MS-DS Master of Data science MS-DS Master of Data science Exploratory Data Analysis Questions and Answers 2 — Questions and Answers
Question 1: Which visualization is most appropriate for examining the relationship between two continuous variables in exploratory data analysis?
- Scatter plot (Correct answer)
- Bar chart
- Pie chart
- Treemap
Correct answer: Scatter plot
Scatter plots display individual data points along two continuous axes, making correlations and clusters visible.
Question 2: What does a right-skewed distribution indicate about the data?
- The tail extends toward higher values (Correct answer)
- The tail extends toward lower values
- The data is perfectly symmetric
- The data has no outliers
Correct answer: The tail extends toward higher values
Right-skewed (positively skewed) distributions have a longer tail on the right side, meaning most values cluster at lower ranges with some extreme high values.
Question 3: In EDA, what is the primary purpose of computing the interquartile range (IQR)?
- To measure the spread of the middle 50% of data (Correct answer)
- To calculate the mean of the dataset
- To determine the mode of the distribution
- To normalize the data for modeling
Correct answer: To measure the spread of the middle 50% of data
The IQR captures the range between the 25th and 75th percentiles, representing the central spread of the data.
Question 4: Which technique helps identify multicollinearity among features during exploratory analysis?
- Correlation heatmap (Correct answer)
- Histogram
- QQ plot
- Run chart
Correct answer: Correlation heatmap
A correlation heatmap visualizes pairwise correlations between all features, making it easy to spot highly correlated variable pairs.
Question 5: What does a bimodal distribution suggest about the underlying data?
- The data likely contains two distinct subgroups (Correct answer)
- The data follows a normal distribution
- All values are equally probable
- The dataset has too many missing values
Correct answer: The data likely contains two distinct subgroups
A bimodal distribution with two peaks typically indicates the presence of two overlapping subpopulations within the dataset.
Question 6: When performing EDA on a dataset with 50 features, which method efficiently reduces dimensionality for visualization?
- Principal Component Analysis (PCA) (Correct answer)
- Simple linear regression
- Chi-square test
- ANOVA
Correct answer: Principal Component Analysis (PCA)
PCA projects high-dimensional data onto fewer principal components while preserving maximum variance, enabling 2D or 3D visualization.
Which visualization is most appropriate for examining the relationship between two continuous variables in exploratory data analysis?