In: Statistics and Probability
In a recent survey of home-buyer preferences, consumers were asked about desired characteristics, such as a wood-burning fireplace, a den/library, and flooring. In particular, each person was asked whether a separate dining room is essential. The sample size and the number who responded Yes to this question are given in the table by geographic region.
a. [11 marks, 2 each, & 1 for value of z] Find a 99% confidence interval for the true proportion of home-buyers who believe a separate dining room is essential in each geographic region. Show all your work in order to get full marks.
b. [4 marks] Which confidence interval in part (a) is the largest? Which confidence interval in part (a) is the smallest? Why? Show all your work in order to get full marks.
Geographic region |
Sample size |
Number who responded Yes |
Northeast |
225 |
180 |
Mideast |
276 |
224 |
South Central |
301 |
232 |
South Atlantic |
454 |
377 |
West |
366 |
304 |
a)
Answer:
Explanation:
Northeast
The confidence interval for the proportion is obtained using the formula,
Where,
Similarly, the confidence interval is obtained for other regions. The calculations are done in excel. The screenshot is shown below,
b)
Answer:
Largest confidence interval: Northeast
Smallest confidence interval: South Atlantic
Reason: The width of the confidence interval depends of the sample size and the proportion estimate.
Explanation:
The confidence interval width is obtained by taking the difference between the upper and lower limits of the confidence interval.
Geographic region | Lower limit | Upper limit | Width |
Northeast | 0.7313 | 0.8687 | 0.1374 |
Mideast | 0.7510 | 0.8722 | 0.1213 |
South Central | 0.7084 | 0.8332 | 0.1248 |
South Atlantic | 0.7850 | 0.8758 | 0.0907 |
West | 0.7801 | 0.8811 | 0.1010 |
From the above table, we can see that the confidence interval for the region Northeast is largest and the confidence interval for the region South Atlantic is smallest.
The width of the confidence interval is defined as the margin of error as shown below,
From the above formula, we can observe that the margin of error depends on,
i) proportion p(1-p) i.e. as the proportion decreases, the margin of error increases.
ii) sample size, i.e. as the sample size decreases, the margin of error increases.
For the Northeast region, the proportion estimate and the sample size both are lower which leads to largest confidence interval.
For the South Atlantic region, the proportion estimate and the sample size both are higher which leads to the smallest confidence interval.