微信客服：xiaoxionga100
微信客服：ITCS521
程序代写案例-PSYC1004
时间：2021-11-11
PSYC1004: Mind, Brain and Behaviour 2
Quantitative methods
Instructions: Pick the best answer
Lecture 1
1. The distribution of sample means is:
a. the collection of all random scores for all possible samples of a given size n
from a population
b. the collection of all sample means for all possible random samples of a given
size n from a population
c. the collection of all scores for a sample of random means of a given size n from
a population
d. None of the above.
Gravetter & Wallnau, section 7.2
2. A measure of variation of the distribution of sample means is:
a. the same as the standard deviation of the population
b. is called the standard error of the mean
c. is independent of the size of the sample
d. both b and c.
Gravetter & Wallnau, section 7.2
3. For the general population, mean IQ is 100 with a standard deviation of 15. A sample
of 100 people is selected at random from the population, with a sample mean of 102. This
sample mean comes from a distribution of sample means with the following properties:
a. a mean of 100 and a standard error of 1.5
b. a mean of 102 and a standard error of 1.5
c. a mean of 100 and a standard error of 15
d. a mean of 102 and a standard error of 15
Gravetter & Wallnau, section 7.2, 7.3
4. The Satisfaction with Life (SWL) questionnaire produces data that is typically highly
negatively skewed, with a long tail towards low scores on the scale. A psychologist takes
a random sample of 30 people from the general community and asks them to complete
the SWL questionnaire. The sample mean can be considered to come from a distribution
that is:
a. highly negatively skewed
b. positively skewed to counteract the negative skew
c. normally distributed
d. a sample size of 30 is not large enough to be sure what is the distribution.
Gravetter & Wallnau, section 7.2
5. A researcher wishes to infer a population mean from a sample of 25. She is not
confident about her estimate and wants to be more precise. What would you advise her?
a. her estimate must be accurate, given the sample size of 25
b. as every sample mean is different, she needs to take many samples to be very
precise
c. the central limit theorem assures her that the population mean is the same as her
sample mean
d. if she wants to improve her precision she should use a larger sample size.
Gravetter & Wallnau, section 7.2, 7.3
6. For a normal distribution:
a. 75% of observations are within one standard deviation of the mean
b. 68% of observations are within two standard deviations of the mean
c. 95% of observations are within one standard deviation of the mean
d. none of the above.
Gravetter & Wallnau, section 6.2
7. A person has an IQ with a z-score more than +2.
a. That person is an extreme case. There is a high probability of seeing a z-score
of that size.
b. That person is not considered an extreme case. There is a low probability of
seeing a z-score of that size.
c. That person is not considered an extreme case. There is a high probability of
seeing a z-score of that size.
d. That person is an extreme case. There is a low probability of seeing a z-score of
that size.
Gravetter & Wallnau, section 6.2
8. The normal distribution is:
a. extremely common for actual psychological measures
b. useful for statistical inference because of the Central Limit theorem
c. not at all common in actual psychological measures
d. is common in actual psychology but only when it is skewed.
Gravetter & Wallnau, section 7.1
9. As the sample size gets larger:
a. There is more variability in the population.
b. The standard error increases by a factor related to the sample size.
c. The standard error decreases.
d. The precision of estimation decreases.
Gravetter & Wallnau, section 7.4
10. To estimate a population mean
a. use a sample mean but only if the population distribution is normal.
b. use a sample standard deviation to increase the precision.
c. calculate a standard error and then increase the sample size.
d. use a sample mean, preferably with a sample of reasonable size.
Gravetter & Wallnau, section 7.2
Lecture 2
1. Which option makes the most sense?
a. A sample is a set of individuals selected (usually randomly) from the
population. A population is every possible individual of relevance to the research
question. μ is notation for the mean of the sample (a sample statistic) while M is
for the mean of the population (a population parameter).
b. A sample is a set of individuals selected (usually randomly) from the
population. A population is every possible individual of relevance to the research
question. M is notation for the mean of the sample (a sample parameter) while μ
is for the mean of the population (a population statistic).
c. A population is a set of individuals selected (usually randomly) from the
sample. A sample is every possible individual of relevance to the research
question. M is notation for the mean of the sample (a sample statistic) while μ is
for the mean of the population (a population parameter).
d. A sample is a set of individuals selected (usually randomly) from the
population. A population is every possible individual of relevance to the research
question. M is notation for the mean of the sample (a sample statistic) while μ is
for the mean of the population (a population parameter).
Gravetter & Wallnau, section 1.2
2. A sample of 25 university students is chosen from the general population and IQ is
measured. Mean IQ for the sample is 103. For the general population, mean IQ is 100
with a standard deviation of 15.
a. Because the mean of the sample is higher than the population mean, we can
infer that the mean IQ of university students is significantly higher than that of the
general population.
b. Because the mean IQ of the sample is 0.2 standard deviations above the mean
IQ of the population, we can infer that the mean IQ of university students is
significantly higher than that of the general population.
c. Because the mean IQ of the sample is 0.2 standard deviations above the mean
IQ of the population, we can infer that the mean IQ of university students is NOT
significantly higher than that of the general population.
d. Because the mean IQ of the sample is 1 standard error above the population
mean, we can infer that the mean IQ of university students is NOT significantly
higher than that of the general population.
Gravetter & Wallnau, section 8.3
3. The null hypothesis is:
a. what the researcher believes is true about the data.
b. the hypothesis that says there is no effect to observe.
c. what the researcher believes is true about the population.
d. the hypothesis that says there is likely to be an effect.
Gravetter & Wallnau, section 8.1
4. The alpha-level is:
a. the probability used to define very unlikely samples if the null hypothesis is
true.
b. the probability used to define very unlikely samples if the null hypothesis is
false.
c. the probability used to define likely samples if the null hypothesis is true.
d. the probability used to define likely samples if the null hypothesis is false.
Gravetter & Wallnau, section 8.1
5. In using a z-score of approximately 2 (to be more precise, 1.96) in a single sample z-
test, we are saying that:
a. the alpha level is 5% and we reject the null hypothesis if the probability is
greater than this.
b. the alpha level is 2.5% and we reject the null hypothesis if the probability is
less than this.
c. the alpha level is 5% and we reject the null hypothesis if the probability is less
than this.
d. the alpha level is 2.5% and we reject the null hypothesis if the probability is
greater than this.
Gravetter & Wallnau, section 8.1
6. A researcher is interested in the effects of a drug on physical activity levels. The
researcher has designed a scale for activity levels that in the general population has a
mean of 18 and a standard deviation of 4. On the scale a higher score indicates higher
activity. A random sample of 16 people is given the drug. The mean activity levels of the
sample in the week after the administration of the drug is 15. The null hypothesis is:
a. μ0=18
b. μ0=15
c. μ0=18/√4 = 9
d. μ0= 4/√4 = 1
Gravetter & Wallnau, section 8.3
7. In regard to the research of question 6, assuming an alpha level of 5%, the z-score for
the sample is:
a. 9
b.– 3
c. 1
d. – 3/4
Gravetter & Wallnau, section 8.3
8. In regard to the research of question 6, assuming an alpha level of 5%, the correct
inference is:
a. Reject the null hypothesis. There is evidence from this study that the drug
decreases activity.
b. Do not reject the null hypothesis. There is no evidence from this study that the
drug decreases activity.
c. Reject the null hypothesis. There is evidence from this study that the drug
increases activity.
d. Do not reject the null hypothesis. There is evidence from this study that the
drug decreases activity.
Gravetter & Wallnau, section 8.3
9. What makes the most sense?
a. If there is a high probability, reject the null hypothesis. There is evidence for an
effect.
b. If there is a low probability, reject the null hypothesis. There is evidence for an
effect.
c. If there is a high probability, reject the null hypothesis. There is no evidence for
an effect.
d. If there is a low probability, reject the null hypothesis. There is no evidence for
an effect.
