In: Statistics and Probability
| 
 Level of Education  | 
||||
| 
 High School  | 
 Bachelor  | 
 Graduate  | 
 Total  | 
|
| 
 Public Broadcasting  | 
 110  | 
 190  | 
 100  | 
 400  | 
| 
 Commercial Stations  | 
 80  | 
 220  | 
 100  | 
 400  | 
| 
 Total  | 
 190  | 
 410  | 
 200  | 
 800  | 
| 
 Level of Education  | 
||||
| 
 High School  | 
 Bachelor  | 
 Graduate  | 
 Total  | 
|
| 
 Public Broadcasting  | 
 400  | 
|||
| 
 Commercial Stations  | 
 400  | 
|||
| 
 Total  | 
 190  | 
 410  | 
 200  | 
 800  | 
Test at a = .05 to determine if the selection of a TV station is dependent upon the level of education.
a)
| degree of freedom(df) =(rows-1)*(columns-1)=(2-1)*(3-1) = | 2 | |
b)
| Expected | Ei=row total*column total/grand total | High School | Bachelor | Graduate | Total | 
| Public Broadcasting | 95.000 | 205.000 | 100.000 | 400 | |
| Commerical Stations | 95.000 | 205.000 | 100.000 | 400 | |
| total | 190 | 410 | 200 | 800 | 
c)
| Applying chi square test of independence: | 
| chi square χ2 | =(Oi-Ei)2/Ei | High School | Bachelor | Graduate | Total | 
| Public Broadcasting | 2.368 | 1.098 | 0.000 | 3.4660 | |
| Commerical Stations | 2.368 | 1.098 | 0.000 | 3.4660 | |
| total | 4.7368 | 2.1951 | 0.0000 | 6.9320 | |
| test statistic X2 = | 6.9320 | ||||
d)
| for 2 df and 0.05 level , critical value χ2= | 5.991 | |
| since test statistic falls in rejection region we reject null hypothesis | |||
| we have sufficient evidence to conclude that selection of a TV station is dependent upon the level of education. | |||