Our first step was to perform a Lin Reg t-test to determine the linear relationship between the number of texts received per month and the number of Facebook friends a student has. Our results showed that there was an extremely weak relationship between the two variables. Our coefficient of determination with outliers removed from the data (R-squared) was calculated to be .1, which the relationship between the two variables is almost non-existent. The data that included outliers had a R-squared value.
We then decided to chi square test to find the association between whether a person has a Facebook account and whether they have texting. However, our test was invalid because some of our expected cell counts were less than 5. Some of the cell counts were so small that we were not even able to generate a p-value.
We were quite surprised by the results of our study. We believed that there would be at least a moderate linear relationship between the two variables since both can serve as indications of popularity. We believed that if a person was popular, he or she would have many Facebook friends and receive a large number of texts as well. Obviously, we were incorrect.