STATS FINAL PT. I

To determine a person's percentile, you first need to convert the person's raw score to a:

A) normalized score.
B) median.
C) z score.
D) formal score.

What proportion of a normal distribution corresponds to z scores greater
than 1.04?

A) 0.8508
B) 0.1492
C) 0.6492
D) 0.3508

If we know that the percentage of scores falling between the mean and a z score of 0.40 is 15.54, then what is the percentage of scores falling between the mean and a z score of –0.40?

A) –15.54
B) –34.46
C) 34.46
D) 15.54

If we know that the percentage of scores falling between the mean and a z score of 0.50 is 19.15, then what is the percentage of scores falling below a z score of –0.50?

A) –19.15
B) 30.85
C) –30.85
D) 19.15

What is the percentage of observations that fall between z scores of –1.2 and 0.50?

A) 57.64
B) 38.49
C) 19.15
D) 19.34

In one statistics course, students reported studying an average of 9.92 hours a week, with a standard deviation of 4.54. Treating this class as the population, what is the percentile for a student in the class who studies 8 hours a week?

A) 16.28
B) 33.72
C) –33.72
D) –16.28

What is the difference between the denominator of the equation for the z score and that of the z statistic?

A) There is no difference between the denominators of the two equations. In both cases, we divide by the standard error.
B) There is no difference between the denominators of the two equations. In both cases, we divide by the standard deviation.
C) When computing a z score, we divide by the population standard deviation, but when computing a z statistic, we divide by the standard error of the sampling distribution.
D) When computing a z statistic, we divide by the population standard deviation, but when computing a z score, we divide by the standard error of the sampling distribution.

Under what conditions is it permissible to proceed with a hypothesis test even though the assumption that participants are randomly selected is violated?

A) The data are not clearly nominal or ordinal.
B) The data are not clearly ratio.
C) We are cautious about generalizing the results.
D) We have a sample size greater than 30.

________ requires that all members of a population have an equal chance of being selected for a study.

A) Normal distribution
B) Random selection
C) Random assignment
D) Scale variable assumption

Because of the principle of ________, when sample sizes are at least 30, the distribution will most likely resemble a normal distribution.

A) robustness
B) central limit theorem
C) parametric statistics
D) nonparametric statistics

The null hypothesis states that:

A) there are no differences between the populations being studied.
B) the sample being studied is different from the population from which it was drawn.
C) a difference exists between the populations being studied.
D) nothing exists.

A New York Times article published on April 24, 2007, reported the research of Dr. Giorgio Vallortigara, a neuroscientist at the University of Trieste, Italy, and his two colleagues. The researchers asked whether a dog wags its tail in a preferred direction in response to positive stimuli and in another direction in response to negative stimuli. To answer their question, they recruited 30 dogs that were family pets. Filming each dog from above, they allowed it to view (through a slat in its cage) three positive stimuli separately, in order of descending positivity: its owner, an unfamiliar human, and a cat. All the dogs responded by wagging their tails to the right. But when the dogs were presented with an unfamiliar, aggressive dog, a negative stimulus, all dogs wagged their tails to the left.

(Study Description: Tail Wagging) Which of the following statements is the null hypothesis for this study?

A) A dog will wag its tail more to the left in response to positive stimuli and more to the right in response to negative stimuli.
B) A dog's tail wagging will be the same in response to positive stimuli as to negative stimuli.
C) A dog's tail will wag more to the right in response to positive stimuli and more to the left in response to negative stimuli.
D) A dog will wag its tail differently in response to positive stimuli and to negative stimuli.

The typical probability adopted by researchers to determine whether a result is extreme is:

A) .05.
B) .25.
C) .50.
D) .01.

Mehl (2007) published a study in the journal Science
reporting the results of an extensive study of 396 men and women comparing the
number of words uttered per day by each sex. If Mehl was testing the idea that
women talk more than men do, the null hypothesis for the study would be
________ and the research hypothesis would be ________ (in symbolic terms).

If a researcher is testing the idea that women talk more than men do, he/she could use a ______ test, whereas if a researcher is testing the statement “It is hypothesized that men and women will differ on the number of words uttered per day, ” he/she must use a _____ test:

A) one-tailed; two-tailed
B) z; d
C) null hypothesis; research hypothesis
D) two-taild; one-tailed

When hypothesis testing, a conservative approach is to use a ________ rather than a ________.

A) two-tailed test; one-tailed test
B) null hypothesis; research hypothesis
C) one-tailed test; two-tailed test
D) research hypothesis; null hypothesis

The critical value(s) associated with a p level of .05 for a one-tailed hypothesis test using the z statistic is (are):

A) –1.65 or 1.65.
B) 1.96.
C) –1.96 and 1.96.
D) 1.65.

The range of raw scores contained in an 80% confidence interval will be ________ the range of raw scores contained in a 95% confidence interval.

A) smaller than
B) larger than
C) the same size as
D) None of these answers is correct.

It is known that the population mean for the verbal section of the SAT is 500 with a standard deviation of 100. In 2006, a sample of 400 students whose family income was between $70,000 and $80,000 had an average verbal SAT score of 511. The point estimate of the mean for this group is ________ and the 80% confidence interval for this group is ________.