Gravetter & Wallnau, section 8.3
10. A single sample z-test:
a. involves calculating a z-score for the population mean, assuming that the
standard deviation is obtained from the sample. It compares the sample mean with
the population mean.
b. involves calculating a z-score for the sample mean, assuming that the standard
deviation is estimated from the sample. It compares the sample mean with a given
number.
c. involves calculating a z-score for the sample mean. This requires that the
standard deviation of the population be known. It compares the sample mean with
the population mean.
d. involves calculating a z-score for the sample mean. This requires that the
standard deviation of the population be known. It compares the sample mean with
a given number.
Gravetter & Wallnau, section 8.3
Lecture 3
1. What is the difference between a single sample z-test and a single sample t-test?
a. The z-test uses the mean and the t-test uses the standard deviation.
b. The z-test requires knowledge about the population mean, and the t-test does
not.
c. The z-test depends on the size of the sample but the t-test does not.
d. The z-test requires knowledge about the population standard deviation and the
t-test does not.
Gravetter & Wallnau, section 9.1
2. A random sample of 25 university students has a mean IQ of 104 and a standard
deviation of 10. For the general population, mean IQ is 100. A single sample t-test is
conducted to seek evidence whether the mean IQ of students in general is higher than the
general population.
a. The estimated standard error of the mean is 2 and the degrees of freedom are 25.
b. The estimated standard error of the mean is 2 and the degrees of freedom are 24.
c. The estimated standard error of the mean is 3 and the degrees of freedom are 25.
d. The estimated standard error of the mean is 3 and the degrees of freedom are 24.
Gravetter & Wallnau, section 9.1
3. In a single sample t-test the calculated t-statistic for a sample of 4 people is 2.8. A
researcher wishes to decide where this value is significant at a 10% alpha level, using
both tails (i.e. top and bottom) of the t-distribution.
a. df = 3. The t-value is not significant because it is less than 3.182.
b. df = 4. The t-value is significant because it is greater than 2.776.
c. df = 4. The t-value is significant because it is greater than 2.132.
d. df = 3. The t-value is significant because it is greater than 2.353.
Gravetter & Wallnau, section 9.1 (Table 9.1)
4. A sample of 10 children with specific brain injury has a mean IQ of 94.2 and a
standard deviation of 6.2. The null hypothesis is that the population of children with this
brain injury has a mean IQ of 100.
a. The calculated t-value is approximately – 1.9. This is not extreme because it is
less than 2.262, so do not reject the null hypothesis.
b. The calculated t-value is approximately – 2.98. This is extreme because it is
more than 2.262, so reject the null hypothesis.
c. The calculated t-value is approximately – 1.9. This is extreme because it is less
than 2.262, so reject the null hypothesis.
d. The calculated t-value is approximately – 2.98. This is not extreme because it is
more than 2.262, so reject the null hypothesis.
Gravetter & Wallnau, section 9.1 – see also lecture overheads
5. A psychologist has prepared an “Optimism test” that is administered yearly to
graduating students. The test measures how students feel about their futures – the higher
the score, the more optimistic. Last year’s class had a mean score of 15. A sample of 9
students is selected from this year’s class. The sample mean is 10 and the estimated
standard error is 1.14. The psychologist wishes to determine whether there has been a
significant fall in the mean level of optimism compared to last year.
a. The null hypothesis is that mean optimism this year is 10, and the degrees of
freedom are 9.
b. The null hypothesis is that mean optimism this year is 15, and the degrees of
freedom are 9.
c. The null hypothesis is that mean optimism this year is 10, and the degrees of
freedom are 8.
d. The null hypothesis is that mean optimism this year is 15, and the degrees of
freedom are 8.
Gravetter & Wallnau, Chapter 9
6. For the sample in question 5, the t-statistic is
a. 4.39
b.– 4.39
c. 8.77
d. – 8.77
Gravetter & Wallnau, Chapter 9
7. For a sample of 9, based on the t-distribution table, with an alpha of 0.05 (two tails),
the critical value is:
a. 2.262
b. .– 2.262
c. 2.306
d. .– 2.306
Gravetter & Wallnau, Chapter 9
8. For the sample in question 5, at a 5% alpha level the correct inference is:
a. reject the null hypothesis, there is no evidence for a significant difference in
optimism compared to the previous year.
b. do not reject the null hypothesis, there is no evidence for a significant
difference in optimism compared to the previous year.
c. reject the null hypothesis, there is evidence for a significant difference in
optimism compared to the previous year.
d. do not reject the null hypothesis, there is evidence for a significant difference in
optimism compared to the previous year.
Gravetter & Wallnau, Chapter 9
9. The correct way to report the statistics from this result is:
a. t(2.306)=9, p<.05
b. t(9)=2.306, p>.05
c. t(8)= .– 4.39, p<.05
d. t(9)=.05, p<.05
See lecture slides.
10. The z-test cannot be used when:
a. you do not know the population standard deviation
b. when you want to compare the means of two different samples
c. when you want to compare change in a sample across time
d. all of the above
See lecture slides.
Laboratory class 1
1. An IQ scale can be considered:
a. a nominal scale of measurement
b. a numerical scale which has a real zero
c. a discrete measurement scale
d. a continuous scale.
Gravetter & Wallnau, section 1.4
2. Which answer makes the most sense:
a. One of our goals in empirical psychology is to infer information about a
population using a sample. We use sample statistics to estimate population
parameters.
b. One of our goals in empirical psychology is to infer information about a sample
using a population. We use sample statistics as estimates of population parameters.
c. One of our goals in empirical psychology is to infer information about a
population using a sample. We use population statistics as estimates from sample
parameters.
d. One of our goals in empirical psychology is to infer information about
populations and samples. We use population statistics as estimates from sample
parameters.
Gravetter & Wallnau, section 1.2
3. Arrival time in class is approximately normally distributed. For a given lecture, the
mean arrival time is 2 minutes after the advertised start time of the lecture with a standard
deviation of 5 minutes. We expect that:
a. about 5% of students will arrive 8 minutes before the advertised time
b. about 5% of students will arrive 10 minutes before the advertised time
c. about 2.5% of students will arrive 12 minutes after the advertised time
d. about 2.5% of students will arrive 8 minutes after the advertised time
Gravetter & Wallnau, sections 6.2-6.3
4. A wonderful Olympic swimmer wins three gold medals. In the first final, the swimmer
completed in 67 seconds while the mean finishing time was 70 seconds (SD=2 seconds);
in the second final, the swimmer completed in 2minutes, 14 seconds while the mean time
was 2.5 minutes (SD= 10 seconds); in the third final the swimmer completed in 20
minutes while the mean was 23 minutes (SD=45 seconds). Comparing all three finals,
how well did the swimmer perform relative to all other finalists?
a. The swimmer did best in the first final, followed by the second and then the
third.
b. It is impossible to make a comparison
c. The swimmer did best in the third final, and beat the field by slightly more in
the second final than the first.
d. The swimmer did best in the second final, followed by the first and then the
third.
Gravetter & Wallnau, sections 5.2
5. A clinical psychologist devises a new psychological scale that measures foolishness. A
high score on the scale indicates a foolish person. The scale is positively skewed with a
long tail towards the higher scores. The minimum score on the scale is 10, the mean is 20
and the standard deviation is 10.
a. Because of the long tail, there are many people who are foolish and few people
get moderate or low scores.
b. Unusual cases are quite rare, so that we expect 95% of people to have a score
between 0 and 40.
c. Because the standard deviation is one-half of the mean (i.e. around 1.96), the
distribution is normally distributed.
d. There are few people who are foolish and it is not unusual to get moderate or
low scores.
Gravetter & Wallnau, sections 2.4
6. The following are measures of variation in a distribution:
a. Variance, standard deviation, mean, range.
b. Standard deviation, range, mean.
c. Variance, standard deviation, range.
d. Standard deviation, skew, normal, symmetric.
