Fill This Form To Receive Instant Help
Fill This Form To Receive Instant Help
Homework answers / question archive / A Human Resources officer is directing a hypothesis test to determine if her company's hiring practices are resulting in disparate impact (that is, unintentional) employment discrimination
A Human Resources officer is directing a hypothesis test to determine if her company's hiring practices are resulting in disparate impact (that is, unintentional) employment discrimination. The null hypothesis for the test is that there is no disparate impact discrimination. The alternate hypothesis is that there is. Considering the relative consequences of Type I and Type II errors, should the significance level (α) be set relatively low (around 0.01) or relatively high (around 0.10)? Explain.
The probability of making a Type I error is α. We set the value of α at the beginning of the test. Thus we can say that if a lower level of significance is set, we have a lesser risk of making the Type I error. The probability of making the Type II error is known as β. The value of β cannot be known directly. For any given test, there is always a lesser risk of making the Type II error, if the sample size is higher. However, the two errors cannot be reduced simultaneously. In fact, for a lower level of α, there is a lesser risk of Type I error and a higher risk of Type II error. In our given problem, studying the consequences of making the Type I and Type II error, a higher α=0.10 should be set. This would lead the researcher to fail to reject the false null hypothesis. That is the researcher would conclude that there is no disparate impact discrimination where there actually is.
