Application of a Two-tailed Pearson’s Correlation
Hypothesis Testing
You are a researcher interested in identifying if there are any correlations between intelligence and driving errors. Using the dataset “assignment 3 correlation,” run a two tailed Pearson’s Correlation for the variables labeled “FSIQ” and “number of driving errors (DRIVERR).”
State the null hypothesis for this test:
Ans: Ho: ρ=0
What is the correlation coefficient for FSIQ and number of driving errors?
Ans: -0.109
What can you conclude from this data? Is there a significant correlation between driving errors and FSIQ?
Ans: The p-value is 0.395, which is not significant. Thus, we can conclude that the correlation is not significant.
Now, let’s say you would like to test your hypothesis that there is a positive correlation between FSIQ and driving errors. Using the same dataset, run a one tailed Pearson’s correlation for the variables labeled “FSIQ” and “number of driving errors (DRIVERR).”
State the null hypothesis for this test:
Ans: Ho: ρ=0
What is the correlation coefficient for FSIQ and number of driving errors?
Ans: -0.109.
What can you conclude from this data? Is there a significant positive correlation between driving errors and FSIQ?
Ans: The p-value is 0.803, which is not significant. Thus, we can conclude that there is no evidence to support the claim that correlation is positive.