MS-DS Master of Data science MS-DS Master of Data science Data Wrangling and Preprocessing Questions and Answers 2

Question 1

Which technique is most appropriate for handling multicollinearity among predictor variables during preprocessing?

Accepted Answer

Variance Inflation Factor analysis followed by feature removal

Answer

Min-max normalization

Answer

Label encoding

Answer

Forward fill imputation

Question 2

When working with a dataset that has 40% missing values in a single feature, which approach is generally preferred over simple deletion?

Accepted Answer

Multiple imputation

Answer

Listwise deletion

Answer

Dropping the entire feature immediately

Answer

Replacing all missing values with zero

Question 3

What is the primary purpose of applying a Box-Cox transformation during data preprocessing?

Accepted Answer

To make the data distribution more closely approximate a normal distribution

Answer

To remove duplicate records from the dataset

Answer

To encode categorical variables as integers

Answer

To split the dataset into training and testing sets

Question 4

In a data wrangling pipeline, what does the term 'tidy data' specifically require?

Accepted Answer

Each variable forms a column, each observation forms a row, and each type of observational unit forms a table

Answer

All missing values are removed before analysis

Answer

Column names are standardized to snake_case

Answer

Data is sorted in ascending order by the primary key

Question 5

Which method is best suited for detecting outliers in a multivariate dataset?

Accepted Answer

Mahalanobis distance

Answer

Z-score on individual columns

Answer

Replacing values beyond the IQR

Answer

Histogram visual inspection

Question 6

What is the key advantage of using robust scaling (median and IQR) over standard scaling (mean and standard deviation)?

Accepted Answer

Robust scaling is less affected by outliers in the data

Answer

Robust scaling always produces values between 0 and 1

Answer

Robust scaling converts categorical features to numerical

Answer

Robust scaling eliminates the need for missing value imputation