Data Preprocessing

What is the formula for IQR?

• Q3 − Q1

• Q1 − Q3

• Q2 − Q1

• Q3 − Q2

If Q1 = 10 and Q3 = 30, what is IQR?

• 10

• 20

• 40

• 15

Which rule is commonly used with IQR to detect outliers?

• ±1.5 * IQR

• ±2 * IQR

• ±3 * IQR

• ±0.5 * IQR

If a value lies below Q1 − 1.5*IQR, it is considered:

• Normal data

• Outlier

• Median

• Missing value

Which library provides a direct function to compute IQR?

• NumPy

• Scipy (iqr())

• Matplotlib

• Pandas

Which visualization best identifies IQR-based outliers?

• Scatter plot

• Boxplot

• Line plot

• Histogram

IQR is resistant to:

• Outliers

• Mean shift

• Scaling

• Skewness

Why is IQR preferred over range?

• Uses only extremes

• Not affected by outliers

• Easier to compute

• Gives mean

Which of the following is NOT a method of handling missing values?

• Deletion

• Imputation

• Interpolation

• Overfitting

What does df.dropna() do in Pandas?

• Replaces NaN with 0

• Removes rows with NaN

• Removes columns only

• Fills with mean