Research Project(7): Examine Correlation between Quantitative Variables with SAS

Introduction

This post is for the week 3 assignment of the Coursera course Data Analysis Tools by Wesleyan University. It’s the 2nd course for the Data Analysis and Interpretation specialization.

This time I used Addhealth dataset. I examined the relationship between hours watching TV per week and hours playing video or computer games per week. I am also interested in predicting the variability in hours playing games by hours watching TV.

CODE

Output

Scatterplot

Correlation

Interpretation

From the scatter plot, we can see that there is a weak linear relationship between two quantitative variables H1DA8 and H1DA10.

The pearson correlation coeficients also indicated that the linear relationship between these two variables is weak, r=0.28822. Also, the correlation is statistically significant, p < .0001.

RSquared=0.28822^2=0.083

8.3% of the variability in hours playing video or computer games per week can be predicted by hours watching TV per week.