Handling missing data MCQs January 8, 2026November 18, 2024 by u930973931_answers 15 min Score: 0 Attempted: 0/15 Subscribe 1. What is the primary reason for handling missing data in a dataset? (A) To prevent bias in the analysis and ensure model accuracy (B) To reduce the complexity of the data (C) To create a smaller dataset (D) To increase the number of features in the dataset 2. Which of the following is a technique for handling missing data in a dataset? (A) Data normalization (B) Feature scaling (C) Data imputation (D) Principal component analysis (PCA) 3. Which method replaces missing values with the mean or median of the available data in the column? (A) Backward fill (B) Deletion (C) Forward fill (D) Imputation 4. What is listwise deletion in the context of missing data handling? (A) Deleting rows that contain any missing values (B) Replacing missing values with the mean of the column (C) Filling missing values with zeros (D) Replacing missing data using predictive models 5. Which of the following is NOT a common method for handling missing data? (A) Mean imputation (B) Data deletion (C) Data transformation (D) Forward or backward filling 6. In forward fill, missing data is replaced with: (A) The previous non-missing value in the dataset (B) The mean of the column (C) A predicted value from a machine learning model (D) The value that occurs most frequently in the column 7. What is the potential issue with using mean imputation to handle missing data? (A) It increases the size of the dataset (B) It can introduce bias, especially if the data is not normally distributed (C) It only works for categorical data (D) It requires complex algorithms for imputation 8. What is multiple imputation? (A) A technique where missing values are replaced by the most frequent value (B) A method that replaces missing values with predictions from a model (C) A technique where missing data is simply ignored (D) A process where multiple values are generated for each missing data point to account for uncertainty 9. When should you consider using predictive modeling for missing data? (A) When there are only a few missing values (B) When the dataset is small (C) When you have enough data to estimate the missing values accurately (D) When the missing data is highly correlated with other variables 10. What is the effect of missing data on machine learning models? (A) Missing data has no impact if the dataset is large (B) Missing data can increase the performance of the model (C) Missing data can lead to incorrect model predictions or biased results (D) Missing data can only be handled through feature scaling 11. Which of the following techniques is generally used when the data is missing completely at random (MCAR)? (A) Imputation with the mean or median (B) Predictive modeling (C) Deletion of rows with missing data (D) Binning the data 12. Which of the following is a disadvantage of using mean imputation to handle missing data? (A) It works best for highly skewed data (B) It introduces outliers (C) It can reduce the variance of the dataset (D) It increases the model complexity 13. K-nearest neighbors (KNN) imputation works by: (A) Predicting missing values using the closest available neighbors in the data (B) Filling missing values with the mean of the column (C) Removing the rows with missing values (D) Using the previous value to fill in missing data 14. What is a key assumption when using multiple imputation? (A) The missing values follow a uniform distribution (B) The data is missing completely at random (MCAR) (C) The missing data can be inferred by a single predictive model (D) Missing data does not affect the analysis 15. Which of the following can be a consequence of not handling missing data properly? (A) Faster computation and simpler models (B) Increased accuracy of models (C) Bias in analysis or misleading results (D) Removal of outliers from the dataset