis. Therefore the researcher can conclude that the null hypothesis
a) is true with probability .95.
b) is probably true.
c) could be true.
d) is false with probability .05.
11.58 Using the .001 level of significance, a researcher rejects the null hypothesis. Therefore the researcher can conclude that the null hypothesis
a) is false with probability .999.
b) is probably false.
c) could be false.
d) is true with probability .001.
11.59 The smallest overlap between true and hypothesized sampling distributions would occur when the effect is
a) very small.
b) moderately small.
c) moderately large.
d) very large.
11.60 A researcher uses a power curve to determine the required sample size, given that she wishes to detect a five‑point effect with probability .80. If, unknown to the researcher, the true effect really equals ten points, the true detection rate
a) is greater than .80.
b) equals .80.
c) is less than .80.
d) is unknown.
11.61 Using a sample of 600 subjects, an experimenter reports that the null hypothesis was rejected at the .05 level of significance. This finding suggests an effect that
a) might lack importance.
b) just barely triggers the decision to reject.
c) possesses considerable importance.
d) must be sizable.
Document Information
Connected Book
Statistics 11th Edition Test Questions and Answer Key
By Robert S. Witte