# Need help with hypothesis question

#### maheshhraut

##### New Member
Random samples of employees were drawn in fastfood restaurants where the employer provides a training program. Of a sample of 67 employees who had not completed high school, 11 had participated in a training program provided by their current employer. Of an independent random sample of 113 employees who had completed high school but had not attended college, 27 had participated. Test at 1% level the null hypothesis that the participation rates are same for two groups against the alternative hypothesis that rate is lower for those who have not completed high

#### hlsmith

##### Not a robit
@Stats fan,

You went with the z-test in lieu of a chi-sq test due to the population interpretation of the question?

#### Stats fan

##### Member
I went with the z test because the alternative hypothesis was one sided. If the alternative hypothesis had been two sided (rate is different between the two groups, no specified direction of the difference), you could just as well have performed the chi-squared test. The p value resulting from the chi-squared test is equivalent to the two sided p value resulting from the z test (and X^2 = z^2). However, the z test also allows (more straight forward) one sided testing. Does that make sense?

#### GretaGarbo

##### Human
However, the z test also allows (more straight forward) one sided testing. Does that make sense?
Yes, that makes sense. And, to me, and to most people I believe it is much easier. It is just two proportions and you can take the difference between them and make a confidence interval for the difference and I am sure that almost everybody would understand that. But I think a chi-squared test would be confusing for most people.