Question 1

A kurtosis value of -2.89 indicates:

Accepted Answer

A) There is a mistake in your calculation. 
B) A flat and light-tailed distribution 
C) A pointy and heavy-tailed distribution 
D) A flat and heavy-tailed distribution 
A) There is a mistake in your calculation. 
B) A flat and light-tailed distribution 
C) A pointy and heavy-tailed distribution 
D) A flat and heavy-tailed distribution B

Question 2

In which of the following situations is the assumption of normality least important?

Accepted Answer

A) If you want only to estimate the parameters of your model. 
B) If you have a small sample. 
C) If you want to construct confidence intervals around the parameter estimates of your model. 
D) If you want to compute significance tests relating to the parameter estimates of your model. 
A) If you want only to estimate the parameters of your model. 
B) If you have a small sample. 
C) If you want to construct confidence intervals around the parameter estimates of your model. 
D) If you want to compute significance tests relating to the parameter estimates of your model. B

Question 3

The central limit theorem tells us:

Accepted Answer

A) In small samples, significance tests can't be trusted. 
B) In small samples, the assumptions of parametric tests matter less. 
C) If the sample is large enough we can assume homogeneity of variance. 
D) If the sample is large enough, the sampling distribution of a parameter will be normal. 
A) In small samples, significance tests can't be trusted. 
B) In small samples, the assumptions of parametric tests matter less. 
C) If the sample is large enough we can assume homogeneity of variance. 
D) If the sample is large enough, the sampling distribution of a parameter will be normal. D

Question 4

What is the Shapiro-Wilk test primarily used for?

Accepted Answer

A) To test for heterogeneity of variance 
B) To test for homogeneity of variance 
C) It is used to test for problematic outliers that could bias the results. 
D) To test whether the distribution of scores deviates from a comparable normal distribution. 
A) To test for heterogeneity of variance 
B) To test for homogeneity of variance 
C) It is used to test for problematic outliers that could bias the results. 
D) To test whether the distribution of scores deviates from a comparable normal distribution.

Question 5

Which of the following symbols does not represent a population parameter?

Accepted Answer

A) $\sigma$ 
B) $\mu$ 
C) SD 
D) $\beta$ 
A) $\sigma$ 
B) $\mu$ 
C) SD 
D) $\beta$

Question 6

Looking at the table below, which of the following statements is the most accurate?

Accepted Answer

A) For the number of hours spent practising, the data are fairly positively skewed. 
B) For the number of hours spent practising, there is not an issue with kurtosis. 
C) For the level of musical skill, the data are heavily negatively skewed. 
D) For the number of hours spent practising, there is an issue with kurtosis. 
A) For the number of hours spent practising, the data are fairly positively skewed. 
B) For the number of hours spent practising, there is not an issue with kurtosis. 
C) For the level of musical skill, the data are heavily negatively skewed. 
D) For the number of hours spent practising, there is an issue with kurtosis.

Question 7

The test statistics we use to assess a linear model are usually _______ based on the normal distribution.

Accepted Answer

A) parametric tests 
B) non-parametric tests 
C) robust 
D) not 
A) parametric tests 
B) non-parametric tests 
C) robust 
D) not

Question 8

Levene's test can be used to measure:

Accepted Answer

A) Whether scores are normally distributed. 
B) Whether scores are independent. 
C) Whether group means are equal. 
D) Whether group variances differ. 
A) Whether scores are normally distributed. 
B) Whether scores are independent. 
C) Whether group means are equal. 
D) Whether group variances differ.

Question 9

The Kolmogorov-Smirnov test can be used to test:

Accepted Answer

A) Whether group means differ. 
B) Whether scores are measured at the interval level. 
C) Whether scores are normally distributed. 
D) Whether group variances are equal. 
A) Whether group means differ. 
B) Whether scores are measured at the interval level. 
C) Whether scores are normally distributed. 
D) Whether group variances are equal.

Question 10

What does the assumption of independence mean?

Accepted Answer

A) This assumption means that you must use an independent design rather than a repeated-measures design. 
B) This assumption means that the residuals in your model are not independent. 
C) This assumption means that the errors in your model are not related to each other. 
D) This assumption means that none of your independent variables are correlated. 
A) This assumption means that you must use an independent design rather than a repeated-measures design. 
B) This assumption means that the residuals in your model are not independent. 
C) This assumption means that the errors in your model are not related to each other. 
D) This assumption means that none of your independent variables are correlated.

