Deck 7: Correlational Research

Question 1

As the reliability of a measure decreases, the magnitude of the correlations between that measure and other measures

A)decreases.
B)increases.
C)remains the same.
D)approaches 1.00.

Answer 1

A

Question 2

Which of the following correlation coefficients reflects the strongest relationship between two variables?

A)+)41
B)-)55
C)+)50
D)- .30

Answer 2

B

Question 3

The correlation between people's height and weight is

A)positive.
B)negative.
C)zero.
D)perfect.

Answer 3

A

Question 4

A researcher obtained a correlation of +.52 between Variable A and Variable B. What is the best interpretation of this correlation?

A)As scores on A increase, scores on B tend to increase.
B)Scores on A can be perfectly predicted from scores on B.
C)As scores on A decrease, scores on B tend to increase.
D)As scores of A increase, scores on B tend to decrease.

Question 5

A correlation of +.90 is _________ times as strong as a correlation of +.30.

A)3
B)9
C)30
D)60

Question 6

On a scatterplot, a correlation of -1.00 appears as a

A)straight line that slopes upward to the right.
B)horizontal straight line.
C)curved line.
D)straight line that slopes downward to the right.

Question 7

When a correlation is statistically significant, we know that it

A)is large.
B)accounts for more than 90% of the variance.
C)is very unlikely to be zero.
D)is important.

Question 8

When plotted on x- and y-axes, a correlation coefficient of .00 appears as a

A)line that slopes upward to the right.
B)horizontal line.
C)random array of scattered points.
D)vertical line.

Question 9

The correlation between self-esteem and shyness is

A)positive.
B)negative.
C)zero.
D)perfect.

Question 10

If the partial correlation between Variables X and Y is equal to the Pearson correlation between X and Y,

A)the correlation between X and Y is statistically significant.
B)X and Y are probably causally related.
C)the range of scores on X and Y is probably restricted.
D)the variable that was partialed out does not account for the correlation between X and Y.

Question 11

If the correlation between two variables is .00, we should conclude that

A)the variables are unrelated.
B)the error variance is excessive.
C)one variable can be predicted from the other.
D)no linear relationship exists between the variables.

Question 12

Having found that people from similar socioeconomic backgrounds are more likely to become friends than people from different backgrounds, a researcher wanted to test the hypothesis that this effect is due to the fact that people from the same socioeconomic background are more likely to share similar attitudes. What could the researcher use to examine this hypothesis?

A)Coefficient of determination
B)Partial correlation
C)A scatterplot
D)Pearson correlation

Question 13

A correlation coefficient of a given magnitude is more likely to be statistically significant when

A)the sample size is small rather than large.
B)the error variance is large rather than small.
C)the coefficient of determination is near zero.
D)it is based on a large rather than a small number of scores.

Question 14

Which of the following can artificially deflate the magnitude of a correlation coefficient?

A)Having a large number of participants
B)On-line outliers
C)Restricted range of scores
D)High reliability of the measures

Question 15

A partial correlation is

A)based on only a portion of a sample.
B)generally larger than the Pearson correlation.
C)the correlation between two variables with the influence of other variables removed.
D)a correlation in which the influence of error variance has been eliminated.

Question 16

Why should a researcher not interpret a correlation that is not statistically significant?

A)It is based on too few participants.
B)The correlation in the population is likely to be zero.
C)Correlation does not imply causality.
D)The data are likely to contain outliers.

Question 17

The formula for the correlation coefficient, as we know it today, was devised by

A)Gibson.
B)Edgeworth.
C)Pearson.
D)Galton.

Question 18

Most correlational research satisfies which of the following criteria for determining whether one variable causes another?

A)Directionality
B)Covariation
C)Determination
D)Elimination of extraneous variables

Question 19

The coefficient of determination is

A)the amount of error variance in a correlation coefficient.
B)the square root of the correlation coefficient.
C)the proportion of variance in one variable that is accounted for by another.
D)an index of negative correlation.

Question 20

On a scatterplot, a correlation coefficient of +1.00 appears as a

A)line that slopes upward to the right.
B)horizontal line.
C)random array of scattered points.
D)vertical line.

Question 21

If a significant correlation is found between X and Y, that means

A)X may cause Y.
B)Y may cause X.
C)a third variable may cause both X and Y.
D)that all of these answers are correct.

Question 22

Distinguish between a positive and a negative correlation. Draw what a positive versus a negative correlation might look like on a scatterplot.

Question 23

When one's data are on an ordinal scale of measurement, a _________ correlation should be used.

A)rank-order
B)point biserial
C)phi
D)partial

Question 24

A researcher predicts that variable X has a positive relationship with variable Y. This is a

A)directional hypothesis.
B)nondirectional hypothesis.
C)positive hypothesis.
D)negative hypothesis.

Question 25

Why can we not infer causality from correlation?

Question 26

What is an outlier? What effect do outliers have on correlation coefficients?

Question 27

A researcher is correlating gender (male/female)with whether adolescents have had sexual intercourse (no/yes). What kind of correlation should he use?

A)Rank-order
B)Partial
C)Phi
D)Point biserial

Question 28

What is a spurious correlation?

Question 29

The correlation between anxiety and depression is +.45. Interpret this correlation.

Question 30

What does a correlation of .00 indicate?

Question 31

What is a partial correlation?

Question 32

Discuss three factors that can distort the value of a correlation coefficient.

Question 33

Why is it important to examine the scatterplot of the relationship between two variables when doing correlational research?

Question 34

Research shows people tend to like attractive individuals more than unattractive ones. Imagine you think this effect occurs because people assume attractive people are friendlier than unattractive people. Explain how you would use partial correlation to test whether inferred friendliness mediates the relationship between physical attractiveness and liking.

Question 35

Why do researchers test the statistical significance of the correlations they obtain?

Question 36

If the correlation between two variables is .40, what is the coefficient of determination? What does the coefficient of determination indicate in this case?

Question 37

Imagine you obtain a correlation coefficient of -.45 between two variables but find the correlation is not statistically significant. How would you interpret this correlation?

Question 38

What is the coefficient of determination, and why is it important?