Gravetter & Wallnau, Chapter 4.1-4.3
7. IQ is normally distributed with a mean of 100 and a standard deviation of 15. George
has an IQ of 85. His z-score is:
a. 1.0
b. – 1.0
c. 0.15
d. – 0.85
Gravetter & Wallnau, Chapter 5
8. Neuroticism and extraversion are said to be two important personality dimensions. A
researcher collects data on a small sample of 6 males and 6 females and measures these
two dimensions, labeled as N and E, respectively. Here is some PASW output from the
Explore command:
a. The mean neuroticism score for males in this sample is 33.0, and for females is
33.2.
b. The extraversion scores for males are more widely spread out than for females.
c. Extraversion scores for males are more tightly grouped around the mean than
for females.
d. Neuroticism is highly skewed.
Computer lab class
Descriptives
33.0000 1.12546
30.1069
35.8931
32.9444
32.5000
7.600
2.75681
30.00
37.00
7.00
4.75
.430 .845
-1.572 1.741
33.1667 4.49753
21.6054
44.7279
33.0185
32.5000
121.367
11.01665
20.00
49.00
29.00
21.50
.297 .845
-1.038 1.741
Mean
Lower Bound
Upper Bound
95% Confidence
Interval for Mean
5% Trimmed Mean
Median
Variance
Std. Deviation
Minimum
Maximum
Range
Interquartile Range
Skewness
Kurtosis
Mean
Lower Bound
Upper Bound
95% Confidence
Interval for Mean
5% Trimmed Mean
Median
Variance
Std. Deviation
Minimum
Maximum
Range
Interquartile Range
Skewness
Kurtosis
sex
male
female
E
Statistic Std. Error
9. For the data of question 8, here are the boxplots for extraversion:
a. On average in this sample, females have higher extraversion than males.
b. On average in this sample, males have higher extraversion than females.
c. Female extraversion in this sample has a larger range.
d. There is a significant difference between males and females.
Computer lab class
10. For the data of question 9, here are the boxplots for neuroticism:
a. On average in this sample, females have higher neuroticism scores than
males.
b. On average in this sample, males have higher neuroticism scores than
females.
c. There are more outliers in the male sample.
d. The middle 50% of the data indicates that the similarity between males
and females for this sample is significant.
Computer lab class
femalemale
sex
45.00
40.00
35.00
30.00
25.00
20.00
15.00
10.00
N
Laboratory class 2
1. A repeated measures research design:
a. involves measuring the same construct across two different samples at two time
points
b. involves measuring the same construct across the same sample at two different
time points
c. is analysed using a t-test because it involves comparing a single sample
repeatedly with the population mean (e.g. 100 for IQ)
d. is analysed using a t-test because the null hypothesis is that there is no
difference between the two independent groups across time.
Gravetter & Wallnau, section 11.1, 11.2
2. An independent groups research design
a. involves measuring the same construct across two different samples
b. involves measuring the same construct at two different time points across an
independent sample
c. is analysed using a t-test because it involves comparing the means of two
groups with a given number (.e.g. 100 for IQ)
d. is analysed using a t-test because the null hypothesis is that there is a difference
between the two groups.
Gravetter & Wallnau, section 10.1, 10.2
3. Which answer makes the most sense?
a. Data for an independent groups t-test involves two variables, both continuous
and measured at separate time points. The null hypothesis is that there is no
difference in means across time.
b. Data for an independent groups t-test involves three variables, one continuous
and the other two to indicate which group the participant is in. The null
hypothesis is that there is no difference in means between the two groups.
c. Data for an independent groups t-test involves two variables, one continuous
and the other to indicate which group the participant is in. The null hypothesis is
that there is a difference in means between the two groups.
d. Data for an independent groups t-test involves two variables, one continuous
and the other a grouping variable. The null hypothesis is that there is no
difference in means between the two groups.
Gravetter & Wallnau, chapter 10.
4. A researcher collects data on a sample of 10 children with specific brain injury. The
researcher has a treatment that is intended to increase IQ for these children. Before
treatment, the mean IQ for the sample is 97 with a standard deviation of 5. The mean IQ
for the sample after treatment is 102, also with a standard deviation of 5.
a. The researcher can use a single sample t-test to infer whether prior to treatment
the brain injury has affected IQ relative to the general population, and a repeated
measures t-test to infer whether the treatment improves IQ.
b. The researcher can use an independent groups t-test to infer whether prior to
treatment the brain injury affects IQ relative to the general population, and a
repeated measures t-test to infer whether the treatment improves IQ.
c. The researcher can use a single sample t-test to infer whether prior to treatment
the brain injury affects IQ relative to the general population, and an independent
groups t-test to infer whether the treatment improves IQ.
d. The researcher can use a repeated measures t-test to infer whether prior to
treatment the brain injury affects IQ relative to the general population, and a
single sample t-test to infer whether the treatment improves IQ.
Gravetter & Wallnau, sections 9.2, 10.2, 11.2
5. A psychologist has prepared an “Optimism test” that is administered yearly to
graduating students. The test measures how students feel about their futures – the higher
the score, the more optimistic. At the beginning of their final year, an initial sample of 9
Arts students had a mean score of 15. The researcher was only able to measure a sample
of 9 Commerce students at the end of the year. They had a sample mean of 10.
a. Two single sample t-tests will reveal whether the means differ from 15.
b. A repeated measures t-test is needed to infer whether there is a decline from the
beginning of the year to the end of the year.
c. Because the data is across time and across groups, either a repeated measures or
an independent groups t-test would determine whether there is a difference.
d. An independent groups t-test is needed to infer whether there is a difference
between Arts and Commerce students, leaving to one side the question of the time
of measurement.
Gravetter & Wallnau, Chapter 10.2, 11.2
6. We have a small sample of 10 school children who have experienced a particular type
of head injury. We suppose that the head injury might affect their IQ levels. We wish to
see whether there is enough evidence in the sample to support this conclusion. Most IQ
tests are standardized to have a mean of 100 and a standard deviation of 15, and have a
normal distribution in the general population. We want to know whether the population
of children with this head injury has a mean that is less 100. Here is the PASW output.
a. There is evidence that mean IQ for children with this type of brain injury is
significantly lower than that of the general population (t(9)=0.016, p<.05).
b. There is evidence that mean IQ for children with this type of brain injury is
significantly lower than that of the general population (t(9)=-3.0, p=0.02).
c. There is no evidence that mean IQ for children with this type of brain injury is
lower than that of the general population (t(9)=-3.0, p>.05).
d. There is evidence that mean IQ for children with this type of brain injury is
significantly lower than that of the general population (t(9)=-5.8, p=0.02).
Gravetter & Wallnau, Chapter 9; Computer lab class
7. A student analyses the data from the study described in question 6 to produce the
following output. What is wrong with this analysis?
One-Sample Test
48.352 9 .000 94.20000 89.7928 98.6072IQ
t df Sig. (2-tailed)
Mean
Difference Lower Upper
95% Confidence
Interval of the
Difference
Test Value = 0
a. The null hypothesis is wrong. The null hypothesis population mean should not
be 0.
b. The t-value is too large for the degrees of freedom, so the probability cannot be
assessed.
c. The null hypothesis is not rejected.
d. The mean difference is equal to the mean of the sample.
Gravetter & Wallnau, Chapter 9; Computer lab class
One-Sample Test
-2.977 9 .016 -5.80000 -10.2072 -1.3928IQ
t df Sig. (2-tailed)
Mean
Difference Lower Upper
95% Confidence
Interval of the
Difference
Test Value = 100
8. As a brilliant and innovative cognitive neuropsychologist, you design a world leading
intervention to increase IQ for children with this type of head injury. The intervention
takes to the form of an extended one-on-one training course. You have a small sample of
children. You measure their IQ before and after your intervention
Here is the PASW output from your analysis:
a. Because the probability of 0.024 is small, do not reject the null hypothesis. The
mean difference of 3.1 indicates a significant improvement in IQ due to the
training.
b. Because the t-value of 2.72 is large, do not reject the null hypothesis. The mean
difference of 3.1 indicates a significant improvement in IQ due to the training.
c. Because the probability of 0.024 is small, reject the null hypothesis. The mean
difference of 3.1 indicates a significant improvement in IQ due to the training.
d. Because the t-value of 0.024 is small, reject the null hypothesis. The mean
difference of 3.1 indicates a significant improvement in IQ due to the training.