Question 11

Which of these variables would be considered not to have met the assumptions of parametric tests based on the normal distribution?

Accepted Answer

A) Heart rate 
B) Gender 
C) Reaction time 
D) Temperature 
A) Heart rate 
B) Gender 
C) Reaction time 
D) Temperature

Question 12

Should you use significance tests of skew and kurtosis in large samples?

Accepted Answer

A) No, because they are likely to be significant even when skew and kurtosis are not too different from normal. 
B) No, because they are likely to be non-significant even when skew and kurtosis are significantly different from normal. 
C) Yes, because large samples produce more accurate results. 
D) Yes, because large samples add power to the test. 
A) No, because they are likely to be significant even when skew and kurtosis are not too different from normal. 
B) No, because they are likely to be non-significant even when skew and kurtosis are significantly different from normal. 
C) Yes, because large samples produce more accurate results. 
D) Yes, because large samples add power to the test.

Question 13

Which of the following transformations is most useful for correcting skewed data?

Accepted Answer

A) Log transformation 
B) Tangent transformation 
C) Arcsine transformation 
D) Cosine transformation 
A) Log transformation 
B) Tangent transformation 
C) Arcsine transformation 
D) Cosine transformation

Question 14

15,467 people rated how much they liked my textbook on a scale of 1 (it is rubbish) to 10 (I love it). The distribution of scores had a skew of 1.23 (SE = 0.65). Which of the following would be the best way to decide whether the skew is problematic? (Hint: Think about what you know about the central limit theorem.)

Accepted Answer

A) Use the Kolmogorov-Smirnov test. 
B) None of the options, because of the large sample size. 
C) See if the z-score is bigger than 1.96 or smaller than -1.96 
D) See if the skew is significant at p < .05. 
A) Use the Kolmogorov-Smirnov test. 
B) None of the options, because of the large sample size. 
C) See if the z-score is bigger than 1.96 or smaller than -1.96 
D) See if the skew is significant at p < .05.

Question 15

A confidence interval (and p-value) associated with a parameter (e.g., the mean, or a b in regression) assumes:

Accepted Answer

A) The residuals are normally distributed. 
B) The sampling distribution of the parameter estimate is normal. 
C) The data are normally distributed. 
D) The data have heterogeneity of variance. 
A) The residuals are normally distributed. 
B) The sampling distribution of the parameter estimate is normal. 
C) The data are normally distributed. 
D) The data have heterogeneity of variance.

Question 16

Is it possible to calculate the skewness of a set of numerical scores?

Accepted Answer

A) Yes. 
B) No. 
C) Only if you have a large sample size. 
D) Only if you have used an independent-measures design. 
A) Yes. 
B) No. 
C) Only if you have a large sample size. 
D) Only if you have used an independent-measures design.

Question 17

Which of the following is not a way to deal with bias in the observed data?

Accepted Answer

A) Watsonize the scores. 
B) Transform the data. 
C) Use bootstrapping. 
D) Trim the data. 
A) Watsonize the scores. 
B) Transform the data. 
C) Use bootstrapping. 
D) Trim the data.

Question 18

A researcher investigating 'Pygmalion in the classroom' measured teachers' perceptions of male and female students' mathematical abilities. She collected teacher ratings of 97 male and female students. Based on the output, what can you say about the data? $\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\quad $$\text { Test of Homogeneity of Variance }$
$\begin{array}{l}
\begin{array}{|ll|r|r|r|r|}
\hline &&{\text { Levene }} & & & \
& &\text { Statistic } &{\text { df1 }} & {\text { df2 }} & {\text { Sig. }} \
\hline \text { Teachers perception of } & \text { Based on Mean } & 4.875 & 1 & 95 & .030 \
\text { mathematical ability } & \text { Based on Median } & 4.616 & 1 & 95 & .034 \
& \begin{array}{l}
\text { Based on Median and } \
\text { with adjusted df }
\end{array} & 4.616 & 1 & 92.069 & .034 \
& \text { Based on trimmed mean } & 4.975 & 1 & 95 & .028 \
\hline
\end{array}
\end{array}$

Accepted Answer

A) The variances of ratings were significantly different for males and females. 
B) Homogeneity of variance can be assumed. 
C) Mean perceptions of male and female students were significantly different. 
D) Mean and median ratings were similar for males and females 
A) The variances of ratings were significantly different for males and females. 
B) Homogeneity of variance can be assumed. 
C) Mean perceptions of male and female students were significantly different. 
D) Mean and median ratings were similar for males and females

Question 19

A standard score is:

Accepted Answer

A) A z-score 
B) The standard deviation of a particular score 
C) The population mean 
D) The variance 
A) A z-score 
B) The standard deviation of a particular score 
C) The population mean 
D) The variance

Question 20

Imagine you conduct a t-test using IBM SPSS and the output reveals that Levene's test for equality of variance is significant. What should you do?

