In: Statistics and Probability
One hundred randomly selected subjects from 51,048 subjects were interviewed as a part of the California Health Interview Survey. The table below was constructed from the responses of the 100 subjects. Use a 0.05 significance level to test the claim that for California adults, exercise is independent of gender.
Have you exercised vigorously in the last 7 days?
| YES | NO | |
| MALE | 13 | 34 |
| FEMALE | 15 | 38 |
| Null hypothesis:Ho: Exercise and Gender are independent. |
| alternate hypothesis:Ha: Exercise and Gender are dependent. |
| degree of freedom(df) =(rows-1)*(columns-1)= | 1 | |
| for 1 df and 0.05 level,critical value χ2= | 3.841 | |
| Decision rule : reject Ho if value of test statistic X2>3.841 | ||
| Applying chi square test of independence: |
| Expected | Ei=row total*column total/grand total | Yes | No | Total |
| Male | 13.16 | 33.84 | 47 | |
| Female | 14.84 | 38.16 | 53 | |
| total | 28 | 72 | 100 | |
| chi square χ2 | =(Oi-Ei)2/Ei | Yes | No | Total |
| Male | 0.002 | 0.001 | 0.0027 | |
| Female | 0.002 | 0.001 | 0.0024 | |
| total | 0.0037 | 0.0014 | 0.0051 | |
| test statistic X2= | 0.005 | |||
| since test statistic does not falls in rejection region we fail to reject null hypothesis |
| we do not have have sufficient evidence to conclude that Exercise and Gender are dependent. |