Bluebook SAT Test One-Variable Data: Distributions and Measures of Center and Spread 6

Question 1

A data set of 9 values has a mean of 12 and a median of 10. If the largest value in the data set is removed, which of the following must be true?

Accepted Answer

The mean decreases, but the median could increase, decrease, or stay the same.

Answer

When the largest value is removed from a data set where mean > median, the mean will decrease (since a high value is pulled out). However, the median depends on the arrangement of the remaining 8 values. The new median is the average of the 4th and 5th values of the remaining sorted set. Depending on those values, the median could go up, down, or stay the same — there is no guarantee of direction. Therefore, only the mean's behavior (decreasing) is certain.

Question 2

The box plots below (described in text) represent two data sets, P and Q. Set P has Q1 = 20, median = 30, Q3 = 50, min = 10, max = 70. Set Q has Q1 = 25, median = 35, Q3 = 45, min = 15, max = 65. Which statement about the two data sets must be true?

Accepted Answer

Set P has a greater interquartile range than Set Q.

Answer

The interquartile range (IQR) is Q3 − Q1. For Set P: IQR = 50 − 20 = 30. For Set Q: IQR = 45 − 25 = 20. Therefore Set P has a greater IQR. The medians differ (30 vs. 35), so choice B is false. Standard deviation cannot be determined from a box plot alone, so choice A is not guaranteed. The mean cannot be determined from a box plot, so choice D is not guaranteed.

Question 3

A symmetric, bell-shaped distribution has a mean of 50 and a standard deviation of 8. A second symmetric distribution has the same mean but a standard deviation of 4. Compared to the second distribution, what percentage of data points in the first distribution fall more than 8 units away from the mean?

Accepted Answer

A greater percentage, because the first distribution has greater spread.

Answer

Being 8 units from the mean of 50 means being outside the interval [42, 58]. In the first distribution (SD = 8), the interval [42, 58] equals [mean − 1SD, mean + 1SD], so about 68% of data falls inside it and roughly 32% outside. In the second distribution (SD = 4), the interval [42, 58] equals [mean − 2SD, mean + 2SD], so about 95% falls inside and only ~5% outside. Since both are described as symmetric and bell-shaped (normal), we can apply empirical rule reasoning: the first distribution has a greater percentage of data more than 8 units from the mean.

Question 4

A data set contains the values {3, 7, 7, 9, 10, 12, 14, 14, 14, 20}. If each value in the data set is multiplied by 3 and then 5 is subtracted, which of the following measures changes?

Accepted Answer

The mean, median, mode, range, and IQR all change.

Answer

When each value is multiplied by 3 and then 5 is subtracted (a linear transformation y = 3x − 5), all measures of center (mean, median, mode) are also transformed by the same rule and thus change. The range and IQR are measures of spread: they scale by the absolute value of the multiplicative factor (3), so Range_new = 3 × Range_old and IQR_new = 3 × IQR_old — both change as well. Therefore all five measures change. The key insight: subtracting a constant shifts all values equally and does not affect range or IQR, but multiplying by 3 does scale range and IQR.

Question 5

A researcher records the ages (in years) of 100 participants. The distribution is heavily right-skewed with several extreme outliers at the high end. Which pair of statistics best describes the center and spread of this distribution, and why?

Accepted Answer

Median and IQR, because they are resistant to the influence of the extreme high values.

Answer

For a right-skewed distribution with extreme outliers, the mean is pulled toward the outliers and gives a misleadingly high estimate of center. The standard deviation is similarly inflated by outliers. The median (middle value) and IQR (middle 50% of data) are resistant — or robust — statistics that are not distorted by extreme values. They give a more accurate picture of the typical value and typical spread for skewed data. The mode and range are poor descriptors of center and meaningful spread, respectively.

Bluebook SAT Practice Test

Bluebook SAT Practice Test

Bluebook SAT Test One-Variable Data: Distributions and Measures of Center and Spread 6