In: Statistics and Probability
An advertising firm has decided to ask 93 customers at each of four local shopping malls if they are willing to take part in a market research survey. At αα = 0.10 is there evidence to show that the proportions are not all the same.
| A | B | C | D | |
| Willing | 67 | 68 | 69 | 70 | 
| Not Willing | 26 | 25 | 24 | 23 | 
What are the expected numbers? (round to 3 decimal places)
| A | B | C | D | |
| Willing | ||||
| Not Willing | 
The hypotheses are
H0:pA=pB=pC=pDH0:pA=pB=pC=pD
HA:HA: At least one of the proportions is different. (claim)
Since αα = 0.10 the critical value is 6.251
The test value is: (round to 3 decimal places)
The p-value is (round to 3 decimal places)
So the decision is to
Thus the final conclusion is
Expected numbers for each cell are,
Eij = (Row i Total) * (Column j total) / Grand Total
| A | B | C | D | Total | |
| Willing | (274 * 93)/372 = 68.5 | (274 * 93)/372 = 68.5 | (274 * 93)/372 = 68.5 | (274 * 93)/372 = 68.5 | 274 | 
| No Willing | (98 * 93)/372 = 24.5 | (98 * 93)/372 = 24.5 | (98 * 93)/372 = 24.5 | (98 * 93)/372 = 24.5 | 98 | 
| Total | 93 | 93 | 93 | 93 | 372 | 
The test value is  
where fo and fe are the observed and expected frequencies respectively.

= 0.277
Degree of freedom = (r - 1) * (c - 1) = (2 - 1) * (4 - 1) = 3
P-value = P(
 > 0.277, df
= 3) = 0.964
Since p-value is greater than the significance level of 0.05,
Thus the final conclusion is