Unoccupied seats on flights cause airlines to lose revenue. It is known from past experience that the standard deviation is 3.2 unoccupied seats. Suppose a large airline wants to estimate the average number of unoccupied seats per flight. Records of 50 flights were randomly selected from the files, and the number of unoccupied seats was noted for each of the sampled flights. The sample mean was 8.4 seats. Suppose a 90% interval estimate for the average number of unoccupied seats was calculated? How large should the sample have been if a margin of error of 0.25 seats was desired?