Gravetter & Wallnau, Chapter 11; Computer lab class
Paired Samples Test
3.1000 .5218 5.6782 2.720 9 .024IQAFTER - IQBEFOPair 1
Mean Lower Upper
95% Confidence
Interval of the
Difference
Paired Differences
t df Sig. (2-tailed)
9. You also investigate your intervention using a control group design. In the treatment
condition, you provide one-on-one training to a sample of 5 children with head injury. In
the control condition, you provide a one-on-one play condition (i.e. no training) to a
different sample of 5 children with head injury.
Here is your PASW output:
a. Because the probability of 0.014 is small, do not reject the null hypothesis. The
mean difference of 3.1 indicates a significant improvement in IQ due to the
training.
b. Because the t-value of 3.1 is large, do not reject the null hypothesis. There is a
significant difference in IQ between the two groups.
c. Because the probability of 0.014 is less than the alpha level, reject the null
hypothesis. There is a significant difference in IQ between the two groups.
d. Because the t-value of 0.94 is large, do not reject the null hypothesis. There is
no significant difference in IQ between the two groups.
Gravetter & Wallnau, Chapter 10; Computer lab class
10. Pick the best option.
a. If a sample mean is expected (i.e. not extreme) assuming a null hypothesis, then
there is evidence that the null hypothesis may not hold. After setting an α-level
(usually 0.05), if the probability of the sample mean is less than α, reject the null
hypothesis.
b. If a sample mean is extreme assuming a null hypothesis, then there is evidence that
the null hypothesis may not hold. After setting an α-level (usually 0.05), if the
probability of the sample mean is more than α, reject the null hypothesis.
c. If a sample mean is extreme assuming a null hypothesis, then there is evidence that
the null hypothesis may not hold. After setting an α-level (usually 0.05), if the
probability of the sample mean is less than α, reject the null hypothesis.
d. If a sample mean is extreme assuming a null hypothesis, then there is no evidence
that the null hypothesis may not hold. After setting an α-level (usually 0.05), if the
probability of the sample mean is less than α, do not reject the null hypothesis.
Gravetter & Wallnau, Chapter 8
Independent Samples Test
.007 .936 3.143 8 .014
3.143 8.000 .014
Equal variances
assumed
Equal variances
not assumed
IQ
F Sig.
Levene's Test for
Equality of Variances
t df Sig. (2-tailed)
t-test for Equality of Means
Laboratory class 3
1. Which answer makes the most sense?
a. In a positive correlation, two variables tend to move in the same direction, so
that an increase in one variable is associated with a decrease in the other.
b. In a negative correlation, two variables tend to move in the same direction, so
that an increase in one variable is associated with a decrease in the other.
c. In a positive correlation, two variables tend to move in the same direction, so
that an increase in one variable is associated with an increase in the other.
d. In a negative correlation, two variables tend to move in the opposite direction,
so that an increase in one variable is associated with an increase in the other.
Gravetter & Wallnau, section 16.1
2. For a large sample, the following is the PASW output for a scatterplot of the
personality dimension of extraversion versus neuroticism:
a. There seems to be a strong positive correlation between the two personality
dimensions.
b. It is impossible to say from the scatterplot whether there is a correlation
between the two personality dimensions.
c. A negative correlation between the two dimensions is suggested by the darker
areas of the scatterplot being in the lower regions of the neuroticism scroes.
d. Although the correlation is not a straight line, there is some evidence for a
curvilinear relationship.
Gravetter & Wallnau, section 16.1
3. For a small sample, the following is the PASW output for a scatterplot of negative
affect versus scores on the Kessler-10 scale. Negative affect is a psychological construct
relating to negative feelings and emotions. The Kessler-10 is a pre-diagnostic instrument
that may indicate issues of psychological wellbeing. For the two variables, higher scores
suggest more negative feelings and lower wellbeing, respectively.
a. The scatterplot suggests a positive correlation. As negative affect decreases,
scores on the Kessler-10 tend to decrease.
b. The scatterplot suggests a negative correlation. As negative affect increases,
scores on the Kessler-10 tend to decrease.
c. The scatterplot suggests a positive correlation. As negative affect increases,
scores on the Kessler-10 tend to decrease.
d. The scatterplot suggests a negative correlation. As negative affect decreases,
scores on the Kessler-10 tend to decrease.
Gravetter & Wallnau, chapter 16.1
4. A researcher finds a negative correlation between optimism and hours watching
television. Which is the best inference?
a. As television watching increases, people tend to become more optimistic.
b. Too much television watching causes more pessimism.
c. In order to cope with increased pessimism, people watch more television rather
than undertake more physical activity.
d. As optimism increases, people tend to spend less time watching television.
Gravetter & Wallnau, section 16.1, 16.3
5. A researcher finds a correlation of – 0.9 between two variables.
a. The negative sign indicates that the relationship between the two variables is
not close to a straight line.
b. Because 0.9 is less than 1, the relationship between the two variables is not
close to a straight line
c. Because – 0.9 is substantially less than 1, the relationship between the two
variables is not close to a straight line.
d. Because 0.9 is close to 1, the relationship between the two variables is close to
a straight line.
Gravetter & Wallnau, section 16.1
6. The following is PASW output for a correlational analysis of the variables for the
personality dimensions of extraversion and agreeableness.
a. The correlation of 0.15 is less than the critical value 0.24, so the correlation is
not significant. There is no evidence of a correlation in the population.
b. The probability of a correlation of 0.15 is 0.24 which is not small, so do not
reject the null hypothesis. There is no evidence of a correlation in the population.
c. The correlation of 0.24 is not large and has a probability of 0.15, so reject the
null hypothesis. There is evidence of a correlation in the population.
d. The correlation of 0.15 is not large and has a probability of 0.24 and degrees of
freedom 63. The correlation is not significant. There is no evidence of a
correlation in the population.
Gravetter & Wallnau, section 16.4; Computer lab class
Correlations
1 .150
.240
63 63
.150 1
.240
63 63
Pearson Correlation
Sig. (2-tailed)
N
Pearson Correlation
Sig. (2-tailed)
N
extraversion
agreeableness
extraversion
agreeabl
eness
7. From the study described in question 6, we may infer the following about the
population:
a. There is a positive correlation that is close to a straight line.
b. There is a negative correlation that is close to a straight line.
c. There is a weak positive correlation.
d. We have no evidence for a correlation
Gravetter & Wallnau, section 16.4
8. When making inferences about correlations from samples to populations:
a. the null hypothesis is that the population correlation is zero.
b. the null hypothesis is that the sample correlation is zero.
c. the null hypothesis is that the population mean correlation is zero.
d. the null hypothesis is that the population correlation is one.
Gravetter & Wallnau, section 16.4
9. We expect the following:
a. the correlation between monthly salary and yearly salary will be 1. But if so a
scatterplot is necessary to see whether the relationship is a straight line.
b. the correlation between monthly salary and yearly salary will be 1/12. A
scatterplot is necessary to see whether the relationship is a straight line.
c. the correlation between monthly salary and yearly salary will be 1. If so the
relationship is a straight line.
d. the correlation between monthly salary and yearly salary will be less than 1.
But, even so, the relationship is a straight line.
Gravetter & Wallnau, section 16.3
10. Which makes the most sense?
a. The Pearson correlation for the sample is represented by r and for the
population by ρ (the Greek letter rho).
b. The Spearman correlation for the sample is represented by r and for the
population by ρ (the Greek letter rho).
c. The Pearson correlation for the sample is represented by ρ (the Greek letter rho)
and for the population by r.
d. The sample statistic is ρ (the Greek letter rho) and the population parameter r.