Accepted Answer

A) Interpret the figures in the row labelled 'equal variances not assumed'. 
B) Interpret the figures in the row labelled 'equal variances assumed'. 
C) Conduct a Kruskal-Wallis test instead. 
D) Collect more data. 
A) Interpret the figures in the row labelled 'equal variances not assumed'. 
B) Interpret the figures in the row labelled 'equal variances assumed'. 
C) Conduct a Kruskal-Wallis test instead. 
D) Collect more data.

A kurtosis value of -2.89 indicates:

In which of the following situations is the assumption of normality least important?

The central limit theorem tells us:

What is the Shapiro-Wilk test primarily used for?

Which of the following symbols does not represent a population parameter?

Looking at the table below, which of the following statements is the most accurate?

The test statistics we use to assess a linear model are usually _______ based on the normal distribution.

Levene's test can be used to measure:

The Kolmogorov-Smirnov test can be used to test:

What does the assumption of independence mean?

Which of these variables would be considered not to have met the assumptions of parametric tests based on the normal distribution?

Should you use significance tests of skew and kurtosis in large samples?

Which of the following transformations is most useful for correcting skewed data?

A confidence interval (and p-value) associated with a parameter (e.g., the mean, or a b in regression) assumes:

Is it possible to calculate the skewness of a set of numerical scores?

Which of the following is not a way to deal with bias in the observed data?

A standard score is:

Imagine you conduct a t-test using IBM SPSS and the output reveals that Levene's test for equality of variance is significant. What should you do?

Why Is My Evil Lecturer Forcing Me to Learn Statistics

The Spine of Statistics

The Phoenix of Statistics

The IBM Spss Statistics Environment

Exploring Data With Graphs

Non-Parametric Models

Correlation

Regression

Comparing Two Means

Moderation, Mediation and More Regression

GlM 1: Comparing Several Independent Means

GlM 2: Comparing Means Adjusted for Other Predictors Analysis of Covariance

GlM 3: Factorial Designs

GlM 4: Repeated-Measures Designs

GlM 5: Mixed Designs

Multivariate Analysis of Variance Manova

Exploratory Factor Analysis

Categorical Outcomes: Chi-Square and Loglinear Analysis

Categorical Outcomes: Logistic Regression

Multilevel Linear Models

Filters

Exam 6: The Beast of Bias

A kurtosis value of -2.89 indicates:

In which of the following situations is the assumption of normality least important?

The central limit theorem tells us:

What is the Shapiro-Wilk test primarily used for?

Which of the following symbols does not represent a population parameter?

Looking at the table below, which of the following statements is the most accurate?

The test statistics we use to assess a linear model are usually _______ based on the normal distribution.

Levene's test can be used to measure:

The Kolmogorov-Smirnov test can be used to test:

What does the assumption of independence mean?

Which of these variables would be considered not to have met the assumptions of parametric tests based on the normal distribution?

Should you use significance tests of skew and kurtosis in large samples?

Which of the following transformations is most useful for correcting skewed data?

A confidence interval (and p-value) associated with a parameter (e.g., the mean, or a b in regression) assumes:

Is it possible to calculate the skewness of a set of numerical scores?

Which of the following is not a way to deal with bias in the observed data?

A standard score is:

Imagine you conduct a t-test using IBM SPSS and the output reveals that Levene's test for equality of variance is significant. What should you do?

Why Is My Evil Lecturer Forcing Me to Learn Statistics

The Spine of Statistics

The Phoenix of Statistics

The IBM Spss Statistics Environment

Exploring Data With Graphs

Non-Parametric Models

Correlation

Regression

Comparing Two Means

Moderation, Mediation and More Regression

GlM 1: Comparing Several Independent Means

GlM 2: Comparing Means Adjusted for Other Predictors Analysis of Covariance

GlM 3: Factorial Designs

GlM 4: Repeated-Measures Designs

GlM 5: Mixed Designs

Multivariate Analysis of Variance Manova

Exploratory Factor Analysis

Categorical Outcomes: Chi-Square and Loglinear Analysis

Categorical Outcomes: Logistic Regression

Multilevel Linear Models

Filters