Chapter 11: Modern approaches to theory testing
Quizzes are available to test your understanding of the key concepts covered in each chapter. Click on the quiz below to get started.
1. Should you use significance tests of skew and kurtosis in large samples?
- No, because they are likely to be non-significant even when skew and kurtosis are significantly different from normal.
- No, because they are likely to be significant even when skew and kurtosis are not too different from normal.
- Yes, because large samples produce more accurate results.
- Yes, because large samples add power to the test.
The correct answer is B. No, because they are likely to be significant even when skew and kurtosis are not too different from normal.
2. In a small data sample (N = 20), what can we say about a z-score of 2.37?
- It is significant at p < 0.05
- It is significant at p < 0.001
- It is significant at p < 0.01
- It is non-significant
The correct answer is A. This is because an absolute value greater than 1.96 is significant at p < .05, above 2.58 is significant at p < 0.01 and above 3.29 is significant at p < 0.001
3. Which of the following is true for Cohen’s d?
- The units of measurement of the effect size are in their original form
- It is not affected by sample size
- The effect size works for continuous and categorical data
- It tells us the position of a score relative to the mean
The correct answer is B. Cohen’s d is a standardized measure of the effect size with standard deviations as units of measurements. Unlike p-values, sample sizes do not affect the effect size.
4. A Pearson’s correlation coefficient of zero has been calculated; which of the following is true?
- The two variables are not correlated.
- The two variables are not linearly correlated.
- The two variables are not non-linearly correlated.
- The two variables are strongly correlated.
The correct answer is A Pearson’s correlation coefficient is a measure of the effect size that ranges from -1 (perfect negative relationship) to 1 (perfect positive relationship). A value of 0 indicates the absence of a relationship between two continuous variables or a continuous variable over a variable with two categories.
5. In a given dataset, we have found that the test statistic of two variables normally distributed takes a value of 5.37 and an alpha value ( = 0.05. What can be concluded?
- As the test statistic exceeds the critical value, we can reject the null hypothesis of independence.
- The test statistic is smaller than the critical value and hence we cannot reject the null hypothesis.
- We don’t have enough information to reach a conclusion about the effects on the population.
- The test statistic is larger than the critical value of the X2 (chi-square) distribution with 3 degrees of freedom and hence we reject the null hypothesis.
The correct answer is C. The information provided does not tell us anything about the significance of the test nor provides the value for the standard error or confidence intervals.