Understanding Point Biserial Correlation

What is a point biserial correlation used for?

• To examine the relationship between two dichotomous variables

• To examine the relationship between a nominal variable and a metric variable

• To examine the relationship between a dichotomous variable and a metric variable

• To examine the relationship between two metric variables

Which of the following is an example of a dichotomous variable?

• Age

• Number of siblings

• Gender

• Height of a person

In the example provided, what score is assigned to students who pass the test?

• 2

• 3

• 1

• 0

What is the correlation coefficient obtained in the example for learning hours and test results?

• 0.21

• 0.51

• 0.41

• 0.31

What does a correlation coefficient of 0 indicate?

• No correlation

• A strong negative correlation

• A perfect correlation

• A strong positive correlation

If the correlation coefficient is greater than zero, what type of correlation exists?

• Negative correlation

• No correlation

• Inverse correlation

• Positive correlation

What is the null hypothesis when testing the significance of a correlation coefficient?

• The correlation coefficient is greater than zero

• The correlation coefficient is less than zero

• The correlation coefficient is equal to zero

• The correlation coefficient is not equal to zero

What is the significance level commonly used to determine if a p-value indicates a significant result?

• 0.05

• 0.01

• 0.15

• 0.10

What must be true about the variables if we want to test whether the correlation coefficient is significantly different from zero?

• They must be normally distributed

• They must be dichotomous

• They must be metric

• They must be nominal

What happens if the variables are not normally distributed when testing the correlation coefficient?

• The test statistic t or p-value cannot be interpreted reliably

• The correlation coefficient becomes zero

• The correlation coefficient becomes one

• The test becomes invalid