DSE Exploratory Data Analysis Techniques 3 — Questions and Answers
Question 1: Which plot is most appropriate for visualizing the joint distribution of two continuous variables along with their marginal distributions?
- Box plot
- Joint plot (with marginal histograms) (Correct answer)
- Stacked bar chart
- Parallel coordinates plot
Correct answer: Joint plot (with marginal histograms)
A joint plot displays a scatter or density plot in the center with marginal histograms or KDE curves along each axis, showing both joint and individual distributions.
Question 2: You notice that a numeric column has values ranging from 1 to 1,000,000 with most values under 1,000. Which transformation would best reveal structure in the lower range?
- Square root transformation
- Logarithmic transformation (Correct answer)
- Z-score normalization
- Min-max scaling
Correct answer: Logarithmic transformation
A log transformation compresses large values while expanding small values, making structure in the dense lower range visible without losing the high-end variation.
Question 3: What does a high kurtosis value (leptokurtic distribution) indicate about a dataset?
- The data is uniformly distributed
- The distribution has heavy tails and a sharp peak (Correct answer)
- The distribution is perfectly symmetric
- The data has low variance
Correct answer: The distribution has heavy tails and a sharp peak
Leptokurtic distributions have excess kurtosis greater than 0, indicating heavier tails and more frequent extreme values than a normal distribution.
Question 4: Which EDA technique would you use to detect multicollinearity among predictor variables before modeling?
- Histogram of the target variable
- Correlation matrix or variance inflation factors (Correct answer)
- Box plot of each predictor
- Scatter plot of target vs. one predictor
Correct answer: Correlation matrix or variance inflation factors
A correlation matrix reveals linear dependencies between predictors, and VIF quantifies how much one predictor's variance is explained by others.
Question 5: In EDA, what is a 'rug plot'?
- A 2D heatmap showing frequency of value pairs
- Tick marks along an axis showing individual data point locations (Correct answer)
- A plot that highlights missing values in a dataset
- A smoothed density curve over a histogram
Correct answer: Tick marks along an axis showing individual data point locations
A rug plot places short vertical tick marks along an axis at each data point's position, showing the actual distribution of individual observations.
Question 6: When should you prefer a log scale on a histogram's x-axis?
- When the variable has negative values
- When the variable spans several orders of magnitude (Correct answer)
- When the distribution is perfectly normal
- When the sample size is small
Correct answer: When the variable spans several orders of magnitude
A log scale is ideal for variables spanning several orders of magnitude (e.g., income, population) so that all ranges are visually represented proportionally.
Question 7: What does the Interquartile Range (IQR) measure?
- The range of the entire dataset
- The spread of the middle 50% of the data (Correct answer)
- The distance between the mean and one standard deviation
- The difference between the maximum and minimum outliers
Correct answer: The spread of the middle 50% of the data
IQR = Q3 − Q1 and captures the spread of the central half of the data, making it robust to extreme outliers.
DSE Exploratory Data Analysis Techniques 3
Which plot is most appropriate for visualizing the joint distribution of two continuous variables along with their marginal distributions?