Gravetter & Wallnau, section 16.4
学霸联盟
Quantitative methods
Instructions: Pick the best answer
Lecture 1
1. The distribution of sample means is:
a. the collection of all random scores for all possible samples of a given size n
from a population
b. the collection of all sample means for all possible random samples of a given
size n from a population
c. the collection of all scores for a sample of random means of a given size n from
a population
d. None of the above.
Gravetter & Wallnau, section 7.2
2. A measure of variation of the distribution of sample means is:
a. the same as the standard deviation of the population
b. is called the standard error of the mean
c. is independent of the size of the sample
d. both b and c.
Gravetter & Wallnau, section 7.2
3. For the general population, mean IQ is 100 with a standard deviation of 15. A sample
of 100 people is selected at random from the population, with a sample mean of 102. This
sample mean comes from a distribution of sample means with the following properties:
a. a mean of 100 and a standard error of 1.5
b. a mean of 102 and a standard error of 1.5
c. a mean of 100 and a standard error of 15
d. a mean of 102 and a standard error of 15
Gravetter & Wallnau, section 7.2, 7.3
4. The Satisfaction with Life (SWL) questionnaire produces data that is typically highly
negatively skewed, with a long tail towards low scores on the scale. A psychologist takes
a random sample of 30 people from the general community and asks them to complete
the SWL questionnaire. The sample mean can be considered to come from a distribution
that is:
a. highly negatively skewed
b. positively skewed to counteract the negative skew
c. normally distributed
d. a sample size of 30 is not large enough to be sure what is the distribution.
Gravetter & Wallnau, section 7.2
5. A researcher wishes to infer a population mean from a sample of 25. She is not
confident about her estimate and wants to be more precise. What would you advise her?
a. her estimate must be accurate, given the sample size of 25
b. as every sample mean is different, she needs to take many samples to be very
precise
c. the central limit theorem assures her that the population mean is the same as her
sample mean
d. if she wants to improve her precision she should use a larger sample size.
Gravetter & Wallnau, section 7.2, 7.3
6. For a normal distribution:
a. 75% of observations are within one standard deviation of the mean
b. 68% of observations are within two standard deviations of the mean
c. 95% of observations are within one standard deviation of the mean
d. none of the above.
Gravetter & Wallnau, section 6.2
7. A person has an IQ with a z-score more than +2.
a. That person is an extreme case. There is a high probability of seeing a z-score
of that size.
b. That person is not considered an extreme case. There is a low probability of
seeing a z-score of that size.
c. That person is not considered an extreme case. There is a high probability of
seeing a z-score of that size.
d. That person is an extreme case. There is a low probability of seeing a z-score of
that size.
Gravetter & Wallnau, section 6.2
8. The normal distribution is:
a. extremely common for actual psychological measures
b. useful for statistical inference because of the Central Limit theorem
c. not at all common in actual psychological measures
d. is common in actual psychology but only when it is skewed.
Gravetter & Wallnau, section 7.1
9. As the sample size gets larger:
a. There is more variability in the population.
b. The standard error increases by a factor related to the sample size.
c. The standard error decreases.
d. The precision of estimation decreases.
Gravetter & Wallnau, section 7.4
10. To estimate a population mean
a. use a sample mean but only if the population distribution is normal.
b. use a sample standard deviation to increase the precision.
c. calculate a standard error and then increase the sample size.
d. use a sample mean, preferably with a sample of reasonable size.
Gravetter & Wallnau, section 7.2
Lecture 2
1. Which option makes the most sense?
a. A sample is a set of individuals selected (usually randomly) from the
population. A population is every possible individual of relevance to the research
question. μ is notation for the mean of the sample (a sample statistic) while M is
for the mean of the population (a population parameter).
b. A sample is a set of individuals selected (usually randomly) from the
population. A population is every possible individual of relevance to the research
question. M is notation for the mean of the sample (a sample parameter) while μ
is for the mean of the population (a population statistic).
c. A population is a set of individuals selected (usually randomly) from the
sample. A sample is every possible individual of relevance to the research
question. M is notation for the mean of the sample (a sample statistic) while μ is
for the mean of the population (a population parameter).
d. A sample is a set of individuals selected (usually randomly) from the
population. A population is every possible individual of relevance to the research
question. M is notation for the mean of the sample (a sample statistic) while μ is
for the mean of the population (a population parameter).
Gravetter & Wallnau, section 1.2
2. A sample of 25 university students is chosen from the general population and IQ is
measured. Mean IQ for the sample is 103. For the general population, mean IQ is 100
with a standard deviation of 15.
a. Because the mean of the sample is higher than the population mean, we can
infer that the mean IQ of university students is significantly higher than that of the
general population.
b. Because the mean IQ of the sample is 0.2 standard deviations above the mean
IQ of the population, we can infer that the mean IQ of university students is
significantly higher than that of the general population.
c. Because the mean IQ of the sample is 0.2 standard deviations above the mean
IQ of the population, we can infer that the mean IQ of university students is NOT
significantly higher than that of the general population.
d. Because the mean IQ of the sample is 1 standard error above the population
mean, we can infer that the mean IQ of university students is NOT significantly
higher than that of the general population.
Gravetter & Wallnau, section 8.3
3. The null hypothesis is:
a. what the researcher believes is true about the data.
b. the hypothesis that says there is no effect to observe.
c. what the researcher believes is true about the population.
d. the hypothesis that says there is likely to be an effect.
Gravetter & Wallnau, section 8.1
4. The alpha-level is:
a. the probability used to define very unlikely samples if the null hypothesis is
true.
b. the probability used to define very unlikely samples if the null hypothesis is
false.
c. the probability used to define likely samples if the null hypothesis is true.
d. the probability used to define likely samples if the null hypothesis is false.
Gravetter & Wallnau, section 8.1
5. In using a z-score of approximately 2 (to be more precise, 1.96) in a single sample z-
test, we are saying that:
a. the alpha level is 5% and we reject the null hypothesis if the probability is
greater than this.
b. the alpha level is 2.5% and we reject the null hypothesis if the probability is
less than this.
c. the alpha level is 5% and we reject the null hypothesis if the probability is less
than this.
d. the alpha level is 2.5% and we reject the null hypothesis if the probability is
greater than this.
Gravetter & Wallnau, section 8.1
6. A researcher is interested in the effects of a drug on physical activity levels. The
researcher has designed a scale for activity levels that in the general population has a
mean of 18 and a standard deviation of 4. On the scale a higher score indicates higher
activity. A random sample of 16 people is given the drug. The mean activity levels of the
sample in the week after the administration of the drug is 15. The null hypothesis is:
a. μ0=18
b. μ0=15
c. μ0=18/√4 = 9
d. μ0= 4/√4 = 1
Gravetter & Wallnau, section 8.3
7. In regard to the research of question 6, assuming an alpha level of 5%, the z-score for
the sample is:
a. 9
b.– 3
c. 1
d. – 3/4
Gravetter & Wallnau, section 8.3
8. In regard to the research of question 6, assuming an alpha level of 5%, the correct
inference is:
a. Reject the null hypothesis. There is evidence from this study that the drug
decreases activity.
b. Do not reject the null hypothesis. There is no evidence from this study that the
drug decreases activity.
c. Reject the null hypothesis. There is evidence from this study that the drug
increases activity.
d. Do not reject the null hypothesis. There is evidence from this study that the
drug decreases activity.
Gravetter & Wallnau, section 8.3
9. What makes the most sense?
a. If there is a high probability, reject the null hypothesis. There is evidence for an
effect.
b. If there is a low probability, reject the null hypothesis. There is evidence for an
effect.
c. If there is a high probability, reject the null hypothesis. There is no evidence for
an effect.
d. If there is a low probability, reject the null hypothesis. There is no evidence for
an effect.
