Data Science Analysis 2 — Questions and Answers
Question 1: A dataset of household incomes has a mean far higher than its median. What does this indicate?
- Right (positive) skew (Correct answer)
- Left (negative) skew
- A perfectly symmetric distribution
- No variance in the data
Correct answer: Right (positive) skew
When the mean exceeds the median, a long right tail of high values pulls the mean up, indicating positive skew.
Question 2: Which measure of central tendency is most robust to outliers?
- Median (Correct answer)
- Mean
- Standard deviation
- Range
Correct answer: Median
The median depends only on the middle value(s) and is unaffected by extreme observations.
Question 3: You compute the interquartile range (IQR) to detect outliers. Which boundary commonly flags an outlier?
- Below Q1 - 1.5*IQR or above Q3 + 1.5*IQR (Correct answer)
- Below the mean - 1 SD
- Any value above the median
- Below Q1 only
Correct answer: Below Q1 - 1.5*IQR or above Q3 + 1.5*IQR
The standard Tukey rule flags points beyond 1.5*IQR past the first or third quartile.
Question 4: A correlation coefficient between two variables is -0.9. What does this describe?
- A strong negative linear relationship (Correct answer)
- A weak negative relationship
- No relationship
- A strong positive relationship
Correct answer: A strong negative linear relationship
A value near -1 indicates a strong inverse linear association.
Question 5: Which statement about correlation and causation is correct?
- Correlation does not imply causation (Correct answer)
- Correlation always implies causation
- A high correlation proves one variable causes the other
- Causation requires zero correlation
Correct answer: Correlation does not imply causation
Two variables can correlate due to confounders or coincidence without any causal link.
Question 6: When summarizing a categorical variable, which is most appropriate?
- Frequency counts or proportions (Correct answer)
- Mean and standard deviation
- Median and IQR
- A correlation matrix
Correct answer: Frequency counts or proportions
Categorical data is summarized by how often each category occurs, not by arithmetic averages.
Question 7: A boxplot shows the box much wider on the upper half than the lower half. This suggests the data is:
- Skewed toward higher values (Correct answer)
- Perfectly symmetric
- Free of any spread
- Bimodal by definition
Correct answer: Skewed toward higher values
An asymmetric box with a longer upper section indicates skew toward larger values.
Data Science Analysis 2
A dataset of household incomes has a mean far higher than its median.
What does this indicate?