The number of ATM uses is presented as a bar chart as shown in Figures A.1, B.1, and C.1. A bar chart is, “…a way of summarising a set of categorical data. It is often used in exploratory data analysis to illustrate the major features of the distribution of the data in a convenient form. It displays the data using a number of rectangles, of the same width, each of which represents a particular category” (Easton and McColl). The regression line on the scatter plots indicates the degree of correlation between account balance and the number of ATM uses.
The data does not indicate that the number of ATM uses increases when the customer has a debit card (see table D.1). Appendix D indicates that the mean number of ATM transactions declined from 10.35 to 10.23 when the customer had a debit card. The table D.1 in Appendix D also includes the Standard Deviation of the account balance and the number of uses. Standard Deviation is “…a measure of the spread or dispersion of a set of data” (Easton and McColl, 1997). The standard deviation is the area around the mean where 95 percent of the data exists. For example, customers with no card had a mean of 10.35 uses and a standard deviation of 4.32. This indicates that 95 percent of the banks customers who do not have a debit card will use the ATM between 6.03 and 14.67 times.
In addition, the median use of a customer with no card was also higher than the customer that had a card. These results were different from the theory that a debit card would lead to an increase in ATM transaction. However, Figures A.2, B.2, and C.2 show a strong positive correlation between the account balance and the number of ATM transactions as would be expected. This was true for all customers whether they had a debit card or not.
Data could be collected through a variety of mechanisms that each have their strength and weaknesses.