Gravetter & Wallnau, section 8.3
10. A single sample z-test:
a. involves calculating a z-score for the population mean, assuming that the
standard deviation is obtained from the sample. It compares the sample mean with
the population mean.
b. involves calculating a z-score for the sample mean, assuming that the standard
deviation is estimated from the sample. It compares the sample mean with a given
number.
c. involves calculating a z-score for the sample mean. This requires that the
standard deviation of the population be known. It compares the sample mean with
the population mean.
d. involves calculating a z-score for the sample mean. This requires that the
standard deviation of the population be known. It compares the sample mean with
a given number.
Gravetter & Wallnau, section 8.3
Lecture 3
1. What is the difference between a single sample z-test and a single sample t-test?
a. The z-test uses the mean and the t-test uses the standard deviation.
b. The z-test requires knowledge about the population mean, and the t-test does
not.
c. The z-test depends on the size of the sample but the t-test does not.
d. The z-test requires knowledge about the population standard deviation and the
t-test does not.
Gravetter & Wallnau, section 9.1
2. A random sample of 25 university students has a mean IQ of 104 and a standard
deviation of 10. For the general population, mean IQ is 100. A single sample t-test is
conducted to seek evidence whether the mean IQ of students in general is higher than the
general population.
a. The estimated standard error of the mean is 2 and the degrees of freedom are 25.
b. The estimated standard error of the mean is 2 and the degrees of freedom are 24.
c. The estimated standard error of the mean is 3 and the degrees of freedom are 25.
d. The estimated standard error of the mean is 3 and the degrees of freedom are 24.
Gravetter & Wallnau, section 9.1
3. In a single sample t-test the calculated t-statistic for a sample of 4 people is 2.8. A
researcher wishes to decide where this value is significant at a 10% alpha level, using
both tails (i.e. top and bottom) of the t-distribution.
a. df = 3. The t-value is not significant because it is less than 3.182.
b. df = 4. The t-value is significant because it is greater than 2.776.
c. df = 4. The t-value is significant because it is greater than 2.132.
d. df = 3. The t-value is significant because it is greater than 2.353.
Gravetter & Wallnau, section 9.1 (Table 9.1)
4. A sample of 10 children with specific brain injury has a mean IQ of 94.2 and a
standard deviation of 6.2. The null hypothesis is that the population of children with this
brain injury has a mean IQ of 100.
a. The calculated t-value is approximately – 1.9. This is not extreme because it is
less than 2.262, so do not reject the null hypothesis.
b. The calculated t-value is approximately – 2.98. This is extreme because it is
more than 2.262, so reject the null hypothesis.
c. The calculated t-value is approximately – 1.9. This is extreme because it is less
than 2.262, so reject the null hypothesis.
d. The calculated t-value is approximately – 2.98. This is not extreme because it is
more than 2.262, so reject the null hypothesis.
Gravetter & Wallnau, section 9.1 – see also lecture overheads
5. A psychologist has prepared an “Optimism test” that is administered yearly to
graduating students. The test measures how students feel about their futures – the higher
the score, the more optimistic. Last year’s class had a mean score of 15. A sample of 9
students is selected from this year’s class. The sample mean is 10 and the estimated
standard error is 1.14. The psychologist wishes to determine whether there has been a
significant fall in the mean level of optimism compared to last year.
a. The null hypothesis is that mean optimism this year is 10, and the degrees of
freedom are 9.
b. The null hypothesis is that mean optimism this year is 15, and the degrees of
freedom are 9.
c. The null hypothesis is that mean optimism this year is 10, and the degrees of
freedom are 8.
d. The null hypothesis is that mean optimism this year is 15, and the degrees of
freedom are 8.
Gravetter & Wallnau, Chapter 9
6. For the sample in question 5, the t-statistic is
a. 4.39
b.– 4.39
c. 8.77
d. – 8.77
Gravetter & Wallnau, Chapter 9
7. For a sample of 9, based on the t-distribution table, with an alpha of 0.05 (two tails),
the critical value is:
a. 2.262
b. .– 2.262
c. 2.306
d. .– 2.306
Gravetter & Wallnau, Chapter 9
8. For the sample in question 5, at a 5% alpha level the correct inference is:
a. reject the null hypothesis, there is no evidence for a significant difference in
optimism compared to the previous year.
b. do not reject the null hypothesis, there is no evidence for a significant
difference in optimism compared to the previous year.
c. reject the null hypothesis, there is evidence for a significant difference in
optimism compared to the previous year.
d. do not reject the null hypothesis, there is evidence for a significant difference in
optimism compared to the previous year.
Gravetter & Wallnau, Chapter 9
9. The correct way to report the statistics from this result is:
a. t(2.306)=9, p<.05
b. t(9)=2.306, p>.05
c. t(8)= .– 4.39, p<.05
d. t(9)=.05, p<.05
See lecture slides.
10. The z-test cannot be used when:
a. you do not know the population standard deviation
b. when you want to compare the means of two different samples
c. when you want to compare change in a sample across time
d. all of the above
See lecture slides.
Laboratory class 1
1. An IQ scale can be considered:
a. a nominal scale of measurement
b. a numerical scale which has a real zero
c. a discrete measurement scale
d. a continuous scale.
Gravetter & Wallnau, section 1.4
2. Which answer makes the most sense:
a. One of our goals in empirical psychology is to infer information about a
population using a sample. We use sample statistics to estimate population
parameters.
b. One of our goals in empirical psychology is to infer information about a sample
using a population. We use sample statistics as estimates of population parameters.
c. One of our goals in empirical psychology is to infer information about a
population using a sample. We use population statistics as estimates from sample
parameters.
d. One of our goals in empirical psychology is to infer information about
populations and samples. We use population statistics as estimates from sample
parameters.
Gravetter & Wallnau, section 1.2
3. Arrival time in class is approximately normally distributed. For a given lecture, the
mean arrival time is 2 minutes after the advertised start time of the lecture with a standard
deviation of 5 minutes. We expect that:
a. about 5% of students will arrive 8 minutes before the advertised time
b. about 5% of students will arrive 10 minutes before the advertised time
c. about 2.5% of students will arrive 12 minutes after the advertised time
d. about 2.5% of students will arrive 8 minutes after the advertised time
Gravetter & Wallnau, sections 6.2-6.3
4. A wonderful Olympic swimmer wins three gold medals. In the first final, the swimmer
completed in 67 seconds while the mean finishing time was 70 seconds (SD=2 seconds);
in the second final, the swimmer completed in 2minutes, 14 seconds while the mean time
was 2.5 minutes (SD= 10 seconds); in the third final the swimmer completed in 20
minutes while the mean was 23 minutes (SD=45 seconds). Comparing all three finals,
how well did the swimmer perform relative to all other finalists?
a. The swimmer did best in the first final, followed by the second and then the
third.
b. It is impossible to make a comparison
c. The swimmer did best in the third final, and beat the field by slightly more in
the second final than the first.
d. The swimmer did best in the second final, followed by the first and then the
third.
Gravetter & Wallnau, sections 5.2
5. A clinical psychologist devises a new psychological scale that measures foolishness. A
high score on the scale indicates a foolish person. The scale is positively skewed with a
long tail towards the higher scores. The minimum score on the scale is 10, the mean is 20
and the standard deviation is 10.
a. Because of the long tail, there are many people who are foolish and few people
get moderate or low scores.
b. Unusual cases are quite rare, so that we expect 95% of people to have a score
between 0 and 40.
c. Because the standard deviation is one-half of the mean (i.e. around 1.96), the
distribution is normally distributed.
d. There are few people who are foolish and it is not unusual to get moderate or
low scores.
Gravetter & Wallnau, sections 2.4
6. The following are measures of variation in a distribution:
a. Variance, standard deviation, mean, range.
b. Standard deviation, range, mean.
c. Variance, standard deviation, range.
d. Standard deviation, skew, normal, symmetric.
