3. Hypotheses tested
The objective of this study is to identify the attributes of consumers who are targeted and
those who are neglected in mail solicitations by credit card companies. For this purpose, we
test for significant differences between the proportions of targeted and neglected consumers
with various attributes. The hypothesized attributes of the two groups are listed in Table 1.
The individual consumer attributes are grouped under broad characteristics for analytical
purposes. In cases where the targeted or neglected proportion is expected to be significantly
higher, based on the assumption that credit card companies target the most credit-worthy
consumers and neglect the least credit-worthy ones, the null hypothesis is one-sided. For
example, because card companies are expected to target high-income consumers, the null
hypothesis for this attribute, which is expected to be rejected, is that the proportion of
targeted consumers is less than or equal to the proportion of neglected consumers. In each
case, the alternative hypothesis reflects our expectation.
We expect credit card companies to target consumers with greater financial resources,
indicated by high income and net worth, and home ownership, and neglect those who rent
their homes or have other indicators of low financial resources. In the case of binary
attributes, we hypothesize a higher proportion for targeted consumers in one category and for
neglected consumers in the other category. For example, we expect a larger proportion of
targeted consumers to own homes and a higher proportion of neglected consumers to rent
homes. Where attributes have three categories, we hypothesize significant differences only
for the top and bottom categories. For example, we expect a greater proportion of targeted
consumers to have high income and a larger proportion of neglected consumers to have low