In order to conduct a chi-square analysis one needs to run a chi-square test. In R the way to run a chi-square test is using the chi-square function, chisq.test( , ). This function will run a chi-squared test between whatever two tables are chosen.
In Lab #8 we ran a chi-squared test between ‘Household_value’ and ‘Donation’. By using the function mentioned above we are able to receive different pieces of helpful information. The X-squared value is the difference between the expected and observed frequencies of the outcomes for the variables. The df is equal to degrees of freedom. The p-value helps us understand if the null hypothesis is to be rejected or accepted. Below is our interpretation of the test we conducted.
We received a warning message because there are many elements in each of the buckets. The p-value, 0.09246, is equal to the likelihood that the distribution would have occurred by chance. Since the p-value is greater than .05 it is likely that this distribution occurred by chance and we cannot reject the null hypothesis and thus cannot conclude that there is a relationship between the two variables.
Thinking about the results of the test along with the variables themselves our findings make sense. The value of a person’s home has no indication as to how much that person may donate. Some could argue a person with a home of higher value has more money and is more likely to donate more money. This is a fair point but just because someone has lots of money doesn’t mean they are going to be inclined to donate. One could speculate over and over again but there is no undisputed correlation between the two variables and this is shown through our data analysis.
Leave a Reply