Gravetter & Wallnau, Chapter 4.1-4.3
7. IQ is normally distributed with a mean of 100 and a standard deviation of 15. George
has an IQ of 85. His z-score is:
a. 1.0
b. – 1.0
c. 0.15
d. – 0.85
Gravetter & Wallnau, Chapter 5
8. Neuroticism and extraversion are said to be two important personality dimensions. A
researcher collects data on a small sample of 6 males and 6 females and measures these
two dimensions, labeled as N and E, respectively. Here is some PASW output from the
Explore command:
a. The mean neuroticism score for males in this sample is 33.0, and for females is
33.2.
b. The extraversion scores for males are more widely spread out than for females.
c. Extraversion scores for males are more tightly grouped around the mean than
for females.
d. Neuroticism is highly skewed.
Computer lab class
Descriptives
33.0000 1.12546
30.1069
35.8931
32.9444
32.5000
7.600
2.75681
30.00
37.00
7.00
4.75
.430 .845
-1.572 1.741
33.1667 4.49753
21.6054
44.7279
33.0185
32.5000
121.367
11.01665
20.00
49.00
29.00
21.50
.297 .845
-1.038 1.741
Mean
Lower Bound
Upper Bound
95% Confidence
Interval for Mean
5% Trimmed Mean
Median
Variance
Std. Deviation
Minimum
Maximum
Range
Interquartile Range
Skewness
Kurtosis
Mean
Lower Bound
Upper Bound
95% Confidence
Interval for Mean
5% Trimmed Mean
Median
Variance
Std. Deviation
Minimum
Maximum
Range
Interquartile Range
Skewness
Kurtosis
sex
male
female
E
Statistic Std. Error
9. For the data of question 8, here are the boxplots for extraversion:
a. On average in this sample, females have higher extraversion than males.
b. On average in this sample, males have higher extraversion than females.
c. Female extraversion in this sample has a larger range.
d. There is a significant difference between males and females.
Computer lab class
10. For the data of question 9, here are the boxplots for neuroticism:
a. On average in this sample, females have higher neuroticism scores than
males.
b. On average in this sample, males have higher neuroticism scores than
females.
c. There are more outliers in the male sample.
d. The middle 50% of the data indicates that the similarity between males
and females for this sample is significant.
Computer lab class
femalemale
sex
45.00
40.00
35.00
30.00
25.00
20.00
15.00
10.00
N
Laboratory class 2
1. A repeated measures research design:
a. involves measuring the same construct across two different samples at two time
points
b. involves measuring the same construct across the same sample at two different
time points
c. is analysed using a t-test because it involves comparing a single sample
repeatedly with the population mean (e.g. 100 for IQ)
d. is analysed using a t-test because the null hypothesis is that there is no
difference between the two independent groups across time.
Gravetter & Wallnau, section 11.1, 11.2
2. An independent groups research design
a. involves measuring the same construct across two different samples
b. involves measuring the same construct at two different time points across an
independent sample
c. is analysed using a t-test because it involves comparing the means of two
groups with a given number (.e.g. 100 for IQ)
d. is analysed using a t-test because the null hypothesis is that there is a difference
between the two groups.
Gravetter & Wallnau, section 10.1, 10.2
3. Which answer makes the most sense?
a. Data for an independent groups t-test involves two variables, both continuous
and measured at separate time points. The null hypothesis is that there is no
difference in means across time.
b. Data for an independent groups t-test involves three variables, one continuous
and the other two to indicate which group the participant is in. The null
hypothesis is that there is no difference in means between the two groups.
c. Data for an independent groups t-test involves two variables, one continuous
and the other to indicate which group the participant is in. The null hypothesis is
that there is a difference in means between the two groups.
d. Data for an independent groups t-test involves two variables, one continuous
and the other a grouping variable. The null hypothesis is that there is no
difference in means between the two groups.
Gravetter & Wallnau, chapter 10.
4. A researcher collects data on a sample of 10 children with specific brain injury. The
researcher has a treatment that is intended to increase IQ for these children. Before
treatment, the mean IQ for the sample is 97 with a standard deviation of 5. The mean IQ
for the sample after treatment is 102, also with a standard deviation of 5.
a. The researcher can use a single sample t-test to infer whether prior to treatment
the brain injury has affected IQ relative to the general population, and a repeated
measures t-test to infer whether the treatment improves IQ.
b. The researcher can use an independent groups t-test to infer whether prior to
treatment the brain injury affects IQ relative to the general population, and a
repeated measures t-test to infer whether the treatment improves IQ.
c. The researcher can use a single sample t-test to infer whether prior to treatment
the brain injury affects IQ relative to the general population, and an independent
groups t-test to infer whether the treatment improves IQ.
d. The researcher can use a repeated measures t-test to infer whether prior to
treatment the brain injury affects IQ relative to the general population, and a
single sample t-test to infer whether the treatment improves IQ.
Gravetter & Wallnau, sections 9.2, 10.2, 11.2
5. A psychologist has prepared an “Optimism test” that is administered yearly to
graduating students. The test measures how students feel about their futures – the higher
the score, the more optimistic. At the beginning of their final year, an initial sample of 9
Arts students had a mean score of 15. The researcher was only able to measure a sample
of 9 Commerce students at the end of the year. They had a sample mean of 10.
a. Two single sample t-tests will reveal whether the means differ from 15.
b. A repeated measures t-test is needed to infer whether there is a decline from the
beginning of the year to the end of the year.
c. Because the data is across time and across groups, either a repeated measures or
an independent groups t-test would determine whether there is a difference.
d. An independent groups t-test is needed to infer whether there is a difference
between Arts and Commerce students, leaving to one side the question of the time
of measurement.
Gravetter & Wallnau, Chapter 10.2, 11.2
6. We have a small sample of 10 school children who have experienced a particular type
of head injury. We suppose that the head injury might affect their IQ levels. We wish to
see whether there is enough evidence in the sample to support this conclusion. Most IQ
tests are standardized to have a mean of 100 and a standard deviation of 15, and have a
normal distribution in the general population. We want to know whether the population
of children with this head injury has a mean that is less 100. Here is the PASW output.
a. There is evidence that mean IQ for children with this type of brain injury is
significantly lower than that of the general population (t(9)=0.016, p<.05).
b. There is evidence that mean IQ for children with this type of brain injury is
significantly lower than that of the general population (t(9)=-3.0, p=0.02).
c. There is no evidence that mean IQ for children with this type of brain injury is
lower than that of the general population (t(9)=-3.0, p>.05).
d. There is evidence that mean IQ for children with this type of brain injury is
significantly lower than that of the general population (t(9)=-5.8, p=0.02).
Gravetter & Wallnau, Chapter 9; Computer lab class
7. A student analyses the data from the study described in question 6 to produce the
following output. What is wrong with this analysis?
One-Sample Test
48.352 9 .000 94.20000 89.7928 98.6072IQ
t df Sig. (2-tailed)
Mean
Difference Lower Upper
95% Confidence
Interval of the
Difference
Test Value = 0
a. The null hypothesis is wrong. The null hypothesis population mean should not
be 0.
b. The t-value is too large for the degrees of freedom, so the probability cannot be
assessed.
c. The null hypothesis is not rejected.
d. The mean difference is equal to the mean of the sample.
Gravetter & Wallnau, Chapter 9; Computer lab class
One-Sample Test
-2.977 9 .016 -5.80000 -10.2072 -1.3928IQ
t df Sig. (2-tailed)
Mean
Difference Lower Upper
95% Confidence
Interval of the
Difference
Test Value = 100
8. As a brilliant and innovative cognitive neuropsychologist, you design a world leading
intervention to increase IQ for children with this type of head injury. The intervention
takes to the form of an extended one-on-one training course. You have a small sample of
children. You measure their IQ before and after your intervention
Here is the PASW output from your analysis:
a. Because the probability of 0.024 is small, do not reject the null hypothesis. The
mean difference of 3.1 indicates a significant improvement in IQ due to the
training.
b. Because the t-value of 2.72 is large, do not reject the null hypothesis. The mean
difference of 3.1 indicates a significant improvement in IQ due to the training.
c. Because the probability of 0.024 is small, reject the null hypothesis. The mean
difference of 3.1 indicates a significant improvement in IQ due to the training.
d. Because the t-value of 0.024 is small, reject the null hypothesis. The mean
difference of 3.1 indicates a significant improvement in IQ due to the training.
