# Research Methods and Statistics in Psychology

## Student Resources

# Chapter 9: Examining Relationships between Variables: Correlation

1. Which of the following statements is true? [TY9.1

- A negative correlation is the same as no correlation.
- Scatterplots are a very poor way to show correlations.
- If the points on a scatterplot are close to a straight line there will be a positive correlation.
- Negative correlations are of no use for predictive purposes.
- None of the above.

**Answer:** E

2. If a calculation of Pearson’s *r *yields a value of −.96, which of the following statements is *false*? [TY9.2]

- The observed correlation between variables is negative.
- There is a small amount of negative covariance between variables relative to random error.
- A high score on one variable is associated with a low score on the other.
- This correlation is useful for predictive purposes.
- Points on a scatterplot would resemble a straight line.

**Answer:** B

3. As part of a psychology assignment Kate has to calculate Pearson’s *r *to measure the strength of association between two variables. She finds that *r = *−*.*2 and that this is significant at her selected alpha level of .05. What should she conclude? [TY9.3]

- That there is a significant but small relationship between the two variables.
- That there is a non-significant but large relationship between the variables.
- That there is a significant and moderate relationship between the variables.
- That the two variables are unrelated.
- That variation in one variable is associated with most of the variation in the other.

**Answer:** A

4. The correlational fallacy refers to which of the following? [TY9.4]

- The idea that a correlation can be statistically significant without being psychologically meaningful.
- The idea that a strong correlation between variables does not mean that one predicts the other.
- The idea that a correlation between variables does not mean that one variable is responsible for variation in the other.
- The idea that correlation does not justify prediction.
- Both (a) and (c)

**Answer:** C

5. A group of researchers conducts some research in which they identify a significant positive correlation (*r* = .42) between the number of children people have and their life satisfaction. Which of the following is it inappropriate to conclude from this research? [TY9.5]

- That having children makes people more satisfied with their life.
- That someone who has children is likely to be happier than someone who does not.
- That the causes of life satisfaction are unclear.
- That the consequences of having children are unclear.
- That it is possible to predict someone’s life happiness partly on the basis of the number of children they have.

**Answer:** A

6. Which of the following statements is true of the problem of restricted range? [TY9.6]

- Restricted range can reduce the size of correlations.
- Restricted range can lead to a violation of the assumption of bivariate normality.
- Restricted range can produce regression to the mean.
- All of the above.
- Answers (a) and (b) only.

**Answer:** D

7. If an experimenter observes a correlation of −1 between two variables, which of the following is *false*? [TY9.7]

- One variable is completely predictive of the other.
- One variable is completely responsible for variation in the other.

- Knowledge of the value of one variable allows one to know with certainty the value of the other.

- A higher score on one variable is associated with a lower score on the other.
- All the variation in one variable is associated with variation in the other.

**Answer:** B

8. If the correlation between people’s wealth and a measure of their psychological well-being is .40, how much of the variation in their scores on the well-being measure will be associated with variation in their wealth? [TY9.8]

- 60%
- 40%
- 16%
- 4%
- It is impossible to say without information about how psychological well-being is defined.

**Answer:** C

9. A researcher conducts some research in which they identify a significant positive correlation (*r* = .42) between the number of children a person has and their life satisfaction. Which of the following is it **inappropriate** to conclude from this research?

- That having children makes people more satisfied with their life.
- That someone who has children is likely to be more happy than someone who doesn't.
- That the causes of life satisfaction are unclear.
- That the consequences of having children are unclear.
- That it is possible to predict someone's life happiness partly on the basis of the number of children they have.

**Answer:** A

10. A researcher conducts a survey with 221 participants who each complete 24 measures designed to assess the impact of social and psychological factors (such as demands, social support and role clarity) on stress in the workplace. As part of her analysis she investigates the correlations between pairs of these variables. How many degrees of freedom will her analysis have?

- 221
- 220
- 219
- 24
- 23

**Answer:** C

11. “A graph plotting the scores on one variable against the scores on another.” What type of graph is this a glossary definition of?

- A line graph
- A bar graph
- A scatterplot
- An angiogram
- A scattergram

**Answer:** C

12. “A relationship between two variables that can be described by a straight line. The equation for such a line is *y = a *+ *bx*, where *b *is the slope of the line (its gradient) and *a *is the *y *intercept (where it cuts the vertical axis).” Which type of relationship is this a glossary definition of?

- A straight-line relationship
- An
*a + b*relationship - A
*bx*relationship - A curvilinear relationship
- A short-term relationship

**Answer:** A

13. “A measure of the degree of linear association between two variables.” What is this a glossary definition of?

- A correlation coefficient.
- A covariance coefficient.
- Covariance.
- A product-moment coefficient.
- A linear coefficient.

**Answer:** A

14. “The amount of variation in one variable associated with variation in another variable (or variables). In the bivariate case this is given by *r*^{2}.” What is this a glossary definition of?

- Variance.
- Covariance.
- Common variance.
- Linear correlation.
- Estimated variance.

**Answer:** C

15. “A barrier to the correct interpretation of results that arises when the range of scores is limited because they are clustered in the region of the maximum scale value.” What specific type of effect is this a glossary definition of?

- Restricted range effect.
- Maximum value effect.
- Floor effect.
- Ceiling effect.
- Doppler effect

**Answer:** D