Fifty two of a test panel of 175 consumers say that they would buy cereal A if it is presented on the market and 35 of another test panel of 150 consumers say that they would buy cereal B. Construct a 90% confidence interval for the difference between the two population proportions. Give the lower limit.

1 answer

To construct a confidence interval for the difference between two population proportions, we can use the formula:

CI = (p1 - p2) ± Z * sqrt((p1 * (1 - p1) / n1) + (p2 * (1 - p2) / n2))

Where:
- CI is the confidence interval
- p1 and p2 are the proportions of the two populations (52/175 for Cereal A and 35/150 for Cereal B)
- Z is the Z-value for the desired confidence level (90% confidence level corresponds to a Z-value of 1.645)
- n1 and n2 are the sample sizes for the two populations (175 for Cereal A and 150 for Cereal B)

Calculating the confidence interval:

p1 = 52/175 = 0.297
p2 = 35/150 = 0.233
Z = 1.645
n1 = 175
n2 = 150

CI = (0.297 - 0.233) ± 1.645 * sqrt((0.297 * (1 - 0.297) / 175) + (0.233 * (1 - 0.233) / 150))

Calculating the standard error:

SE = sqrt((0.297 * (1 - 0.297) / 175) + (0.233 * (1 - 0.233) / 150))

Substituting the values:

CI = (0.064) ± 1.645 * (0.028)

Calculating the confidence interval:

CI = 0.064 ± 0.046

To find the lower limit, subtract the margin of error from the difference:

Lower limit = 0.064 - 0.046 = 0.018

Therefore, the lower limit of the 90% confidence interval for the difference between the two population proportions is 0.018.