Gravetter & Wallnau, Chapter 11; Computer lab class
Paired Samples Test
3.1000 .5218 5.6782 2.720 9 .024IQAFTER - IQBEFOPair 1
Mean Lower Upper
95% Confidence
Interval of the
Difference
Paired Differences
t df Sig. (2-tailed)
9. You also investigate your intervention using a control group design. In the treatment
condition, you provide one-on-one training to a sample of 5 children with head injury. In
the control condition, you provide a one-on-one play condition (i.e. no training) to a
different sample of 5 children with head injury.
Here is your PASW output:
a. Because the probability of 0.014 is small, do not reject the null hypothesis. The
mean difference of 3.1 indicates a significant improvement in IQ due to the
training.
b. Because the t-value of 3.1 is large, do not reject the null hypothesis. There is a
significant difference in IQ between the two groups.
c. Because the probability of 0.014 is less than the alpha level, reject the null
hypothesis. There is a significant difference in IQ between the two groups.
d. Because the t-value of 0.94 is large, do not reject the null hypothesis. There is
no significant difference in IQ between the two groups.
Gravetter & Wallnau, Chapter 10; Computer lab class
10. Pick the best option.
a. If a sample mean is expected (i.e. not extreme) assuming a null hypothesis, then
there is evidence that the null hypothesis may not hold. After setting an α-level
(usually 0.05), if the probability of the sample mean is less than α, reject the null
hypothesis.
b. If a sample mean is extreme assuming a null hypothesis, then there is evidence that
the null hypothesis may not hold. After setting an α-level (usually 0.05), if the
probability of the sample mean is more than α, reject the null hypothesis.
c. If a sample mean is extreme assuming a null hypothesis, then there is evidence that
the null hypothesis may not hold. After setting an α-level (usually 0.05), if the
probability of the sample mean is less than α, reject the null hypothesis.
d. If a sample mean is extreme assuming a null hypothesis, then there is no evidence
that the null hypothesis may not hold. After setting an α-level (usually 0.05), if the
probability of the sample mean is less than α, do not reject the null hypothesis.
Gravetter & Wallnau, Chapter 8
Independent Samples Test
.007 .936 3.143 8 .014
3.143 8.000 .014
Equal variances
assumed
Equal variances
not assumed
IQ
F Sig.
Levene's Test for
Equality of Variances
t df Sig. (2-tailed)
t-test for Equality of Means
Laboratory class 3
1. Which answer makes the most sense?
a. In a positive correlation, two variables tend to move in the same direction, so
that an increase in one variable is associated with a decrease in the other.
b. In a negative correlation, two variables tend to move in the same direction, so
that an increase in one variable is associated with a decrease in the other.
c. In a positive correlation, two variables tend to move in the same direction, so
that an increase in one variable is associated with an increase in the other.
d. In a negative correlation, two variables tend to move in the opposite direction,
so that an increase in one variable is associated with an increase in the other.
Gravetter & Wallnau, section 16.1
2. For a large sample, the following is the PASW output for a scatterplot of the
personality dimension of extraversion versus neuroticism:
a. There seems to be a strong positive correlation between the two personality
dimensions.
b. It is impossible to say from the scatterplot whether there is a correlation
between the two personality dimensions.
c. A negative correlation between the two dimensions is suggested by the darker
areas of the scatterplot being in the lower regions of the neuroticism scroes.
d. Although the correlation is not a straight line, there is some evidence for a
curvilinear relationship.
Gravetter & Wallnau, section 16.1
3. For a small sample, the following is the PASW output for a scatterplot of negative
affect versus scores on the Kessler-10 scale. Negative affect is a psychological construct
relating to negative feelings and emotions. The Kessler-10 is a pre-diagnostic instrument
that may indicate issues of psychological wellbeing. For the two variables, higher scores
suggest more negative feelings and lower wellbeing, respectively.
a. The scatterplot suggests a positive correlation. As negative affect decreases,
scores on the Kessler-10 tend to decrease.
b. The scatterplot suggests a negative correlation. As negative affect increases,
scores on the Kessler-10 tend to decrease.
c. The scatterplot suggests a positive correlation. As negative affect increases,
scores on the Kessler-10 tend to decrease.
d. The scatterplot suggests a negative correlation. As negative affect decreases,
scores on the Kessler-10 tend to decrease.
Gravetter & Wallnau, chapter 16.1
4. A researcher finds a negative correlation between optimism and hours watching
television. Which is the best inference?
a. As television watching increases, people tend to become more optimistic.
b. Too much television watching causes more pessimism.
c. In order to cope with increased pessimism, people watch more television rather
than undertake more physical activity.
d. As optimism increases, people tend to spend less time watching television.
Gravetter & Wallnau, section 16.1, 16.3
5. A researcher finds a correlation of – 0.9 between two variables.
a. The negative sign indicates that the relationship between the two variables is
not close to a straight line.
b. Because 0.9 is less than 1, the relationship between the two variables is not
close to a straight line
c. Because – 0.9 is substantially less than 1, the relationship between the two
variables is not close to a straight line.
d. Because 0.9 is close to 1, the relationship between the two variables is close to
a straight line.
Gravetter & Wallnau, section 16.1
6. The following is PASW output for a correlational analysis of the variables for the
personality dimensions of extraversion and agreeableness.
a. The correlation of 0.15 is less than the critical value 0.24, so the correlation is
not significant. There is no evidence of a correlation in the population.
b. The probability of a correlation of 0.15 is 0.24 which is not small, so do not
reject the null hypothesis. There is no evidence of a correlation in the population.
c. The correlation of 0.24 is not large and has a probability of 0.15, so reject the
null hypothesis. There is evidence of a correlation in the population.
d. The correlation of 0.15 is not large and has a probability of 0.24 and degrees of
freedom 63. The correlation is not significant. There is no evidence of a
correlation in the population.
Gravetter & Wallnau, section 16.4; Computer lab class
Correlations
1 .150
.240
63 63
.150 1
.240
63 63
Pearson Correlation
Sig. (2-tailed)
N
Pearson Correlation
Sig. (2-tailed)
N
extraversion
agreeableness
extraversion
agreeabl
eness
7. From the study described in question 6, we may infer the following about the
population:
a. There is a positive correlation that is close to a straight line.
b. There is a negative correlation that is close to a straight line.
c. There is a weak positive correlation.
d. We have no evidence for a correlation
Gravetter & Wallnau, section 16.4
8. When making inferences about correlations from samples to populations:
a. the null hypothesis is that the population correlation is zero.
b. the null hypothesis is that the sample correlation is zero.
c. the null hypothesis is that the population mean correlation is zero.
d. the null hypothesis is that the population correlation is one.
Gravetter & Wallnau, section 16.4
9. We expect the following:
a. the correlation between monthly salary and yearly salary will be 1. But if so a
scatterplot is necessary to see whether the relationship is a straight line.
b. the correlation between monthly salary and yearly salary will be 1/12. A
scatterplot is necessary to see whether the relationship is a straight line.
c. the correlation between monthly salary and yearly salary will be 1. If so the
relationship is a straight line.
d. the correlation between monthly salary and yearly salary will be less than 1.
But, even so, the relationship is a straight line.
Gravetter & Wallnau, section 16.3
10. Which makes the most sense?
a. The Pearson correlation for the sample is represented by r and for the
population by ρ (the Greek letter rho).
b. The Spearman correlation for the sample is represented by r and for the
population by ρ (the Greek letter rho).
c. The Pearson correlation for the sample is represented by ρ (the Greek letter rho)
and for the population by r.
d. The sample statistic is ρ (the Greek letter rho) and the population parameter r.
Gravetter & Wallnau, section 16.4
学霸联盟