A) 500; (504.55, 517.45)
B) 500; (493.55, 506.45)
C) 511; (504.6, 517.4)
D) 511; (493.55, 506.45)

The statement “The findings based on a sample of 1000 participants were statistically significant, providing evidence for our hypothesis” would be strengthened by:

A) measuring effect sizes.
B) using convenience sampling.
C) sampling university students.
D) hypothesis testing.

Measures of effect size:

A) do not rely on sample means.
B) decrease as the difference between population means increases.
C) increase as sample size increases.
D) are unaffected by sample size.

Imagine that a study of memory and aging finds that younger participants correctly recall 55% of studied words, older participants correctly recall 42% of studied words, and the size of this effect is Cohen's d = 0.49. This effect size indicates that the memory performance of:

A) younger participants is significantly better than that of older participants.
B) younger participants is approximately half a standard deviation below that of older participants.
C) older participants is approximately 4 standard deviations below that of younger participants.
D) older participants is approximately half a standard deviation below that of younger participants.

To remove the adjustment for the influence of sample size, Cohen's d uses the ________ rather than the ________ as part of its formula.

A) standard deviation; standard error
B) standard error; standard deviation
C) raw scores; standard scores
D) variance; raw scores

If an effect is significant but the effect size for the difference between the two means is small (according to Cohen's conventions), about how much overlap will there be between the two distributions?

A) 50%
B) 85%
C) 15%
D) 99%

QUESTION WAS DELETED

An overlap between two distributions of approximately 39% is most likely to result in a(n) ________ effect size.

A) medium
B) small
C) unconventional
D) large

A prep value of 0.67 would indicate:

A) a high effect size.
B) a moderate effect size.
C) that an effect would replicate 67% of the time.
D) statistical significance.

The concepts of effect size and prep are preferred over statistical significance testing alone because they:

A) assess the relative importance of results.
B) are directly influenced by sample size.
C) directly measure Type I error.
D) directly measure Type II error.

Our ability to reject the null hypothesis given that the null hypothesis is false is:

A) a correct rejection.
B) statistical power.
C) a Type I error.
D) a Type II error.

We calculate a statistical power and find that it is .93. This means that if the null hypothesis is ________, we have a ________% chance of rejecting the null hypothesis.

A) false; 93
B) true; 93
C) true; 7
D) false; 7

When alpha increases, both ________ and ________ increase.

A) power; probability of a Type I error
B) power; probability of a Type II error
C) standard error; power
D) probability of a Type I error; probability of a Type II error

If you are correct about the expected direction of an effect, then using a one-tailed hypothesis test instead of a two-tailed hypothesis test:

A) makes power 0.
B) decreases power.
C) increases power.
D) makes power 1.0.

According to the textbook, a ________ has more statistical power; however, a ________ is more conservative.

A) one-tailed test; two-tailed test
B) one-tailed test; effect-size test
C) effect-size test; hypothesis test
D) two-tailed test; one-tailed test

Increasing sample size:

A) increases power.
B) increases the magnitude of the test statistic.
C) All of these answers are correct.
D) decreases standard error.

Why do we divide by N – 1 rather than by N when estimating a population standard deviation from the sample standard deviation?

A) Because the sample standard deviation is likely to be an imprecise estimate, we allow the error of the estimate (the standard deviation) to be larger by dividing the sum of squares by a smaller number.
B) We typically have to throw out at least one data point in any given study, so the N – 1 allows us to account for that.
C) The sample standard deviation is a superior estimate of the variability in the population than is the population standard deviation.
D) None of these statements accurately describes why we divide by N – 1 rather than by N.

The symbol representing a standard deviation calculated by using a sample to estimate the population standard deviation is:

A)  
B) sd.
C) Std. Dev.
D) s.

The t statistic indicates the:

A) distance of a sample mean from the population mean in terms of estimated standard error.
B) distance of two sample means from a single population mean.
C) number of standard deviations a sample is from the population mean.
D) number of standard deviations an individual score is from the sample mean.

Identify the correct formula for using the
sample standard deviation to estimate the population standard deviation.

A newspaper article reported that the typical American family spent an average of $81 for Halloween candy and costumes last year. A sample of N = 16 families this year reported spending a mean of M = $85, with s = $20. What statistical test would we use to determine whether these data indicate a significant change in holiday spending?

A) paired-samples t test
B) z test
C) effect size test
D) single-sample t test

Many companies that manufacture lightbulbs advertise their 60-watt bulbs as having an average life of 1000 hours. A cynical consumer bought 30 bulbs and burned them until they failed. He found that they burned for an average of M = 1233, with a standard deviation of s = 232.06. What statistical test would this consumer use to determine whether the average burn time of lightbulbs differs significantly from that advertised?

A) single-sample t test
B) dependent-samples t test
C) z test
D) standard deviation analysis

The difference between the denominator of the z test and that of the single sample t test is that in a:

A) t test we divide by the actual population standard error (sM), but in a z test we divide by the estimated standard error (M).
B) z test we divide by the actual population standard error (M), but in a t test we divide by the estimated standard error (sM).
C) z test we divide by the actual population standard error (sM), but in a t test we divide by the estimated standard error (M).
D) t test we divide by the actual population standard error (M), but in a z test we divide by the estimated standard error (sM).