Question

Difficulty: HardData Distributions and Measures

An analyst recorded the number of years of experience for 2525 employees at a software company. The distribution of the employees' experience is shown in the table below:

Years of ExperienceNumber of Employees
1155
2288
3366
4444
151522

If the 22 employees with 1515 years of experience are removed from the dataset, which of the following statements is true?

  1. The mean of the dataset will decrease, and the median of the dataset will remain the same.Answer
  2. B
    Both the mean and the median of the dataset will decrease.
  3. C
    The median of the dataset will decrease, and the mean of the dataset will remain the same.
  4. D
    The mean of the dataset will decrease, and the median of the dataset will increase.

Answer

The mean of the dataset will decrease, and the median of the dataset will remain the same.
Removing the two extreme values of 1515 years of experience significantly reduces the sum of the data, causing the mean to decrease from 3.43.4 to approximately 2.392.39. However, the median remains 22 because both the 13th13^{\text{th}} value of the original 2525-element dataset and the 12th12^{\text{th}} value of the new 2323-element dataset fall within the category of 22 years of experience.

Step-by-Step Solution

1
Calculate the initial mean and identify the initial median of the dataset.
Initial mean is 3.43.4 years, and initial median is 22 years.
To establish the baseline values. The total number of employees is 5+8+6+4+2=255 + 8 + 6 + 4 + 2 = 25. The sum of the years of experience is (1×5)+(2×8)+(3×6)+(4×4)+(15×2)=5+16+18+16+30=85(1 \times 5) + (2 \times 8) + (3 \times 6) + (4 \times 4) + (15 \times 2) = 5 + 16 + 18 + 16 + 30 = 85. The initial mean is 8525=3.4\frac{85}{25} = 3.4. Since there are 2525 data points, the median is the 13th13^{\text{th}} data point when ordered. Cumulatively counting the frequencies: the first 55 values are 11, and the next 88 values (positions 66 to 1313) are 22. Therefore, the 13th13^{\text{th}} value is 22.
2
Calculate the new mean and identify the new median after removing the two employees with 1515 years of experience.
New mean is approximately 2.392.39 years, and new median is 22 years.
To find the new measures of center after the outliers are removed. The new total number of employees is 252=2325 - 2 = 23. The new sum of experience is 8530=5585 - 30 = 55. The new mean is 55232.39\frac{55}{23} \approx 2.39. With 2323 data points, the median is the 12th12^{\text{th}} data point when ordered. Cumulatively, the first 55 values are 11, and the next 88 values (positions 66 to 1313) are 22. Therefore, the 12th12^{\text{th}} value is still 22.
3
Compare the initial and new values of the mean and median.
The mean decreases from 3.43.4 to approximately 2.392.39, while the median remains 22.
To determine which option correctly describes the relationship between the changes.

Key Concept

The mean is sensitive to extreme values (outliers) and changes when they are removed. The median is a resistant measure of center and remains unchanged if the middle position of the ordered data stays within the same value class.
Rate this question